| { |
| "schema_version": 3, |
| "title": "RISE Leaderboard", |
| "benchmarks": [ |
| { |
| "id": "risebench-plusplus", |
| "name": "RISEBench++", |
| "case_count": 1000, |
| "available_result_languages": [ |
| "en", |
| "zh" |
| ], |
| "accuracy_unit": "%", |
| "metric_unit": "/100", |
| "score_decimals": 1, |
| "default_sort": "total", |
| "dimensions": [ |
| { |
| "key": "temporal", |
| "label": "Temporal", |
| "description": "Infer how a scene changes over time." |
| }, |
| { |
| "key": "causal", |
| "label": "Causal", |
| "description": "Reason about causes, actions, and their consequences." |
| }, |
| { |
| "key": "spatial", |
| "label": "Spatial", |
| "description": "Reason about spatial relationships and transformations." |
| }, |
| { |
| "key": "logical", |
| "label": "Logical", |
| "description": "Apply explicit rules, patterns, and logical constraints." |
| }, |
| { |
| "key": "counterfactual", |
| "label": "Counterfactual", |
| "description": "Visualize outcomes under hypothetical or contrary-to-fact conditions." |
| }, |
| { |
| "key": "hybrid", |
| "label": "Hybrid", |
| "description": "Combine reasoning across three to five successive editing instructions." |
| } |
| ], |
| "metrics": [ |
| { |
| "key": "instruction_reasoning", |
| "label": "Instruction Reasoning", |
| "description": "Whether the edit realizes the intended reasoning outcome." |
| }, |
| { |
| "key": "appearance_consistency", |
| "label": "Appearance Consistency", |
| "description": "Whether content that should remain unchanged is preserved." |
| }, |
| { |
| "key": "visual_plausibility", |
| "label": "Visual Plausibility", |
| "description": "Visual quality and plausibility; logical tasks are excluded." |
| } |
| ], |
| "accuracy_columns": [ |
| { |
| "key": "temporal", |
| "label": "Temporal", |
| "description": "Infer how a scene changes over time." |
| }, |
| { |
| "key": "causal", |
| "label": "Causal", |
| "description": "Reason about causes, actions, and their consequences." |
| }, |
| { |
| "key": "spatial", |
| "label": "Spatial", |
| "description": "Reason about spatial relationships and transformations." |
| }, |
| { |
| "key": "logical", |
| "label": "Logical", |
| "description": "Apply explicit rules, patterns, and logical constraints." |
| }, |
| { |
| "key": "counterfactual", |
| "label": "Counterfactual", |
| "description": "Visualize outcomes under hypothetical or contrary-to-fact conditions." |
| }, |
| { |
| "key": "hybrid", |
| "label": "Hybrid", |
| "description": "Combine reasoning across three to five successive editing instructions." |
| }, |
| { |
| "key": "single", |
| "label": "Single", |
| "description": "Accuracy on single-image cases." |
| }, |
| { |
| "key": "multi", |
| "label": "Multi", |
| "description": "Accuracy on multi-image cases. Not evaluated for models without multi-image support." |
| }, |
| { |
| "key": "total", |
| "label": "Total", |
| "description": "Accuracy on the complete benchmark. Not evaluated for single-image-only models." |
| } |
| ], |
| "subcategory_columns": [ |
| { |
| "key": "temporal_common_sense_knowledge", |
| "label": "Common-Sense Knowledge", |
| "dimension": "temporal", |
| "case_count": 85, |
| "multi_image_case_count": 0, |
| "code": "CSK", |
| "description": "Temporal · Common-Sense Knowledge — accuracy (%)" |
| }, |
| { |
| "key": "temporal_context_knowledge", |
| "label": "Context Knowledge", |
| "dimension": "temporal", |
| "case_count": 52, |
| "multi_image_case_count": 28, |
| "code": "CtxK", |
| "description": "Temporal · Context Knowledge — accuracy (%)" |
| }, |
| { |
| "key": "temporal_disciplinary_knowledge", |
| "label": "Disciplinary Knowledge", |
| "dimension": "temporal", |
| "case_count": 63, |
| "multi_image_case_count": 4, |
| "code": "DK", |
| "description": "Temporal · Disciplinary Knowledge — accuracy (%)" |
| }, |
| { |
| "key": "causal_common_sense_knowledge", |
| "label": "Common-Sense Knowledge", |
| "dimension": "causal", |
| "case_count": 80, |
| "multi_image_case_count": 1, |
| "code": "CSK", |
| "description": "Causal · Common-Sense Knowledge — accuracy (%)" |
| }, |
| { |
| "key": "causal_context_knowledge", |
| "label": "Context Knowledge", |
| "dimension": "causal", |
| "case_count": 40, |
| "multi_image_case_count": 2, |
| "code": "CtxK", |
| "description": "Causal · Context Knowledge — accuracy (%)" |
| }, |
| { |
| "key": "causal_disciplinary_knowledge", |
| "label": "Disciplinary Knowledge", |
| "dimension": "causal", |
| "case_count": 80, |
| "multi_image_case_count": 5, |
| "code": "DK", |
| "description": "Causal · Disciplinary Knowledge — accuracy (%)" |
| }, |
| { |
| "key": "spatial_relation", |
| "label": "Relation", |
| "dimension": "spatial", |
| "case_count": 106, |
| "multi_image_case_count": 6, |
| "code": "Rel.", |
| "description": "Spatial · Relation — accuracy (%)" |
| }, |
| { |
| "key": "spatial_structure", |
| "label": "Structure", |
| "dimension": "spatial", |
| "case_count": 94, |
| "multi_image_case_count": 12, |
| "code": "Struct.", |
| "description": "Spatial · Structure — accuracy (%)" |
| }, |
| { |
| "key": "logical_explicit_rule_deduction", |
| "label": "Explicit Rule Deduction", |
| "dimension": "logical", |
| "case_count": 123, |
| "multi_image_case_count": 0, |
| "code": "ERD", |
| "description": "Logical · Explicit Rule Deduction — accuracy (%)" |
| }, |
| { |
| "key": "logical_implicit_pattern_induction", |
| "label": "Implicit Pattern Induction", |
| "dimension": "logical", |
| "case_count": 77, |
| "multi_image_case_count": 20, |
| "code": "IPI", |
| "description": "Logical · Implicit Pattern Induction — accuracy (%)" |
| }, |
| { |
| "key": "counterfactual_counterfactual_imagination", |
| "label": "Counterfactual Imagination", |
| "dimension": "counterfactual", |
| "case_count": 70, |
| "multi_image_case_count": 0, |
| "code": "CFI", |
| "description": "Counterfactual · Counterfactual Imagination — accuracy (%)" |
| }, |
| { |
| "key": "counterfactual_anomaly_correction_and_generation", |
| "label": "Anomaly Correction and Generation", |
| "dimension": "counterfactual", |
| "case_count": 30, |
| "multi_image_case_count": 0, |
| "code": "ACG", |
| "description": "Counterfactual · Anomaly Correction and Generation — accuracy (%)" |
| } |
| ], |
| "task_type_columns": [ |
| { |
| "key": "T01", |
| "code": "T01", |
| "label": "Life Progression", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 24, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Life Progression — accuracy (%)" |
| }, |
| { |
| "key": "T02", |
| "code": "T02", |
| "label": "Material Transformation", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 9, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Material Transformation — accuracy (%)" |
| }, |
| { |
| "key": "T03", |
| "code": "T03", |
| "label": "Natural Environmental Changes", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 13, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Natural Environmental Changes — accuracy (%)" |
| }, |
| { |
| "key": "T04", |
| "code": "T04", |
| "label": "Physical Aging", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 20, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Physical Aging — accuracy (%)" |
| }, |
| { |
| "key": "T05", |
| "code": "T05", |
| "label": "Social Activities", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 8, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Social Activities — accuracy (%)" |
| }, |
| { |
| "key": "T06", |
| "code": "T06", |
| "label": "Tool Evolution", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 7, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Tool Evolution — accuracy (%)" |
| }, |
| { |
| "key": "T07", |
| "code": "T07", |
| "label": "Urban Evolution", |
| "dimension": "temporal", |
| "subcategory": "temporal_common_sense_knowledge", |
| "case_count": 4, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Urban Evolution — accuracy (%)" |
| }, |
| { |
| "key": "T08", |
| "code": "T08", |
| "label": "Temporal State Transition", |
| "dimension": "temporal", |
| "subcategory": "temporal_context_knowledge", |
| "case_count": 15, |
| "multi_image_case_count": 4, |
| "description": "Temporal · Temporal State Transition — accuracy (%)" |
| }, |
| { |
| "key": "T09", |
| "code": "T09", |
| "label": "Precise Temporal Localization", |
| "dimension": "temporal", |
| "subcategory": "temporal_context_knowledge", |
| "case_count": 14, |
| "multi_image_case_count": 2, |
| "description": "Temporal · Precise Temporal Localization — accuracy (%)" |
| }, |
| { |
| "key": "T10", |
| "code": "T10", |
| "label": "Position Change", |
| "dimension": "temporal", |
| "subcategory": "temporal_context_knowledge", |
| "case_count": 15, |
| "multi_image_case_count": 14, |
| "description": "Temporal · Position Change — accuracy (%)" |
| }, |
| { |
| "key": "T11", |
| "code": "T11", |
| "label": "Action Sequence", |
| "dimension": "temporal", |
| "subcategory": "temporal_context_knowledge", |
| "case_count": 8, |
| "multi_image_case_count": 8, |
| "description": "Temporal · Action Sequence — accuracy (%)" |
| }, |
| { |
| "key": "T12", |
| "code": "T12", |
| "label": "Physics", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 4, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Physics — accuracy (%)" |
| }, |
| { |
| "key": "T13", |
| "code": "T13", |
| "label": "Chemistry", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 8, |
| "multi_image_case_count": 4, |
| "description": "Temporal · Chemistry — accuracy (%)" |
| }, |
| { |
| "key": "T14", |
| "code": "T14", |
| "label": "Biology", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 9, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Biology — accuracy (%)" |
| }, |
| { |
| "key": "T15", |
| "code": "T15", |
| "label": "Astronomy", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 12, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Astronomy — accuracy (%)" |
| }, |
| { |
| "key": "T16", |
| "code": "T16", |
| "label": "Geography", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 18, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Geography — accuracy (%)" |
| }, |
| { |
| "key": "T17", |
| "code": "T17", |
| "label": "History", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 5, |
| "multi_image_case_count": 0, |
| "description": "Temporal · History — accuracy (%)" |
| }, |
| { |
| "key": "T18", |
| "code": "T18", |
| "label": "Medicine", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 4, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Medicine — accuracy (%)" |
| }, |
| { |
| "key": "T19", |
| "code": "T19", |
| "label": "Computer Science", |
| "dimension": "temporal", |
| "subcategory": "temporal_disciplinary_knowledge", |
| "case_count": 3, |
| "multi_image_case_count": 0, |
| "description": "Temporal · Computer Science — accuracy (%)" |
| }, |
| { |
| "key": "C01", |
| "code": "C01", |
| "label": "Physical State Transition", |
| "dimension": "causal", |
| "subcategory": "causal_common_sense_knowledge", |
| "case_count": 31, |
| "multi_image_case_count": 0, |
| "description": "Causal · Physical State Transition — accuracy (%)" |
| }, |
| { |
| "key": "C02", |
| "code": "C02", |
| "label": "Structural Damage", |
| "dimension": "causal", |
| "subcategory": "causal_common_sense_knowledge", |
| "case_count": 27, |
| "multi_image_case_count": 0, |
| "description": "Causal · Structural Damage — accuracy (%)" |
| }, |
| { |
| "key": "C03", |
| "code": "C03", |
| "label": "Flexible Deformation", |
| "dimension": "causal", |
| "subcategory": "causal_common_sense_knowledge", |
| "case_count": 22, |
| "multi_image_case_count": 1, |
| "description": "Causal · Flexible Deformation — accuracy (%)" |
| }, |
| { |
| "key": "C04", |
| "code": "C04", |
| "label": "Magnitude Change", |
| "dimension": "causal", |
| "subcategory": "causal_context_knowledge", |
| "case_count": 10, |
| "multi_image_case_count": 0, |
| "description": "Causal · Magnitude Change — accuracy (%)" |
| }, |
| { |
| "key": "C05", |
| "code": "C05", |
| "label": "Reading Offset", |
| "dimension": "causal", |
| "subcategory": "causal_context_knowledge", |
| "case_count": 10, |
| "multi_image_case_count": 2, |
| "description": "Causal · Reading Offset — accuracy (%)" |
| }, |
| { |
| "key": "C06", |
| "code": "C06", |
| "label": "Order Relation", |
| "dimension": "causal", |
| "subcategory": "causal_context_knowledge", |
| "case_count": 10, |
| "multi_image_case_count": 0, |
| "description": "Causal · Order Relation — accuracy (%)" |
| }, |
| { |
| "key": "C07", |
| "code": "C07", |
| "label": "Feature Mapping", |
| "dimension": "causal", |
| "subcategory": "causal_context_knowledge", |
| "case_count": 10, |
| "multi_image_case_count": 0, |
| "description": "Causal · Feature Mapping — accuracy (%)" |
| }, |
| { |
| "key": "C08", |
| "code": "C08", |
| "label": "Physics", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 25, |
| "multi_image_case_count": 1, |
| "description": "Causal · Physics — accuracy (%)" |
| }, |
| { |
| "key": "C09", |
| "code": "C09", |
| "label": "Chemistry", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 23, |
| "multi_image_case_count": 4, |
| "description": "Causal · Chemistry — accuracy (%)" |
| }, |
| { |
| "key": "C10", |
| "code": "C10", |
| "label": "Biology", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 12, |
| "multi_image_case_count": 0, |
| "description": "Causal · Biology — accuracy (%)" |
| }, |
| { |
| "key": "C11", |
| "code": "C11", |
| "label": "Astronomy", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 3, |
| "multi_image_case_count": 0, |
| "description": "Causal · Astronomy — accuracy (%)" |
| }, |
| { |
| "key": "C12", |
| "code": "C12", |
| "label": "Medicine", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 4, |
| "multi_image_case_count": 0, |
| "description": "Causal · Medicine — accuracy (%)" |
| }, |
| { |
| "key": "C13", |
| "code": "C13", |
| "label": "Music Theory", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 3, |
| "multi_image_case_count": 0, |
| "description": "Causal · Music Theory — accuracy (%)" |
| }, |
| { |
| "key": "C14", |
| "code": "C14", |
| "label": "Computer Science", |
| "dimension": "causal", |
| "subcategory": "causal_disciplinary_knowledge", |
| "case_count": 10, |
| "multi_image_case_count": 0, |
| "description": "Causal · Computer Science — accuracy (%)" |
| }, |
| { |
| "key": "S01", |
| "code": "S01", |
| "label": "Adjacency", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 11, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Adjacency — accuracy (%)" |
| }, |
| { |
| "key": "S02", |
| "code": "S02", |
| "label": "Direction", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 11, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Direction — accuracy (%)" |
| }, |
| { |
| "key": "S03", |
| "code": "S03", |
| "label": "Orientation", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 11, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Orientation — accuracy (%)" |
| }, |
| { |
| "key": "S04", |
| "code": "S04", |
| "label": "Projection", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 12, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Projection — accuracy (%)" |
| }, |
| { |
| "key": "S05", |
| "code": "S05", |
| "label": "Distance", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 13, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Distance — accuracy (%)" |
| }, |
| { |
| "key": "S06", |
| "code": "S06", |
| "label": "Size", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 15, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Size — accuracy (%)" |
| }, |
| { |
| "key": "S07", |
| "code": "S07", |
| "label": "Configuration", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 18, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Configuration — accuracy (%)" |
| }, |
| { |
| "key": "S08", |
| "code": "S08", |
| "label": "Viewing Scale", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 9, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Viewing Scale — accuracy (%)" |
| }, |
| { |
| "key": "S09", |
| "code": "S09", |
| "label": "Localization", |
| "dimension": "spatial", |
| "subcategory": "spatial_relation", |
| "case_count": 6, |
| "multi_image_case_count": 6, |
| "description": "Spatial · Localization — accuracy (%)" |
| }, |
| { |
| "key": "S10", |
| "code": "S10", |
| "label": "Part-Whole Perception", |
| "dimension": "spatial", |
| "subcategory": "spatial_structure", |
| "case_count": 24, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Part-Whole Perception — accuracy (%)" |
| }, |
| { |
| "key": "S11", |
| "code": "S11", |
| "label": "Geometric Regularities Reasoning", |
| "dimension": "spatial", |
| "subcategory": "spatial_structure", |
| "case_count": 15, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Geometric Regularities Reasoning — accuracy (%)" |
| }, |
| { |
| "key": "S12", |
| "code": "S12", |
| "label": "Viewpoint Generation", |
| "dimension": "spatial", |
| "subcategory": "spatial_structure", |
| "case_count": 26, |
| "multi_image_case_count": 0, |
| "description": "Spatial · Viewpoint Generation — accuracy (%)" |
| }, |
| { |
| "key": "S13", |
| "code": "S13", |
| "label": "Environmental Structure Reasoning", |
| "dimension": "spatial", |
| "subcategory": "spatial_structure", |
| "case_count": 19, |
| "multi_image_case_count": 2, |
| "description": "Spatial · Environmental Structure Reasoning — accuracy (%)" |
| }, |
| { |
| "key": "S14", |
| "code": "S14", |
| "label": "Egocentric Scene Reconstruction", |
| "dimension": "spatial", |
| "subcategory": "spatial_structure", |
| "case_count": 10, |
| "multi_image_case_count": 10, |
| "description": "Spatial · Egocentric Scene Reconstruction — accuracy (%)" |
| }, |
| { |
| "key": "L01", |
| "code": "L01", |
| "label": "Path Searching", |
| "dimension": "logical", |
| "subcategory": "logical_explicit_rule_deduction", |
| "case_count": 24, |
| "multi_image_case_count": 0, |
| "description": "Logical · Path Searching — accuracy (%)" |
| }, |
| { |
| "key": "L02", |
| "code": "L02", |
| "label": "Mathematical Derivation", |
| "dimension": "logical", |
| "subcategory": "logical_explicit_rule_deduction", |
| "case_count": 27, |
| "multi_image_case_count": 0, |
| "description": "Logical · Mathematical Derivation — accuracy (%)" |
| }, |
| { |
| "key": "L03", |
| "code": "L03", |
| "label": "Game Deduction", |
| "dimension": "logical", |
| "subcategory": "logical_explicit_rule_deduction", |
| "case_count": 37, |
| "multi_image_case_count": 0, |
| "description": "Logical · Game Deduction — accuracy (%)" |
| }, |
| { |
| "key": "L04", |
| "code": "L04", |
| "label": "Puzzle Solving", |
| "dimension": "logical", |
| "subcategory": "logical_explicit_rule_deduction", |
| "case_count": 35, |
| "multi_image_case_count": 0, |
| "description": "Logical · Puzzle Solving — accuracy (%)" |
| }, |
| { |
| "key": "L05", |
| "code": "L05", |
| "label": "Pattern Prediction", |
| "dimension": "logical", |
| "subcategory": "logical_implicit_pattern_induction", |
| "case_count": 39, |
| "multi_image_case_count": 0, |
| "description": "Logical · Pattern Prediction — accuracy (%)" |
| }, |
| { |
| "key": "L06", |
| "code": "L06", |
| "label": "Visual Oddity Detection", |
| "dimension": "logical", |
| "subcategory": "logical_implicit_pattern_induction", |
| "case_count": 18, |
| "multi_image_case_count": 0, |
| "description": "Logical · Visual Oddity Detection — accuracy (%)" |
| }, |
| { |
| "key": "L07", |
| "code": "L07", |
| "label": "Rule Transfer", |
| "dimension": "logical", |
| "subcategory": "logical_implicit_pattern_induction", |
| "case_count": 20, |
| "multi_image_case_count": 20, |
| "description": "Logical · Rule Transfer — accuracy (%)" |
| }, |
| { |
| "key": "F01", |
| "code": "F01", |
| "label": "Physical Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 23, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Physical Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F02", |
| "code": "F02", |
| "label": "Chemical Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 9, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Chemical Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F03", |
| "code": "F03", |
| "label": "Biological Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 8, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Biological Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F04", |
| "code": "F04", |
| "label": "Astronomy Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 7, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Astronomy Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F05", |
| "code": "F05", |
| "label": "Geography Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 8, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Geography Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F06", |
| "code": "F06", |
| "label": "History Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 7, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · History Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F07", |
| "code": "F07", |
| "label": "Music Theory Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 4, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Music Theory Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F08", |
| "code": "F08", |
| "label": "Computer Science Counterfactual", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_counterfactual_imagination", |
| "case_count": 4, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Computer Science Counterfactual — accuracy (%)" |
| }, |
| { |
| "key": "F09", |
| "code": "F09", |
| "label": "Anatomical Errors", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_anomaly_correction_and_generation", |
| "case_count": 10, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Anatomical Errors — accuracy (%)" |
| }, |
| { |
| "key": "F10", |
| "code": "F10", |
| "label": "Structural Anomalies", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_anomaly_correction_and_generation", |
| "case_count": 11, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Structural Anomalies — accuracy (%)" |
| }, |
| { |
| "key": "F11", |
| "code": "F11", |
| "label": "Relational Anomalies", |
| "dimension": "counterfactual", |
| "subcategory": "counterfactual_anomaly_correction_and_generation", |
| "case_count": 9, |
| "multi_image_case_count": 0, |
| "description": "Counterfactual · Relational Anomalies — accuracy (%)" |
| } |
| ], |
| "links": { |
| "paper": "https://arxiv.org/abs/2610.12343", |
| "data": "https://huggingface.co/datasets/VisionXLab/RISEBench-plusplus", |
| "outputs": "https://huggingface.co/datasets/VisionXLab/RISEBench-plusplus_Outputs", |
| "github": "https://github.com/VisionXLab/RISEBench/tree/main/RISEBench%2B%2B" |
| }, |
| "judges": { |
| "instruction_reasoning": "Gemini-3-Flash", |
| "appearance_consistency": "Gemini-3-Flash", |
| "visual_plausibility": "Gemini-3.1-Flash-Lite" |
| }, |
| "results_by_language": { |
| "en": { |
| "language": "English", |
| "language_code": "en", |
| "model_count": 58, |
| "groups": [ |
| { |
| "id": "closed", |
| "label": "Closed-source Models", |
| "count": 19 |
| }, |
| { |
| "id": "open", |
| "label": "Open-source Models", |
| "count": 34 |
| }, |
| { |
| "id": "agentic", |
| "label": "Agentic Methods", |
| "count": 5 |
| } |
| ], |
| "models": [ |
| { |
| "id": "gpt-image-2-5-sunburst", |
| "name": "GPT-Image-2.5 Sunburst", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 1, |
| "accuracy": { |
| "temporal": 67.5, |
| "causal": 69.0, |
| "spatial": 64.0, |
| "logical": 27.0, |
| "counterfactual": 72.0, |
| "hybrid": 39.0, |
| "single": 56.9, |
| "multi": 52.6, |
| "total": 56.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 68.1, |
| "appearance_consistency": 96.3, |
| "visual_plausibility": 98.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 72.9, |
| "temporal_context_knowledge": 67.3, |
| "temporal_disciplinary_knowledge": 60.3, |
| "causal_common_sense_knowledge": 78.8, |
| "causal_context_knowledge": 55.0, |
| "causal_disciplinary_knowledge": 66.3, |
| "spatial_relation": 63.2, |
| "spatial_structure": 64.9, |
| "logical_explicit_rule_deduction": 32.5, |
| "logical_implicit_pattern_induction": 18.2, |
| "counterfactual_counterfactual_imagination": 71.4, |
| "counterfactual_anomaly_correction_and_generation": 73.3 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 88.9, |
| "T03": 76.9, |
| "T04": 80.0, |
| "T05": 87.5, |
| "T06": 71.4, |
| "T07": 50.0, |
| "T08": 60.0, |
| "T09": 50.0, |
| "T10": 73.3, |
| "T11": 100.0, |
| "T12": 50.0, |
| "T13": 50.0, |
| "T14": 66.7, |
| "T15": 58.3, |
| "T16": 66.7, |
| "T17": 40.0, |
| "T18": 75.0, |
| "T19": 66.7, |
| "C01": 80.6, |
| "C02": 85.2, |
| "C03": 68.2, |
| "C04": 50.0, |
| "C05": 60.0, |
| "C06": 30.0, |
| "C07": 80.0, |
| "C08": 56.0, |
| "C09": 69.6, |
| "C10": 100.0, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 66.7, |
| "C14": 40.0, |
| "S01": 63.6, |
| "S02": 72.7, |
| "S03": 45.5, |
| "S04": 58.3, |
| "S05": 76.9, |
| "S06": 80.0, |
| "S07": 72.2, |
| "S08": 44.4, |
| "S09": 16.7, |
| "S10": 79.2, |
| "S11": 73.3, |
| "S12": 65.4, |
| "S13": 52.6, |
| "S14": 40.0, |
| "L01": 25.0, |
| "L02": 29.6, |
| "L03": 40.5, |
| "L04": 31.4, |
| "L05": 12.8, |
| "L06": 33.3, |
| "L07": 15.0, |
| "F01": 87.0, |
| "F02": 66.7, |
| "F03": 87.5, |
| "F04": 42.9, |
| "F05": 75.0, |
| "F06": 57.1, |
| "F07": 50.0, |
| "F08": 50.0, |
| "F09": 90.0, |
| "F10": 63.6, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "nano-banana-pro", |
| "name": "Nano Banana Pro", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 2, |
| "accuracy": { |
| "temporal": 63.0, |
| "causal": 71.0, |
| "spatial": 51.5, |
| "logical": 36.0, |
| "counterfactual": 65.0, |
| "hybrid": 38.0, |
| "single": 55.4, |
| "multi": 44.9, |
| "total": 54.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 69.8, |
| "appearance_consistency": 87.7, |
| "visual_plausibility": 96.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 68.2, |
| "temporal_context_knowledge": 63.5, |
| "temporal_disciplinary_knowledge": 55.6, |
| "causal_common_sense_knowledge": 77.5, |
| "causal_context_knowledge": 65.0, |
| "causal_disciplinary_knowledge": 67.5, |
| "spatial_relation": 50.9, |
| "spatial_structure": 52.1, |
| "logical_explicit_rule_deduction": 41.5, |
| "logical_implicit_pattern_induction": 27.3, |
| "counterfactual_counterfactual_imagination": 61.4, |
| "counterfactual_anomaly_correction_and_generation": 73.3 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 100.0, |
| "T03": 76.9, |
| "T04": 70.0, |
| "T05": 50.0, |
| "T06": 42.9, |
| "T07": 75.0, |
| "T08": 66.7, |
| "T09": 64.3, |
| "T10": 60.0, |
| "T11": 62.5, |
| "T12": 75.0, |
| "T13": 25.0, |
| "T14": 66.7, |
| "T15": 66.7, |
| "T16": 50.0, |
| "T17": 60.0, |
| "T18": 75.0, |
| "T19": 33.3, |
| "C01": 74.2, |
| "C02": 74.1, |
| "C03": 86.4, |
| "C04": 40.0, |
| "C05": 80.0, |
| "C06": 60.0, |
| "C07": 80.0, |
| "C08": 64.0, |
| "C09": 73.9, |
| "C10": 91.7, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 33.3, |
| "C14": 40.0, |
| "S01": 81.8, |
| "S02": 45.5, |
| "S03": 54.5, |
| "S04": 58.3, |
| "S05": 53.8, |
| "S06": 46.7, |
| "S07": 55.6, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 58.3, |
| "S11": 66.7, |
| "S12": 50.0, |
| "S13": 36.8, |
| "S14": 50.0, |
| "L01": 29.2, |
| "L02": 66.7, |
| "L03": 45.9, |
| "L04": 25.7, |
| "L05": 25.6, |
| "L06": 27.8, |
| "L07": 30.0, |
| "F01": 78.3, |
| "F02": 55.6, |
| "F03": 87.5, |
| "F04": 42.9, |
| "F05": 12.5, |
| "F06": 85.7, |
| "F07": 25.0, |
| "F08": 50.0, |
| "F09": 80.0, |
| "F10": 81.8, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "nano-banana-2", |
| "name": "Nano Banana 2", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 3, |
| "accuracy": { |
| "temporal": 67.5, |
| "causal": 67.0, |
| "spatial": 45.0, |
| "logical": 28.5, |
| "counterfactual": 62.0, |
| "hybrid": 30.0, |
| "single": 51.3, |
| "multi": 44.9, |
| "total": 50.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 68.5, |
| "appearance_consistency": 91.1, |
| "visual_plausibility": 97.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 77.6, |
| "temporal_context_knowledge": 63.5, |
| "temporal_disciplinary_knowledge": 57.1, |
| "causal_common_sense_knowledge": 76.3, |
| "causal_context_knowledge": 50.0, |
| "causal_disciplinary_knowledge": 66.3, |
| "spatial_relation": 47.2, |
| "spatial_structure": 42.6, |
| "logical_explicit_rule_deduction": 38.2, |
| "logical_implicit_pattern_induction": 13.0, |
| "counterfactual_counterfactual_imagination": 58.6, |
| "counterfactual_anomaly_correction_and_generation": 70.0 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 88.9, |
| "T03": 76.9, |
| "T04": 90.0, |
| "T05": 100.0, |
| "T06": 57.1, |
| "T07": 75.0, |
| "T08": 60.0, |
| "T09": 71.4, |
| "T10": 53.3, |
| "T11": 75.0, |
| "T12": 25.0, |
| "T13": 37.5, |
| "T14": 55.6, |
| "T15": 66.7, |
| "T16": 55.6, |
| "T17": 100.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 71.0, |
| "C02": 74.1, |
| "C03": 86.4, |
| "C04": 40.0, |
| "C05": 40.0, |
| "C06": 70.0, |
| "C07": 50.0, |
| "C08": 64.0, |
| "C09": 73.9, |
| "C10": 91.7, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 50.0, |
| "S01": 54.5, |
| "S02": 54.5, |
| "S03": 36.4, |
| "S04": 41.7, |
| "S05": 46.2, |
| "S06": 60.0, |
| "S07": 55.6, |
| "S08": 33.3, |
| "S09": 16.7, |
| "S10": 41.7, |
| "S11": 53.3, |
| "S12": 34.6, |
| "S13": 42.1, |
| "S14": 50.0, |
| "L01": 33.3, |
| "L02": 51.9, |
| "L03": 45.9, |
| "L04": 22.9, |
| "L05": 12.8, |
| "L06": 27.8, |
| "L07": 0.0, |
| "F01": 65.2, |
| "F02": 55.6, |
| "F03": 100.0, |
| "F04": 28.6, |
| "F05": 12.5, |
| "F06": 71.4, |
| "F07": 50.0, |
| "F08": 75.0, |
| "F09": 80.0, |
| "F10": 81.8, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "gpt-image-2", |
| "name": "GPT-Image-2", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 4, |
| "accuracy": { |
| "temporal": 59.5, |
| "causal": 64.5, |
| "spatial": 60.5, |
| "logical": 15.0, |
| "counterfactual": 58.0, |
| "hybrid": 21.0, |
| "single": 48.2, |
| "multi": 43.6, |
| "total": 47.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 61.5, |
| "appearance_consistency": 95.2, |
| "visual_plausibility": 97.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 61.2, |
| "temporal_context_knowledge": 67.3, |
| "temporal_disciplinary_knowledge": 50.8, |
| "causal_common_sense_knowledge": 76.3, |
| "causal_context_knowledge": 60.0, |
| "causal_disciplinary_knowledge": 55.0, |
| "spatial_relation": 60.4, |
| "spatial_structure": 60.6, |
| "logical_explicit_rule_deduction": 21.1, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 52.9, |
| "counterfactual_anomaly_correction_and_generation": 70.0 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 88.9, |
| "T03": 69.2, |
| "T04": 65.0, |
| "T05": 62.5, |
| "T06": 42.9, |
| "T07": 0.0, |
| "T08": 53.3, |
| "T09": 64.3, |
| "T10": 86.7, |
| "T11": 62.5, |
| "T12": 50.0, |
| "T13": 50.0, |
| "T14": 66.7, |
| "T15": 50.0, |
| "T16": 44.4, |
| "T17": 40.0, |
| "T18": 75.0, |
| "T19": 33.3, |
| "C01": 71.0, |
| "C02": 77.8, |
| "C03": 81.8, |
| "C04": 60.0, |
| "C05": 60.0, |
| "C06": 60.0, |
| "C07": 60.0, |
| "C08": 36.0, |
| "C09": 69.6, |
| "C10": 83.3, |
| "C11": 100.0, |
| "C12": 0.0, |
| "C13": 100.0, |
| "C14": 30.0, |
| "S01": 72.7, |
| "S02": 54.5, |
| "S03": 54.5, |
| "S04": 66.7, |
| "S05": 76.9, |
| "S06": 60.0, |
| "S07": 61.1, |
| "S08": 55.6, |
| "S09": 16.7, |
| "S10": 79.2, |
| "S11": 73.3, |
| "S12": 50.0, |
| "S13": 57.9, |
| "S14": 30.0, |
| "L01": 16.7, |
| "L02": 22.2, |
| "L03": 27.0, |
| "L04": 17.1, |
| "L05": 10.3, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 52.2, |
| "F02": 55.6, |
| "F03": 87.5, |
| "F04": 42.9, |
| "F05": 50.0, |
| "F06": 42.9, |
| "F07": 50.0, |
| "F08": 25.0, |
| "F09": 100.0, |
| "F10": 72.7, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "gpt-image-2-5-flare", |
| "name": "GPT-Image-2.5 Flare", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 5, |
| "accuracy": { |
| "temporal": 61.0, |
| "causal": 63.0, |
| "spatial": 56.5, |
| "logical": 11.0, |
| "counterfactual": 57.0, |
| "hybrid": 20.0, |
| "single": 46.6, |
| "multi": 38.5, |
| "total": 46.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 59.8, |
| "appearance_consistency": 93.2, |
| "visual_plausibility": 98.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 68.2, |
| "temporal_context_knowledge": 61.5, |
| "temporal_disciplinary_knowledge": 50.8, |
| "causal_common_sense_knowledge": 76.3, |
| "causal_context_knowledge": 52.5, |
| "causal_disciplinary_knowledge": 55.0, |
| "spatial_relation": 56.6, |
| "spatial_structure": 56.4, |
| "logical_explicit_rule_deduction": 17.1, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 52.9, |
| "counterfactual_anomaly_correction_and_generation": 66.7 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 77.8, |
| "T03": 76.9, |
| "T04": 75.0, |
| "T05": 87.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 66.7, |
| "T09": 42.9, |
| "T10": 73.3, |
| "T11": 62.5, |
| "T12": 25.0, |
| "T13": 37.5, |
| "T14": 55.6, |
| "T15": 50.0, |
| "T16": 55.6, |
| "T17": 60.0, |
| "T18": 75.0, |
| "T19": 33.3, |
| "C01": 67.7, |
| "C02": 88.9, |
| "C03": 72.7, |
| "C04": 40.0, |
| "C05": 50.0, |
| "C06": 50.0, |
| "C07": 70.0, |
| "C08": 44.0, |
| "C09": 65.2, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 33.3, |
| "C14": 30.0, |
| "S01": 63.6, |
| "S02": 90.9, |
| "S03": 36.4, |
| "S04": 58.3, |
| "S05": 38.5, |
| "S06": 40.0, |
| "S07": 83.3, |
| "S08": 55.6, |
| "S09": 16.7, |
| "S10": 75.0, |
| "S11": 46.7, |
| "S12": 69.2, |
| "S13": 47.4, |
| "S14": 10.0, |
| "L01": 8.3, |
| "L02": 14.8, |
| "L03": 24.3, |
| "L04": 17.1, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 65.2, |
| "F02": 33.3, |
| "F03": 87.5, |
| "F04": 28.6, |
| "F05": 50.0, |
| "F06": 42.9, |
| "F07": 25.0, |
| "F08": 50.0, |
| "F09": 80.0, |
| "F10": 63.6, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "luma-uni-1", |
| "name": "Luma Uni-1", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 6, |
| "accuracy": { |
| "temporal": 61.0, |
| "causal": 57.0, |
| "spatial": 50.5, |
| "logical": 18.0, |
| "counterfactual": 55.0, |
| "hybrid": 24.0, |
| "single": 45.7, |
| "multi": 39.7, |
| "total": 45.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 62.2, |
| "appearance_consistency": 91.0, |
| "visual_plausibility": 94.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 74.1, |
| "temporal_context_knowledge": 57.7, |
| "temporal_disciplinary_knowledge": 46.0, |
| "causal_common_sense_knowledge": 68.8, |
| "causal_context_knowledge": 42.5, |
| "causal_disciplinary_knowledge": 52.5, |
| "spatial_relation": 50.0, |
| "spatial_structure": 51.1, |
| "logical_explicit_rule_deduction": 21.1, |
| "logical_implicit_pattern_induction": 13.0, |
| "counterfactual_counterfactual_imagination": 55.7, |
| "counterfactual_anomaly_correction_and_generation": 53.3 |
| }, |
| "task_types": { |
| "T01": 70.8, |
| "T02": 88.9, |
| "T03": 76.9, |
| "T04": 75.0, |
| "T05": 87.5, |
| "T06": 42.9, |
| "T07": 75.0, |
| "T08": 60.0, |
| "T09": 64.3, |
| "T10": 46.7, |
| "T11": 62.5, |
| "T12": 75.0, |
| "T13": 12.5, |
| "T14": 66.7, |
| "T15": 41.7, |
| "T16": 27.8, |
| "T17": 80.0, |
| "T18": 75.0, |
| "T19": 66.7, |
| "C01": 77.4, |
| "C02": 66.7, |
| "C03": 59.1, |
| "C04": 30.0, |
| "C05": 40.0, |
| "C06": 40.0, |
| "C07": 60.0, |
| "C08": 44.0, |
| "C09": 60.9, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 0.0, |
| "C13": 100.0, |
| "C14": 20.0, |
| "S01": 63.6, |
| "S02": 45.5, |
| "S03": 27.3, |
| "S04": 75.0, |
| "S05": 38.5, |
| "S06": 53.3, |
| "S07": 55.6, |
| "S08": 55.6, |
| "S09": 16.7, |
| "S10": 50.0, |
| "S11": 60.0, |
| "S12": 42.3, |
| "S13": 42.1, |
| "S14": 80.0, |
| "L01": 0.0, |
| "L02": 29.6, |
| "L03": 29.7, |
| "L04": 20.0, |
| "L05": 12.8, |
| "L06": 16.7, |
| "L07": 10.0, |
| "F01": 52.2, |
| "F02": 77.8, |
| "F03": 87.5, |
| "F04": 28.6, |
| "F05": 50.0, |
| "F06": 71.4, |
| "F07": 25.0, |
| "F08": 25.0, |
| "F09": 60.0, |
| "F10": 54.5, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "qwen-image-3-0", |
| "name": "Qwen-Image-3.0", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 7, |
| "accuracy": { |
| "temporal": 58.5, |
| "causal": 47.5, |
| "spatial": 41.0, |
| "logical": 36.0, |
| "counterfactual": 49.0, |
| "hybrid": 34.0, |
| "single": 44.5, |
| "multi": 50.0, |
| "total": 44.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 68.4, |
| "appearance_consistency": 87.3, |
| "visual_plausibility": 95.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 58.8, |
| "temporal_context_knowledge": 67.3, |
| "temporal_disciplinary_knowledge": 50.8, |
| "causal_common_sense_knowledge": 51.3, |
| "causal_context_knowledge": 50.0, |
| "causal_disciplinary_knowledge": 42.5, |
| "spatial_relation": 44.3, |
| "spatial_structure": 37.2, |
| "logical_explicit_rule_deduction": 39.0, |
| "logical_implicit_pattern_induction": 31.2, |
| "counterfactual_counterfactual_imagination": 44.3, |
| "counterfactual_anomaly_correction_and_generation": 60.0 |
| }, |
| "task_types": { |
| "T01": 45.8, |
| "T02": 77.8, |
| "T03": 53.8, |
| "T04": 70.0, |
| "T05": 75.0, |
| "T06": 42.9, |
| "T07": 50.0, |
| "T08": 60.0, |
| "T09": 85.7, |
| "T10": 66.7, |
| "T11": 50.0, |
| "T12": 100.0, |
| "T13": 50.0, |
| "T14": 22.2, |
| "T15": 66.7, |
| "T16": 61.1, |
| "T17": 0.0, |
| "T18": 50.0, |
| "T19": 33.3, |
| "C01": 51.6, |
| "C02": 59.3, |
| "C03": 40.9, |
| "C04": 60.0, |
| "C05": 40.0, |
| "C06": 50.0, |
| "C07": 50.0, |
| "C08": 44.0, |
| "C09": 34.8, |
| "C10": 75.0, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 66.7, |
| "C14": 20.0, |
| "S01": 81.8, |
| "S02": 45.5, |
| "S03": 18.2, |
| "S04": 50.0, |
| "S05": 38.5, |
| "S06": 60.0, |
| "S07": 50.0, |
| "S08": 11.1, |
| "S09": 16.7, |
| "S10": 41.7, |
| "S11": 60.0, |
| "S12": 34.6, |
| "S13": 36.8, |
| "S14": 0.0, |
| "L01": 16.7, |
| "L02": 55.6, |
| "L03": 40.5, |
| "L04": 40.0, |
| "L05": 15.4, |
| "L06": 38.9, |
| "L07": 55.0, |
| "F01": 47.8, |
| "F02": 22.2, |
| "F03": 25.0, |
| "F04": 28.6, |
| "F05": 50.0, |
| "F06": 71.4, |
| "F07": 25.0, |
| "F08": 100.0, |
| "F09": 70.0, |
| "F10": 54.5, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "nano-banana-2-lite", |
| "name": "Nano Banana 2 Lite", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 8, |
| "accuracy": { |
| "temporal": 60.5, |
| "causal": 61.5, |
| "spatial": 46.5, |
| "logical": 15.0, |
| "counterfactual": 62.0, |
| "hybrid": 12.0, |
| "single": 44.5, |
| "multi": 39.7, |
| "total": 44.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 60.8, |
| "appearance_consistency": 89.7, |
| "visual_plausibility": 96.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 67.1, |
| "temporal_context_knowledge": 63.5, |
| "temporal_disciplinary_knowledge": 49.2, |
| "causal_common_sense_knowledge": 77.5, |
| "causal_context_knowledge": 45.0, |
| "causal_disciplinary_knowledge": 53.8, |
| "spatial_relation": 44.3, |
| "spatial_structure": 48.9, |
| "logical_explicit_rule_deduction": 18.7, |
| "logical_implicit_pattern_induction": 9.1, |
| "counterfactual_counterfactual_imagination": 61.4, |
| "counterfactual_anomaly_correction_and_generation": 63.3 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 100.0, |
| "T03": 61.5, |
| "T04": 60.0, |
| "T05": 87.5, |
| "T06": 71.4, |
| "T07": 75.0, |
| "T08": 53.3, |
| "T09": 78.6, |
| "T10": 60.0, |
| "T11": 62.5, |
| "T12": 50.0, |
| "T13": 37.5, |
| "T14": 55.6, |
| "T15": 41.7, |
| "T16": 50.0, |
| "T17": 40.0, |
| "T18": 75.0, |
| "T19": 66.7, |
| "C01": 77.4, |
| "C02": 81.5, |
| "C03": 72.7, |
| "C04": 40.0, |
| "C05": 50.0, |
| "C06": 40.0, |
| "C07": 50.0, |
| "C08": 44.0, |
| "C09": 73.9, |
| "C10": 91.7, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 54.5, |
| "S02": 63.6, |
| "S03": 36.4, |
| "S04": 41.7, |
| "S05": 53.8, |
| "S06": 60.0, |
| "S07": 33.3, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 54.2, |
| "S11": 60.0, |
| "S12": 50.0, |
| "S13": 36.8, |
| "S14": 40.0, |
| "L01": 16.7, |
| "L02": 22.2, |
| "L03": 21.6, |
| "L04": 14.3, |
| "L05": 7.7, |
| "L06": 16.7, |
| "L07": 5.0, |
| "F01": 73.9, |
| "F02": 77.8, |
| "F03": 62.5, |
| "F04": 57.1, |
| "F05": 12.5, |
| "F06": 85.7, |
| "F07": 25.0, |
| "F08": 50.0, |
| "F09": 90.0, |
| "F10": 36.4, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "flux-2-max", |
| "name": "FLUX.2 Max", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 9, |
| "accuracy": { |
| "temporal": 57.0, |
| "causal": 57.0, |
| "spatial": 42.5, |
| "logical": 12.5, |
| "counterfactual": 61.0, |
| "hybrid": 18.0, |
| "single": 41.5, |
| "multi": 43.6, |
| "total": 41.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 61.5, |
| "appearance_consistency": 79.2, |
| "visual_plausibility": 95.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 61.2, |
| "temporal_context_knowledge": 69.2, |
| "temporal_disciplinary_knowledge": 41.3, |
| "causal_common_sense_knowledge": 67.5, |
| "causal_context_knowledge": 40.0, |
| "causal_disciplinary_knowledge": 55.0, |
| "spatial_relation": 33.0, |
| "spatial_structure": 53.2, |
| "logical_explicit_rule_deduction": 17.9, |
| "logical_implicit_pattern_induction": 3.9, |
| "counterfactual_counterfactual_imagination": 62.9, |
| "counterfactual_anomaly_correction_and_generation": 56.7 |
| }, |
| "task_types": { |
| "T01": 45.8, |
| "T02": 88.9, |
| "T03": 69.2, |
| "T04": 55.0, |
| "T05": 87.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 80.0, |
| "T09": 71.4, |
| "T10": 73.3, |
| "T11": 37.5, |
| "T12": 50.0, |
| "T13": 12.5, |
| "T14": 55.6, |
| "T15": 66.7, |
| "T16": 27.8, |
| "T17": 20.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 58.1, |
| "C02": 74.1, |
| "C03": 72.7, |
| "C04": 30.0, |
| "C05": 50.0, |
| "C06": 30.0, |
| "C07": 50.0, |
| "C08": 40.0, |
| "C09": 82.6, |
| "C10": 66.7, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 27.3, |
| "S02": 36.4, |
| "S03": 27.3, |
| "S04": 41.7, |
| "S05": 23.1, |
| "S06": 33.3, |
| "S07": 50.0, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 75.0, |
| "S11": 66.7, |
| "S12": 34.6, |
| "S13": 21.1, |
| "S14": 90.0, |
| "L01": 4.2, |
| "L02": 33.3, |
| "L03": 18.9, |
| "L04": 14.3, |
| "L05": 5.1, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 69.6, |
| "F02": 77.8, |
| "F03": 62.5, |
| "F04": 71.4, |
| "F05": 37.5, |
| "F06": 71.4, |
| "F07": 0.0, |
| "F08": 75.0, |
| "F09": 60.0, |
| "F10": 63.6, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "gpt-image-1-5", |
| "name": "GPT-Image-1.5", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 10, |
| "accuracy": { |
| "temporal": 57.5, |
| "causal": 62.5, |
| "spatial": 39.5, |
| "logical": 8.0, |
| "counterfactual": 59.0, |
| "hybrid": 12.0, |
| "single": 41.2, |
| "multi": 33.3, |
| "total": 40.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 59.9, |
| "appearance_consistency": 81.0, |
| "visual_plausibility": 96.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 65.9, |
| "temporal_context_knowledge": 51.9, |
| "temporal_disciplinary_knowledge": 50.8, |
| "causal_common_sense_knowledge": 80.0, |
| "causal_context_knowledge": 52.5, |
| "causal_disciplinary_knowledge": 50.0, |
| "spatial_relation": 29.2, |
| "spatial_structure": 51.1, |
| "logical_explicit_rule_deduction": 8.9, |
| "logical_implicit_pattern_induction": 6.5, |
| "counterfactual_counterfactual_imagination": 61.4, |
| "counterfactual_anomaly_correction_and_generation": 53.3 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 88.9, |
| "T03": 53.8, |
| "T04": 80.0, |
| "T05": 75.0, |
| "T06": 42.9, |
| "T07": 25.0, |
| "T08": 46.7, |
| "T09": 50.0, |
| "T10": 60.0, |
| "T11": 50.0, |
| "T12": 50.0, |
| "T13": 25.0, |
| "T14": 77.8, |
| "T15": 58.3, |
| "T16": 61.1, |
| "T17": 20.0, |
| "T18": 25.0, |
| "T19": 33.3, |
| "C01": 87.1, |
| "C02": 77.8, |
| "C03": 72.7, |
| "C04": 50.0, |
| "C05": 30.0, |
| "C06": 60.0, |
| "C07": 70.0, |
| "C08": 36.0, |
| "C09": 60.9, |
| "C10": 83.3, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 36.4, |
| "S04": 50.0, |
| "S05": 30.8, |
| "S06": 53.3, |
| "S07": 22.2, |
| "S08": 44.4, |
| "S09": 0.0, |
| "S10": 66.7, |
| "S11": 46.7, |
| "S12": 42.3, |
| "S13": 63.2, |
| "S14": 20.0, |
| "L01": 4.2, |
| "L02": 3.7, |
| "L03": 18.9, |
| "L04": 5.7, |
| "L05": 7.7, |
| "L06": 5.6, |
| "L07": 5.0, |
| "F01": 60.9, |
| "F02": 55.6, |
| "F03": 87.5, |
| "F04": 57.1, |
| "F05": 75.0, |
| "F06": 71.4, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 80.0, |
| "F10": 36.4, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "flux-2-pro", |
| "name": "FLUX.2 Pro", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 11, |
| "accuracy": { |
| "temporal": 53.5, |
| "causal": 48.5, |
| "spatial": 36.5, |
| "logical": 10.5, |
| "counterfactual": 61.0, |
| "hybrid": 18.0, |
| "single": 37.3, |
| "multi": 42.3, |
| "total": 37.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 57.5, |
| "appearance_consistency": 74.7, |
| "visual_plausibility": 94.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 58.8, |
| "temporal_context_knowledge": 59.6, |
| "temporal_disciplinary_knowledge": 41.3, |
| "causal_common_sense_knowledge": 58.8, |
| "causal_context_knowledge": 30.0, |
| "causal_disciplinary_knowledge": 47.5, |
| "spatial_relation": 23.6, |
| "spatial_structure": 51.1, |
| "logical_explicit_rule_deduction": 14.6, |
| "logical_implicit_pattern_induction": 3.9, |
| "counterfactual_counterfactual_imagination": 64.3, |
| "counterfactual_anomaly_correction_and_generation": 53.3 |
| }, |
| "task_types": { |
| "T01": 50.0, |
| "T02": 77.8, |
| "T03": 61.5, |
| "T04": 55.0, |
| "T05": 75.0, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 60.0, |
| "T09": 57.1, |
| "T10": 66.7, |
| "T11": 50.0, |
| "T12": 50.0, |
| "T13": 37.5, |
| "T14": 55.6, |
| "T15": 58.3, |
| "T16": 27.8, |
| "T17": 60.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 61.3, |
| "C02": 51.9, |
| "C03": 63.6, |
| "C04": 40.0, |
| "C05": 20.0, |
| "C06": 30.0, |
| "C07": 30.0, |
| "C08": 32.0, |
| "C09": 69.6, |
| "C10": 58.3, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 27.3, |
| "S02": 18.2, |
| "S03": 36.4, |
| "S04": 25.0, |
| "S05": 23.1, |
| "S06": 40.0, |
| "S07": 16.7, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 62.5, |
| "S11": 53.3, |
| "S12": 38.5, |
| "S13": 36.8, |
| "S14": 80.0, |
| "L01": 4.2, |
| "L02": 29.6, |
| "L03": 18.9, |
| "L04": 5.7, |
| "L05": 5.1, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 78.3, |
| "F02": 77.8, |
| "F03": 75.0, |
| "F04": 42.9, |
| "F05": 37.5, |
| "F06": 57.1, |
| "F07": 25.0, |
| "F08": 75.0, |
| "F09": 60.0, |
| "F10": 45.5, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "nano-banana", |
| "name": "Nano Banana", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 12, |
| "accuracy": { |
| "temporal": 52.0, |
| "causal": 52.5, |
| "spatial": 39.5, |
| "logical": 11.0, |
| "counterfactual": 47.0, |
| "hybrid": 11.0, |
| "single": 36.8, |
| "multi": 37.2, |
| "total": 36.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 52.9, |
| "appearance_consistency": 84.1, |
| "visual_plausibility": 95.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 55.3, |
| "temporal_context_knowledge": 51.9, |
| "temporal_disciplinary_knowledge": 47.6, |
| "causal_common_sense_knowledge": 70.0, |
| "causal_context_knowledge": 25.0, |
| "causal_disciplinary_knowledge": 48.8, |
| "spatial_relation": 35.8, |
| "spatial_structure": 43.6, |
| "logical_explicit_rule_deduction": 14.6, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 45.7, |
| "counterfactual_anomaly_correction_and_generation": 50.0 |
| }, |
| "task_types": { |
| "T01": 37.5, |
| "T02": 77.8, |
| "T03": 61.5, |
| "T04": 55.0, |
| "T05": 75.0, |
| "T06": 42.9, |
| "T07": 75.0, |
| "T08": 46.7, |
| "T09": 50.0, |
| "T10": 60.0, |
| "T11": 50.0, |
| "T12": 25.0, |
| "T13": 62.5, |
| "T14": 55.6, |
| "T15": 50.0, |
| "T16": 44.4, |
| "T17": 20.0, |
| "T18": 25.0, |
| "T19": 100.0, |
| "C01": 74.2, |
| "C02": 66.7, |
| "C03": 68.2, |
| "C04": 10.0, |
| "C05": 40.0, |
| "C06": 20.0, |
| "C07": 30.0, |
| "C08": 32.0, |
| "C09": 65.2, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 75.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 63.6, |
| "S02": 27.3, |
| "S03": 54.5, |
| "S04": 50.0, |
| "S05": 30.8, |
| "S06": 26.7, |
| "S07": 27.8, |
| "S08": 11.1, |
| "S09": 33.3, |
| "S10": 58.3, |
| "S11": 46.7, |
| "S12": 42.3, |
| "S13": 31.6, |
| "S14": 30.0, |
| "L01": 0.0, |
| "L02": 22.2, |
| "L03": 13.5, |
| "L04": 20.0, |
| "L05": 7.7, |
| "L06": 0.0, |
| "L07": 5.0, |
| "F01": 60.9, |
| "F02": 33.3, |
| "F03": 75.0, |
| "F04": 42.9, |
| "F05": 12.5, |
| "F06": 42.9, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 80.0, |
| "F10": 36.4, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "hunyuanimage-3-5", |
| "name": "HunyuanImage-3.5", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 13, |
| "accuracy": { |
| "temporal": 43.5, |
| "causal": 46.0, |
| "spatial": 43.5, |
| "logical": 14.0, |
| "counterfactual": 37.0, |
| "hybrid": 17.0, |
| "single": 34.5, |
| "multi": 38.5, |
| "total": 34.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 51.3, |
| "appearance_consistency": 93.4, |
| "visual_plausibility": 95.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 52.9, |
| "temporal_context_knowledge": 46.2, |
| "temporal_disciplinary_knowledge": 28.6, |
| "causal_common_sense_knowledge": 58.8, |
| "causal_context_knowledge": 32.5, |
| "causal_disciplinary_knowledge": 40.0, |
| "spatial_relation": 37.7, |
| "spatial_structure": 50.0, |
| "logical_explicit_rule_deduction": 14.6, |
| "logical_implicit_pattern_induction": 13.0, |
| "counterfactual_counterfactual_imagination": 31.4, |
| "counterfactual_anomaly_correction_and_generation": 50.0 |
| }, |
| "task_types": { |
| "T01": 33.3, |
| "T02": 77.8, |
| "T03": 46.2, |
| "T04": 55.0, |
| "T05": 87.5, |
| "T06": 71.4, |
| "T07": 25.0, |
| "T08": 46.7, |
| "T09": 28.6, |
| "T10": 66.7, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 37.5, |
| "T14": 22.2, |
| "T15": 58.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 51.6, |
| "C02": 70.4, |
| "C03": 54.5, |
| "C04": 20.0, |
| "C05": 50.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 24.0, |
| "C09": 56.5, |
| "C10": 66.7, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 33.3, |
| "C14": 0.0, |
| "S01": 63.6, |
| "S02": 18.2, |
| "S03": 63.6, |
| "S04": 25.0, |
| "S05": 30.8, |
| "S06": 46.7, |
| "S07": 38.9, |
| "S08": 22.2, |
| "S09": 16.7, |
| "S10": 75.0, |
| "S11": 46.7, |
| "S12": 30.8, |
| "S13": 31.6, |
| "S14": 80.0, |
| "L01": 8.3, |
| "L02": 22.2, |
| "L03": 5.4, |
| "L04": 22.9, |
| "L05": 10.3, |
| "L06": 33.3, |
| "L07": 0.0, |
| "F01": 43.5, |
| "F02": 44.4, |
| "F03": 37.5, |
| "F04": 28.6, |
| "F05": 25.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 25.0, |
| "F09": 70.0, |
| "F10": 36.4, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "wan2-7-image-pro", |
| "name": "Wan2.7-Image-Pro", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 14, |
| "accuracy": { |
| "temporal": 41.5, |
| "causal": 52.0, |
| "spatial": 32.5, |
| "logical": 10.5, |
| "counterfactual": 49.0, |
| "hybrid": 13.0, |
| "single": 36.3, |
| "multi": 0.0, |
| "total": 33.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 48.8, |
| "appearance_consistency": 80.1, |
| "visual_plausibility": 93.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 60.0, |
| "temporal_context_knowledge": 19.2, |
| "temporal_disciplinary_knowledge": 34.9, |
| "causal_common_sense_knowledge": 70.0, |
| "causal_context_knowledge": 42.5, |
| "causal_disciplinary_knowledge": 38.8, |
| "spatial_relation": 33.0, |
| "spatial_structure": 31.9, |
| "logical_explicit_rule_deduction": 13.0, |
| "logical_implicit_pattern_induction": 6.5, |
| "counterfactual_counterfactual_imagination": 44.3, |
| "counterfactual_anomaly_correction_and_generation": 60.0 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 88.9, |
| "T03": 61.5, |
| "T04": 60.0, |
| "T05": 62.5, |
| "T06": 28.6, |
| "T07": 50.0, |
| "T08": 26.7, |
| "T09": 42.9, |
| "T10": 0.0, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 33.3, |
| "T15": 41.7, |
| "T16": 50.0, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 66.7, |
| "C01": 58.1, |
| "C02": 74.1, |
| "C03": 81.8, |
| "C04": 20.0, |
| "C05": 40.0, |
| "C06": 50.0, |
| "C07": 60.0, |
| "C08": 24.0, |
| "C09": 47.8, |
| "C10": 75.0, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 63.6, |
| "S02": 18.2, |
| "S03": 9.1, |
| "S04": 33.3, |
| "S05": 46.2, |
| "S06": 40.0, |
| "S07": 33.3, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 50.0, |
| "S11": 40.0, |
| "S12": 26.9, |
| "S13": 26.3, |
| "S14": 0.0, |
| "L01": 8.3, |
| "L02": 11.1, |
| "L03": 21.6, |
| "L04": 8.6, |
| "L05": 2.6, |
| "L06": 22.2, |
| "L07": 0.0, |
| "F01": 60.9, |
| "F02": 33.3, |
| "F03": 75.0, |
| "F04": 42.9, |
| "F05": 62.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 80.0, |
| "F10": 36.4, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "gpt-image-1", |
| "name": "GPT-Image-1", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 15, |
| "accuracy": { |
| "temporal": 51.0, |
| "causal": 49.0, |
| "spatial": 29.5, |
| "logical": 5.5, |
| "counterfactual": 41.0, |
| "hybrid": 7.0, |
| "single": 32.3, |
| "multi": 25.6, |
| "total": 31.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 53.4, |
| "appearance_consistency": 73.6, |
| "visual_plausibility": 95.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 64.7, |
| "temporal_context_knowledge": 38.5, |
| "temporal_disciplinary_knowledge": 42.9, |
| "causal_common_sense_knowledge": 72.5, |
| "causal_context_knowledge": 27.5, |
| "causal_disciplinary_knowledge": 36.3, |
| "spatial_relation": 24.5, |
| "spatial_structure": 35.1, |
| "logical_explicit_rule_deduction": 7.3, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 41.4, |
| "counterfactual_anomaly_correction_and_generation": 40.0 |
| }, |
| "task_types": { |
| "T01": 75.0, |
| "T02": 77.8, |
| "T03": 61.5, |
| "T04": 55.0, |
| "T05": 75.0, |
| "T06": 71.4, |
| "T07": 0.0, |
| "T08": 53.3, |
| "T09": 35.7, |
| "T10": 26.7, |
| "T11": 37.5, |
| "T12": 50.0, |
| "T13": 25.0, |
| "T14": 55.6, |
| "T15": 41.7, |
| "T16": 50.0, |
| "T17": 40.0, |
| "T18": 50.0, |
| "T19": 0.0, |
| "C01": 83.9, |
| "C02": 63.0, |
| "C03": 68.2, |
| "C04": 0.0, |
| "C05": 30.0, |
| "C06": 30.0, |
| "C07": 50.0, |
| "C08": 24.0, |
| "C09": 39.1, |
| "C10": 66.7, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 18.2, |
| "S03": 18.2, |
| "S04": 41.7, |
| "S05": 30.8, |
| "S06": 26.7, |
| "S07": 22.2, |
| "S08": 11.1, |
| "S09": 33.3, |
| "S10": 45.8, |
| "S11": 40.0, |
| "S12": 30.8, |
| "S13": 31.6, |
| "S14": 20.0, |
| "L01": 0.0, |
| "L02": 7.4, |
| "L03": 10.8, |
| "L04": 8.6, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 47.8, |
| "F02": 55.6, |
| "F03": 50.0, |
| "F04": 42.9, |
| "F05": 50.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 50.0, |
| "F10": 45.5, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "qwen-image-2-0", |
| "name": "Qwen-Image-2.0", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 16, |
| "accuracy": { |
| "temporal": 44.0, |
| "causal": 47.0, |
| "spatial": 36.0, |
| "logical": 6.5, |
| "counterfactual": 36.0, |
| "hybrid": 0.0, |
| "single": 30.2, |
| "multi": 32.1, |
| "total": 30.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.6, |
| "appearance_consistency": 79.7, |
| "visual_plausibility": 91.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 51.8, |
| "temporal_context_knowledge": 44.2, |
| "temporal_disciplinary_knowledge": 33.3, |
| "causal_common_sense_knowledge": 58.8, |
| "causal_context_knowledge": 27.5, |
| "causal_disciplinary_knowledge": 45.0, |
| "spatial_relation": 37.7, |
| "spatial_structure": 34.0, |
| "logical_explicit_rule_deduction": 7.3, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 30.0, |
| "counterfactual_anomaly_correction_and_generation": 50.0 |
| }, |
| "task_types": { |
| "T01": 45.8, |
| "T02": 66.7, |
| "T03": 38.5, |
| "T04": 65.0, |
| "T05": 50.0, |
| "T06": 42.9, |
| "T07": 50.0, |
| "T08": 53.3, |
| "T09": 35.7, |
| "T10": 60.0, |
| "T11": 12.5, |
| "T12": 25.0, |
| "T13": 12.5, |
| "T14": 55.6, |
| "T15": 25.0, |
| "T16": 33.3, |
| "T17": 0.0, |
| "T18": 75.0, |
| "T19": 66.7, |
| "C01": 61.3, |
| "C02": 63.0, |
| "C03": 50.0, |
| "C04": 20.0, |
| "C05": 50.0, |
| "C06": 10.0, |
| "C07": 30.0, |
| "C08": 24.0, |
| "C09": 73.9, |
| "C10": 75.0, |
| "C11": 0.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 45.5, |
| "S02": 45.5, |
| "S03": 45.5, |
| "S04": 58.3, |
| "S05": 30.8, |
| "S06": 33.3, |
| "S07": 44.4, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 41.7, |
| "S11": 53.3, |
| "S12": 23.1, |
| "S13": 10.5, |
| "S14": 60.0, |
| "L01": 0.0, |
| "L02": 7.4, |
| "L03": 8.1, |
| "L04": 11.4, |
| "L05": 5.1, |
| "L06": 11.1, |
| "L07": 0.0, |
| "F01": 39.1, |
| "F02": 22.2, |
| "F03": 50.0, |
| "F04": 28.6, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 25.0, |
| "F08": 25.0, |
| "F09": 70.0, |
| "F10": 45.5, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "seedream-4-5", |
| "name": "Seedream 4.5", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 17, |
| "accuracy": { |
| "temporal": 42.5, |
| "causal": 42.0, |
| "spatial": 26.5, |
| "logical": 7.5, |
| "counterfactual": 36.0, |
| "hybrid": 6.0, |
| "single": 28.0, |
| "multi": 26.9, |
| "total": 27.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.8, |
| "appearance_consistency": 76.0, |
| "visual_plausibility": 94.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 47.1, |
| "temporal_context_knowledge": 46.2, |
| "temporal_disciplinary_knowledge": 33.3, |
| "causal_common_sense_knowledge": 62.5, |
| "causal_context_knowledge": 17.5, |
| "causal_disciplinary_knowledge": 33.8, |
| "spatial_relation": 24.5, |
| "spatial_structure": 28.7, |
| "logical_explicit_rule_deduction": 10.6, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 28.6, |
| "counterfactual_anomaly_correction_and_generation": 53.3 |
| }, |
| "task_types": { |
| "T01": 37.5, |
| "T02": 66.7, |
| "T03": 53.8, |
| "T04": 50.0, |
| "T05": 25.0, |
| "T06": 42.9, |
| "T07": 75.0, |
| "T08": 53.3, |
| "T09": 35.7, |
| "T10": 46.7, |
| "T11": 50.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 33.3, |
| "T15": 41.7, |
| "T16": 61.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 74.2, |
| "C02": 59.3, |
| "C03": 50.0, |
| "C04": 30.0, |
| "C05": 10.0, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 16.0, |
| "C09": 47.8, |
| "C10": 58.3, |
| "C11": 66.7, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 45.5, |
| "S02": 9.1, |
| "S03": 27.3, |
| "S04": 25.0, |
| "S05": 23.1, |
| "S06": 26.7, |
| "S07": 22.2, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 33.3, |
| "S11": 40.0, |
| "S12": 23.1, |
| "S13": 21.1, |
| "S14": 30.0, |
| "L01": 0.0, |
| "L02": 25.9, |
| "L03": 8.1, |
| "L04": 8.6, |
| "L05": 2.6, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 43.5, |
| "F02": 22.2, |
| "F03": 62.5, |
| "F04": 0.0, |
| "F05": 25.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 25.0, |
| "F09": 60.0, |
| "F10": 36.4, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "seedream-5-0", |
| "name": "Seedream 5.0", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 18, |
| "accuracy": { |
| "temporal": 42.5, |
| "causal": 43.0, |
| "spatial": 26.0, |
| "logical": 5.5, |
| "counterfactual": 30.0, |
| "hybrid": 3.0, |
| "single": 27.2, |
| "multi": 20.5, |
| "total": 26.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 47.8, |
| "appearance_consistency": 71.7, |
| "visual_plausibility": 94.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 57.6, |
| "temporal_context_knowledge": 34.6, |
| "temporal_disciplinary_knowledge": 28.6, |
| "causal_common_sense_knowledge": 52.5, |
| "causal_context_knowledge": 30.0, |
| "causal_disciplinary_knowledge": 40.0, |
| "spatial_relation": 23.6, |
| "spatial_structure": 28.7, |
| "logical_explicit_rule_deduction": 7.3, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 24.3, |
| "counterfactual_anomaly_correction_and_generation": 43.3 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 66.7, |
| "T03": 61.5, |
| "T04": 55.0, |
| "T05": 62.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 20.0, |
| "T09": 35.7, |
| "T10": 40.0, |
| "T11": 50.0, |
| "T12": 0.0, |
| "T13": 37.5, |
| "T14": 33.3, |
| "T15": 33.3, |
| "T16": 27.8, |
| "T17": 40.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 58.1, |
| "C02": 63.0, |
| "C03": 31.8, |
| "C04": 20.0, |
| "C05": 50.0, |
| "C06": 20.0, |
| "C07": 30.0, |
| "C08": 20.0, |
| "C09": 56.5, |
| "C10": 75.0, |
| "C11": 33.3, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 45.5, |
| "S02": 9.1, |
| "S03": 45.5, |
| "S04": 33.3, |
| "S05": 15.4, |
| "S06": 6.7, |
| "S07": 33.3, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 33.3, |
| "S11": 40.0, |
| "S12": 34.6, |
| "S13": 15.8, |
| "S14": 10.0, |
| "L01": 4.2, |
| "L02": 11.1, |
| "L03": 13.5, |
| "L04": 0.0, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 34.8, |
| "F02": 22.2, |
| "F03": 50.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 25.0, |
| "F09": 50.0, |
| "F10": 63.6, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "step-image-edit-2", |
| "name": "Step Image Edit 2", |
| "group": "closed", |
| "multi_image": false, |
| "source_order": 19, |
| "accuracy": { |
| "temporal": 18.5, |
| "causal": 22.9, |
| "spatial": 26.4, |
| "logical": 1.7, |
| "counterfactual": 10.0, |
| "hybrid": 1.0, |
| "single": 14.9, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.0, |
| "appearance_consistency": 68.3, |
| "visual_plausibility": 86.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 28.2, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 10.2, |
| "causal_common_sense_knowledge": 31.6, |
| "causal_context_knowledge": 23.7, |
| "causal_disciplinary_knowledge": 13.3, |
| "spatial_relation": 27.0, |
| "spatial_structure": 25.6, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 20.0 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 11.1, |
| "T03": 46.2, |
| "T04": 35.0, |
| "T05": 37.5, |
| "T06": 28.6, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 16.7, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 41.9, |
| "C02": 14.8, |
| "C03": 38.1, |
| "C04": 10.0, |
| "C05": 25.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 8.3, |
| "C09": 15.8, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 36.4, |
| "S02": 36.4, |
| "S03": 45.5, |
| "S04": 25.0, |
| "S05": 23.1, |
| "S06": 6.7, |
| "S07": 33.3, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 26.7, |
| "S12": 30.8, |
| "S13": 35.3, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 17.4, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "hunyuanimage-3-0-instruct", |
| "name": "HunyuanImage-3.0-Instruct", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 20, |
| "accuracy": { |
| "temporal": 30.5, |
| "causal": 37.5, |
| "spatial": 29.5, |
| "logical": 7.0, |
| "counterfactual": 21.0, |
| "hybrid": 0.0, |
| "single": 22.5, |
| "multi": 29.5, |
| "total": 23.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 38.2, |
| "appearance_consistency": 75.8, |
| "visual_plausibility": 88.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 38.8, |
| "temporal_context_knowledge": 32.7, |
| "temporal_disciplinary_knowledge": 17.5, |
| "causal_common_sense_knowledge": 50.0, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 33.8, |
| "spatial_relation": 26.4, |
| "spatial_structure": 33.0, |
| "logical_explicit_rule_deduction": 9.8, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 12.9, |
| "counterfactual_anomaly_correction_and_generation": 40.0 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 77.8, |
| "T03": 30.8, |
| "T04": 60.0, |
| "T05": 37.5, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 20.0, |
| "T09": 7.1, |
| "T10": 66.7, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 44.4, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 45.2, |
| "C02": 59.3, |
| "C03": 45.5, |
| "C04": 30.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 50.0, |
| "C08": 32.0, |
| "C09": 39.1, |
| "C10": 66.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 27.3, |
| "S02": 27.3, |
| "S03": 27.3, |
| "S04": 50.0, |
| "S05": 30.8, |
| "S06": 13.3, |
| "S07": 22.2, |
| "S08": 22.2, |
| "S09": 16.7, |
| "S10": 33.3, |
| "S11": 26.7, |
| "S12": 26.9, |
| "S13": 36.8, |
| "S14": 50.0, |
| "L01": 12.5, |
| "L02": 0.0, |
| "L03": 13.5, |
| "L04": 11.4, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 21.7, |
| "F02": 22.2, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 70.0, |
| "F10": 18.2, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "qwen-image-edit-2511", |
| "name": "Qwen-Image-Edit-2511", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 21, |
| "accuracy": { |
| "temporal": 22.0, |
| "causal": 24.5, |
| "spatial": 23.5, |
| "logical": 4.5, |
| "counterfactual": 17.0, |
| "hybrid": 5.0, |
| "single": 16.9, |
| "multi": 19.2, |
| "total": 17.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 36.0, |
| "appearance_consistency": 64.0, |
| "visual_plausibility": 90.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 28.2, |
| "temporal_context_knowledge": 25.0, |
| "temporal_disciplinary_knowledge": 11.1, |
| "causal_common_sense_knowledge": 38.8, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 12.5, |
| "spatial_relation": 17.9, |
| "spatial_structure": 29.8, |
| "logical_explicit_rule_deduction": 3.3, |
| "logical_implicit_pattern_induction": 6.5, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 40.0 |
| }, |
| "task_types": { |
| "T01": 16.7, |
| "T02": 44.4, |
| "T03": 46.2, |
| "T04": 30.0, |
| "T05": 37.5, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 40.0, |
| "T09": 0.0, |
| "T10": 46.7, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 45.2, |
| "C02": 48.1, |
| "C03": 18.2, |
| "C04": 20.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 60.0, |
| "C08": 12.0, |
| "C09": 13.0, |
| "C10": 25.0, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 30.8, |
| "S06": 0.0, |
| "S07": 16.7, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 16.7, |
| "S11": 53.3, |
| "S12": 38.5, |
| "S13": 15.8, |
| "S14": 30.0, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 5.7, |
| "L05": 12.8, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 13.0, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 27.3, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "qwen-image-2-1", |
| "name": "Qwen-Image-2.1", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 22, |
| "accuracy": { |
| "temporal": 21.5, |
| "causal": 25.5, |
| "spatial": 24.5, |
| "logical": 2.0, |
| "counterfactual": 16.0, |
| "hybrid": 0.0, |
| "single": 15.0, |
| "multi": 32.1, |
| "total": 16.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.6, |
| "appearance_consistency": 77.6, |
| "visual_plausibility": 86.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 23.5, |
| "temporal_context_knowledge": 28.8, |
| "temporal_disciplinary_knowledge": 12.7, |
| "causal_common_sense_knowledge": 42.5, |
| "causal_context_knowledge": 12.5, |
| "causal_disciplinary_knowledge": 15.0, |
| "spatial_relation": 17.9, |
| "spatial_structure": 31.9, |
| "logical_explicit_rule_deduction": 2.4, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 11.4, |
| "counterfactual_anomaly_correction_and_generation": 26.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 66.7, |
| "T03": 30.8, |
| "T04": 35.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 26.7, |
| "T09": 14.3, |
| "T10": 46.7, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 22.2, |
| "T15": 8.3, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 48.4, |
| "C02": 37.0, |
| "C03": 40.9, |
| "C04": 0.0, |
| "C05": 20.0, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 0.0, |
| "C09": 17.4, |
| "C10": 41.7, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 36.4, |
| "S03": 18.2, |
| "S04": 25.0, |
| "S05": 38.5, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 16.7, |
| "S11": 46.7, |
| "S12": 30.8, |
| "S13": 31.6, |
| "S14": 50.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 8.6, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 5.0, |
| "F01": 21.7, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "firered-image-edit-1-0", |
| "name": "FireRed-Image-Edit-1.0", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 23, |
| "accuracy": { |
| "temporal": 22.0, |
| "causal": 18.0, |
| "spatial": 28.0, |
| "logical": 2.0, |
| "counterfactual": 21.0, |
| "hybrid": 2.0, |
| "single": 16.1, |
| "multi": 19.2, |
| "total": 16.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 32.2, |
| "appearance_consistency": 64.0, |
| "visual_plausibility": 93.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 30.6, |
| "temporal_context_knowledge": 17.3, |
| "temporal_disciplinary_knowledge": 14.3, |
| "causal_common_sense_knowledge": 26.3, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 11.3, |
| "spatial_relation": 24.5, |
| "spatial_structure": 31.9, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 36.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 33.3, |
| "T03": 46.2, |
| "T04": 40.0, |
| "T05": 50.0, |
| "T06": 14.3, |
| "T07": 50.0, |
| "T08": 6.7, |
| "T09": 0.0, |
| "T10": 33.3, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 33.3, |
| "T15": 8.3, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 29.0, |
| "C02": 25.9, |
| "C03": 22.7, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 40.0, |
| "C08": 0.0, |
| "C09": 13.0, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 27.3, |
| "S02": 54.5, |
| "S03": 27.3, |
| "S04": 41.7, |
| "S05": 23.1, |
| "S06": 0.0, |
| "S07": 16.7, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 25.0, |
| "S11": 46.7, |
| "S12": 38.5, |
| "S13": 10.5, |
| "S14": 50.0, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 21.7, |
| "F02": 22.2, |
| "F03": 12.5, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 27.3, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "firered-image-edit-1-1", |
| "name": "FireRed-Image-Edit-1.1", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 24, |
| "accuracy": { |
| "temporal": 22.5, |
| "causal": 23.5, |
| "spatial": 22.5, |
| "logical": 1.5, |
| "counterfactual": 16.0, |
| "hybrid": 2.0, |
| "single": 14.8, |
| "multi": 28.2, |
| "total": 15.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 32.8, |
| "appearance_consistency": 66.2, |
| "visual_plausibility": 93.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 24.7, |
| "temporal_context_knowledge": 28.8, |
| "temporal_disciplinary_knowledge": 14.3, |
| "causal_common_sense_knowledge": 32.5, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 18.8, |
| "spatial_relation": 17.9, |
| "spatial_structure": 27.7, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 36.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 22.2, |
| "T03": 38.5, |
| "T04": 30.0, |
| "T05": 62.5, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 20.0, |
| "T09": 14.3, |
| "T10": 53.3, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 8.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 37.0, |
| "C03": 36.4, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 16.0, |
| "C09": 17.4, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 27.3, |
| "S03": 18.2, |
| "S04": 33.3, |
| "S05": 23.1, |
| "S06": 0.0, |
| "S07": 27.8, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 20.8, |
| "S11": 46.7, |
| "S12": 26.9, |
| "S13": 10.5, |
| "S14": 50.0, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 13.0, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 36.4, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "qwen-image-edit-2509", |
| "name": "Qwen-Image-Edit-2509", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 25, |
| "accuracy": { |
| "temporal": 21.0, |
| "causal": 24.5, |
| "spatial": 20.0, |
| "logical": 0.5, |
| "counterfactual": 16.0, |
| "hybrid": 0.0, |
| "single": 15.0, |
| "multi": 12.8, |
| "total": 14.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 29.8, |
| "appearance_consistency": 61.3, |
| "visual_plausibility": 85.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 24.7, |
| "temporal_context_knowledge": 17.3, |
| "temporal_disciplinary_knowledge": 19.0, |
| "causal_common_sense_knowledge": 37.5, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 16.3, |
| "spatial_relation": 17.9, |
| "spatial_structure": 22.3, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 12.9, |
| "counterfactual_anomaly_correction_and_generation": 23.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 22.2, |
| "T03": 38.5, |
| "T04": 20.0, |
| "T05": 62.5, |
| "T06": 28.6, |
| "T07": 50.0, |
| "T08": 13.3, |
| "T09": 0.0, |
| "T10": 26.7, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 22.2, |
| "T15": 25.0, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 40.7, |
| "C03": 31.8, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 50.0, |
| "C08": 12.0, |
| "C09": 17.4, |
| "C10": 25.0, |
| "C11": 0.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 36.4, |
| "S03": 36.4, |
| "S04": 25.0, |
| "S05": 15.4, |
| "S06": 0.0, |
| "S07": 22.2, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 12.5, |
| "S11": 46.7, |
| "S12": 30.8, |
| "S13": 15.8, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 30.4, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 27.3, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "hidream-o1-image", |
| "name": "HiDream-O1-Image", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 26, |
| "accuracy": { |
| "temporal": 27.5, |
| "causal": 18.0, |
| "spatial": 20.5, |
| "logical": 3.0, |
| "counterfactual": 5.0, |
| "hybrid": 0.0, |
| "single": 13.6, |
| "multi": 23.1, |
| "total": 14.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 35.2, |
| "appearance_consistency": 57.3, |
| "visual_plausibility": 87.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 40.0, |
| "temporal_context_knowledge": 26.9, |
| "temporal_disciplinary_knowledge": 11.1, |
| "causal_common_sense_knowledge": 31.3, |
| "causal_context_knowledge": 2.5, |
| "causal_disciplinary_knowledge": 12.5, |
| "spatial_relation": 17.9, |
| "spatial_structure": 23.4, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 1.4, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 41.7, |
| "T02": 77.8, |
| "T03": 30.8, |
| "T04": 50.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 20.0, |
| "T09": 7.1, |
| "T10": 40.0, |
| "T11": 50.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 22.2, |
| "T15": 0.0, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 37.0, |
| "C03": 13.6, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 10.0, |
| "C08": 8.0, |
| "C09": 17.4, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 23.1, |
| "S06": 6.7, |
| "S07": 22.2, |
| "S08": 11.1, |
| "S09": 16.7, |
| "S10": 33.3, |
| "S11": 40.0, |
| "S12": 11.5, |
| "S13": 15.8, |
| "S14": 20.0, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 0.0, |
| "L05": 10.3, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 4.3, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "flux-2-dev", |
| "name": "FLUX.2 Dev", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 27, |
| "accuracy": { |
| "temporal": 19.5, |
| "causal": 27.5, |
| "spatial": 17.0, |
| "logical": 1.0, |
| "counterfactual": 10.0, |
| "hybrid": 1.0, |
| "single": 12.8, |
| "multi": 29.5, |
| "total": 14.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.1, |
| "appearance_consistency": 57.7, |
| "visual_plausibility": 91.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 18.8, |
| "temporal_context_knowledge": 28.8, |
| "temporal_disciplinary_knowledge": 12.7, |
| "causal_common_sense_knowledge": 40.0, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 18.8, |
| "spatial_relation": 9.4, |
| "spatial_structure": 25.5, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 26.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 55.6, |
| "T03": 23.1, |
| "T04": 15.0, |
| "T05": 37.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 20.0, |
| "T09": 14.3, |
| "T10": 46.7, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 45.2, |
| "C02": 33.3, |
| "C03": 40.9, |
| "C04": 10.0, |
| "C05": 10.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 12.0, |
| "C09": 21.7, |
| "C10": 25.0, |
| "C11": 33.3, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 9.1, |
| "S03": 18.2, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 11.1, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 25.0, |
| "S11": 20.0, |
| "S12": 15.4, |
| "S13": 21.1, |
| "S14": 70.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 0.0, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 27.3, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "flux-2-klein-9b", |
| "name": "FLUX.2 Klein 9B", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 28, |
| "accuracy": { |
| "temporal": 16.0, |
| "causal": 16.5, |
| "spatial": 22.0, |
| "logical": 0.5, |
| "counterfactual": 17.0, |
| "hybrid": 2.0, |
| "single": 11.4, |
| "multi": 30.8, |
| "total": 12.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 28.9, |
| "appearance_consistency": 67.2, |
| "visual_plausibility": 92.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 11.8, |
| "temporal_context_knowledge": 30.8, |
| "temporal_disciplinary_knowledge": 9.5, |
| "causal_common_sense_knowledge": 26.3, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 7.5, |
| "spatial_relation": 16.0, |
| "spatial_structure": 28.7, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 15.7, |
| "counterfactual_anomaly_correction_and_generation": 20.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 33.3, |
| "T03": 23.1, |
| "T04": 10.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 20.0, |
| "T09": 0.0, |
| "T10": 53.3, |
| "T11": 62.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 50.0, |
| "T19": 0.0, |
| "C01": 35.5, |
| "C02": 22.2, |
| "C03": 18.2, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 0.0, |
| "C09": 8.7, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 36.4, |
| "S04": 25.0, |
| "S05": 23.1, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 25.0, |
| "S11": 33.3, |
| "S12": 23.1, |
| "S13": 15.8, |
| "S14": 70.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 17.4, |
| "F02": 55.6, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 27.3, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "joyai-image-edit-plus", |
| "name": "JoyAI-Image-Edit-Plus", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 29, |
| "accuracy": { |
| "temporal": 16.5, |
| "causal": 16.0, |
| "spatial": 20.0, |
| "logical": 4.0, |
| "counterfactual": 13.0, |
| "hybrid": 3.0, |
| "single": 11.7, |
| "multi": 26.9, |
| "total": 12.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.7, |
| "appearance_consistency": 76.9, |
| "visual_plausibility": 92.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 12.9, |
| "temporal_context_knowledge": 32.7, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 28.8, |
| "causal_context_knowledge": 10.0, |
| "causal_disciplinary_knowledge": 6.3, |
| "spatial_relation": 13.2, |
| "spatial_structure": 27.7, |
| "logical_explicit_rule_deduction": 5.7, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 23.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 22.2, |
| "T03": 23.1, |
| "T04": 5.0, |
| "T05": 37.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 20.0, |
| "T09": 7.1, |
| "T10": 53.3, |
| "T11": 62.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 25.9, |
| "C03": 27.3, |
| "C04": 10.0, |
| "C05": 10.0, |
| "C06": 0.0, |
| "C07": 20.0, |
| "C08": 4.0, |
| "C09": 8.7, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 18.2, |
| "S03": 18.2, |
| "S04": 16.7, |
| "S05": 15.4, |
| "S06": 6.7, |
| "S07": 16.7, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 25.0, |
| "S11": 40.0, |
| "S12": 30.8, |
| "S13": 15.8, |
| "S14": 30.0, |
| "L01": 0.0, |
| "L02": 7.4, |
| "L03": 0.0, |
| "L04": 14.3, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 33.3, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "sensenova-u1-a3b-mot-sft", |
| "name": "SenseNova-U1-A3B-MoT-SFT", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 30, |
| "accuracy": { |
| "temporal": 20.5, |
| "causal": 25.5, |
| "spatial": 2.5, |
| "logical": 3.0, |
| "counterfactual": 17.0, |
| "hybrid": 0.0, |
| "single": 12.9, |
| "multi": 1.3, |
| "total": 12.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 38.0, |
| "appearance_consistency": 53.0, |
| "visual_plausibility": 58.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 41.2, |
| "temporal_context_knowledge": 1.9, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 40.0, |
| "causal_context_knowledge": 5.0, |
| "causal_disciplinary_knowledge": 21.3, |
| "spatial_relation": 0.0, |
| "spatial_structure": 5.3, |
| "logical_explicit_rule_deduction": 3.3, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 18.6, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 66.7, |
| "T03": 38.5, |
| "T04": 35.0, |
| "T05": 0.0, |
| "T06": 28.6, |
| "T07": 0.0, |
| "T08": 6.7, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 48.4, |
| "C02": 29.6, |
| "C03": 40.9, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 10.0, |
| "C08": 12.0, |
| "C09": 39.1, |
| "C10": 33.3, |
| "C11": 33.3, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 12.5, |
| "S11": 6.7, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": 0.0, |
| "L01": 12.5, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 11.1, |
| "L07": 0.0, |
| "F01": 21.7, |
| "F02": 22.2, |
| "F03": 50.0, |
| "F04": 14.3, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "unipic-3-0", |
| "name": "UniPic 3.0", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 31, |
| "accuracy": { |
| "temporal": 18.5, |
| "causal": 17.5, |
| "spatial": 18.0, |
| "logical": 0.5, |
| "counterfactual": 9.0, |
| "hybrid": 1.0, |
| "single": 11.1, |
| "multi": 21.8, |
| "total": 11.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 28.2, |
| "appearance_consistency": 60.7, |
| "visual_plausibility": 83.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 17.6, |
| "temporal_context_knowledge": 30.8, |
| "temporal_disciplinary_knowledge": 9.5, |
| "causal_common_sense_knowledge": 23.8, |
| "causal_context_knowledge": 17.5, |
| "causal_disciplinary_knowledge": 11.3, |
| "spatial_relation": 16.0, |
| "spatial_structure": 20.2, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 11.1, |
| "T03": 38.5, |
| "T04": 25.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 13.3, |
| "T09": 7.1, |
| "T10": 60.0, |
| "T11": 50.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 33.3, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 18.5, |
| "C03": 9.1, |
| "C04": 20.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 40.0, |
| "C08": 12.0, |
| "C09": 17.4, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 18.2, |
| "S02": 27.3, |
| "S03": 9.1, |
| "S04": 25.0, |
| "S05": 15.4, |
| "S06": 0.0, |
| "S07": 22.2, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 12.5, |
| "S11": 33.3, |
| "S12": 26.9, |
| "S13": 21.1, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 17.4, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 18.2, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "bagel-w-cot", |
| "name": "BAGEL (w/ CoT)", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 32, |
| "accuracy": { |
| "temporal": 18.5, |
| "causal": 16.0, |
| "spatial": 16.0, |
| "logical": 1.5, |
| "counterfactual": 10.0, |
| "hybrid": 0.0, |
| "single": 10.4, |
| "multi": 23.1, |
| "total": 11.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 33.3, |
| "appearance_consistency": 61.2, |
| "visual_plausibility": 75.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 22.4, |
| "temporal_context_knowledge": 23.1, |
| "temporal_disciplinary_knowledge": 9.5, |
| "causal_common_sense_knowledge": 21.3, |
| "causal_context_knowledge": 10.0, |
| "causal_disciplinary_knowledge": 13.8, |
| "spatial_relation": 11.3, |
| "spatial_structure": 21.3, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 10.0, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 25.0, |
| "T02": 55.6, |
| "T03": 15.4, |
| "T04": 15.0, |
| "T05": 25.0, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 26.7, |
| "T09": 7.1, |
| "T10": 33.3, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 22.2, |
| "T15": 16.7, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 19.4, |
| "C02": 18.5, |
| "C03": 27.3, |
| "C04": 20.0, |
| "C05": 10.0, |
| "C06": 0.0, |
| "C07": 10.0, |
| "C08": 4.0, |
| "C09": 21.7, |
| "C10": 41.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 36.4, |
| "S04": 33.3, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 16.7, |
| "S11": 6.7, |
| "S12": 11.5, |
| "S13": 31.6, |
| "S14": 60.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 5.0, |
| "F01": 21.7, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "sensenova-u1-8b-mot-sft", |
| "name": "SenseNova-U1-8B-MoT-SFT", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 33, |
| "accuracy": { |
| "temporal": 16.5, |
| "causal": 22.5, |
| "spatial": 7.5, |
| "logical": 3.5, |
| "counterfactual": 13.0, |
| "hybrid": 0.0, |
| "single": 12.3, |
| "multi": 0.0, |
| "total": 11.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 36.0, |
| "appearance_consistency": 58.1, |
| "visual_plausibility": 60.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 28.2, |
| "temporal_context_knowledge": 3.8, |
| "temporal_disciplinary_knowledge": 11.1, |
| "causal_common_sense_knowledge": 35.0, |
| "causal_context_knowledge": 10.0, |
| "causal_disciplinary_knowledge": 16.3, |
| "spatial_relation": 6.6, |
| "spatial_structure": 8.5, |
| "logical_explicit_rule_deduction": 4.1, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 11.4, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 41.7, |
| "T02": 66.7, |
| "T03": 15.4, |
| "T04": 30.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 13.3, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 8.3, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 41.9, |
| "C02": 37.0, |
| "C03": 22.7, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 20.0, |
| "C09": 13.0, |
| "C10": 41.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 18.2, |
| "S03": 18.2, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 6.7, |
| "S07": 5.6, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 16.7, |
| "S11": 6.7, |
| "S12": 11.5, |
| "S13": 0.0, |
| "S14": 0.0, |
| "L01": 8.3, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 5.7, |
| "L05": 0.0, |
| "L06": 11.1, |
| "L07": 0.0, |
| "F01": 13.0, |
| "F02": 33.3, |
| "F03": 12.5, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "flux-2-klein-4b", |
| "name": "FLUX.2 Klein 4B", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 34, |
| "accuracy": { |
| "temporal": 15.5, |
| "causal": 14.5, |
| "spatial": 17.0, |
| "logical": 2.5, |
| "counterfactual": 8.0, |
| "hybrid": 1.0, |
| "single": 8.7, |
| "multi": 35.9, |
| "total": 10.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 25.6, |
| "appearance_consistency": 71.0, |
| "visual_plausibility": 90.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 11.8, |
| "temporal_context_knowledge": 36.5, |
| "temporal_disciplinary_knowledge": 3.2, |
| "causal_common_sense_knowledge": 17.5, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 8.8, |
| "spatial_relation": 10.4, |
| "spatial_structure": 24.5, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 11.1, |
| "T03": 30.8, |
| "T04": 10.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 26.7, |
| "T09": 14.3, |
| "T10": 73.3, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 11.1, |
| "C03": 4.5, |
| "C04": 0.0, |
| "C05": 10.0, |
| "C06": 30.0, |
| "C07": 40.0, |
| "C08": 4.0, |
| "C09": 8.7, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 9.1, |
| "S04": 25.0, |
| "S05": 15.4, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 4.2, |
| "S11": 26.7, |
| "S12": 30.8, |
| "S13": 15.8, |
| "S14": 70.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 10.3, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 33.3, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "uniworld-v2", |
| "name": "UniWorld-V2", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 35, |
| "accuracy": { |
| "temporal": 10.0, |
| "causal": 18.0, |
| "spatial": 12.0, |
| "logical": 0.5, |
| "counterfactual": 13.0, |
| "hybrid": 1.0, |
| "single": 9.9, |
| "multi": 5.1, |
| "total": 9.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 30.7, |
| "appearance_consistency": 51.6, |
| "visual_plausibility": 84.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 14.1, |
| "temporal_context_knowledge": 7.7, |
| "temporal_disciplinary_knowledge": 6.3, |
| "causal_common_sense_knowledge": 25.0, |
| "causal_context_knowledge": 22.5, |
| "causal_disciplinary_knowledge": 8.8, |
| "spatial_relation": 14.2, |
| "spatial_structure": 9.6, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 30.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 11.1, |
| "T03": 23.1, |
| "T04": 15.0, |
| "T05": 37.5, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 13.3, |
| "T09": 0.0, |
| "T10": 6.7, |
| "T11": 12.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 29.0, |
| "C02": 18.5, |
| "C03": 27.3, |
| "C04": 20.0, |
| "C05": 0.0, |
| "C06": 30.0, |
| "C07": 40.0, |
| "C08": 4.0, |
| "C09": 13.0, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 9.1, |
| "S03": 27.3, |
| "S04": 25.0, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 16.7, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 12.5, |
| "S11": 6.7, |
| "S12": 11.5, |
| "S13": 5.3, |
| "S14": 10.0, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 27.3, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "bagel", |
| "name": "BAGEL", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 36, |
| "accuracy": { |
| "temporal": 6.5, |
| "causal": 6.0, |
| "spatial": 8.0, |
| "logical": 1.0, |
| "counterfactual": 2.0, |
| "hybrid": 0.0, |
| "single": 3.1, |
| "multi": 20.5, |
| "total": 4.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 23.1, |
| "appearance_consistency": 47.7, |
| "visual_plausibility": 76.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 2.4, |
| "temporal_context_knowledge": 19.2, |
| "temporal_disciplinary_knowledge": 1.6, |
| "causal_common_sense_knowledge": 11.3, |
| "causal_context_knowledge": 2.5, |
| "causal_disciplinary_knowledge": 2.5, |
| "spatial_relation": 5.7, |
| "spatial_structure": 10.6, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 0.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 11.1, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 13.3, |
| "T09": 7.1, |
| "T10": 26.7, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 16.1, |
| "C02": 7.4, |
| "C03": 9.1, |
| "C04": 0.0, |
| "C05": 10.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 4.0, |
| "C09": 0.0, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 9.1, |
| "S04": 8.3, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 0.0, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 8.3, |
| "S11": 0.0, |
| "S12": 7.7, |
| "S13": 15.8, |
| "S14": 30.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 10.0, |
| "F01": 4.3, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "omnigen2", |
| "name": "OmniGen2", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 37, |
| "accuracy": { |
| "temporal": 7.0, |
| "causal": 6.0, |
| "spatial": 5.5, |
| "logical": 0.0, |
| "counterfactual": 8.0, |
| "hybrid": 0.0, |
| "single": 3.7, |
| "multi": 14.1, |
| "total": 4.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 15.4, |
| "appearance_consistency": 58.4, |
| "visual_plausibility": 80.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 3.5, |
| "temporal_context_knowledge": 15.4, |
| "temporal_disciplinary_knowledge": 4.8, |
| "causal_common_sense_knowledge": 6.3, |
| "causal_context_knowledge": 7.5, |
| "causal_disciplinary_knowledge": 5.0, |
| "spatial_relation": 3.8, |
| "spatial_structure": 7.4, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 6.7 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 15.4, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 6.7, |
| "T09": 0.0, |
| "T10": 26.7, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 9.7, |
| "C02": 3.7, |
| "C03": 4.5, |
| "C04": 0.0, |
| "C05": 10.0, |
| "C06": 10.0, |
| "C07": 10.0, |
| "C08": 4.0, |
| "C09": 4.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 18.2, |
| "S04": 8.3, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 0.0, |
| "S11": 6.7, |
| "S12": 11.5, |
| "S13": 15.8, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 17.4, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 18.2, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "omnigen", |
| "name": "OmniGen", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 38, |
| "accuracy": { |
| "temporal": 4.5, |
| "causal": 4.0, |
| "spatial": 5.0, |
| "logical": 1.5, |
| "counterfactual": 1.0, |
| "hybrid": 0.0, |
| "single": 2.7, |
| "multi": 7.7, |
| "total": 3.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 13.6, |
| "appearance_consistency": 44.5, |
| "visual_plausibility": 61.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 3.5, |
| "temporal_context_knowledge": 7.7, |
| "temporal_disciplinary_knowledge": 3.2, |
| "causal_common_sense_knowledge": 2.5, |
| "causal_context_knowledge": 5.0, |
| "causal_disciplinary_knowledge": 5.0, |
| "spatial_relation": 0.9, |
| "spatial_structure": 9.6, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 0.0, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 26.7, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 6.5, |
| "C02": 0.0, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 10.0, |
| "C08": 8.0, |
| "C09": 4.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 8.3, |
| "S11": 6.7, |
| "S12": 11.5, |
| "S13": 15.8, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 0.0, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "emu2-gen", |
| "name": "Emu2-Gen", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 39, |
| "accuracy": { |
| "temporal": 4.0, |
| "causal": 1.5, |
| "spatial": 0.5, |
| "logical": 0.5, |
| "counterfactual": 1.0, |
| "hybrid": 0.0, |
| "single": 1.4, |
| "multi": 1.3, |
| "total": 1.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 10.7, |
| "appearance_consistency": 25.5, |
| "visual_plausibility": 62.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 2.4, |
| "temporal_context_knowledge": 1.9, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 3.8, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 0.0, |
| "spatial_relation": 0.0, |
| "spatial_structure": 1.1, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 0.0, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 6.7, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 6.5, |
| "C02": 3.7, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 0.0, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "joyai-image-edit", |
| "name": "JoyAI-Image-Edit", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 40, |
| "accuracy": { |
| "temporal": 17.9, |
| "causal": 24.0, |
| "spatial": 22.0, |
| "logical": 2.2, |
| "counterfactual": 16.0, |
| "hybrid": 2.0, |
| "single": 15.0, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.6, |
| "appearance_consistency": 71.9, |
| "visual_plausibility": 90.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 24.7, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 13.6, |
| "causal_common_sense_knowledge": 39.2, |
| "causal_context_knowledge": 15.8, |
| "causal_disciplinary_knowledge": 12.0, |
| "spatial_relation": 20.0, |
| "spatial_structure": 24.4, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 5.3, |
| "counterfactual_counterfactual_imagination": 11.4, |
| "counterfactual_anomaly_correction_and_generation": 26.7 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 44.4, |
| "T03": 53.8, |
| "T04": 30.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 8.3, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 75.0, |
| "T19": 0.0, |
| "C01": 41.9, |
| "C02": 37.0, |
| "C03": 38.1, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 4.2, |
| "C09": 15.8, |
| "C10": 25.0, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 27.3, |
| "S03": 18.2, |
| "S04": 25.0, |
| "S05": 30.8, |
| "S06": 13.3, |
| "S07": 22.2, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 16.7, |
| "S11": 33.3, |
| "S12": 30.8, |
| "S13": 17.6, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 0.0, |
| "L05": 5.1, |
| "L06": 5.6, |
| "L07": null, |
| "F01": 13.0, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 25.0, |
| "F09": 30.0, |
| "F10": 36.4, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "step1x-edit-thinking", |
| "name": "Step1X-Edit (thinking)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 41, |
| "accuracy": { |
| "temporal": 19.6, |
| "causal": 27.1, |
| "spatial": 14.3, |
| "logical": 0.6, |
| "counterfactual": 16.0, |
| "hybrid": 2.0, |
| "single": 14.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 28.5, |
| "appearance_consistency": 70.3, |
| "visual_plausibility": 89.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 28.2, |
| "temporal_context_knowledge": 8.3, |
| "temporal_disciplinary_knowledge": 11.9, |
| "causal_common_sense_knowledge": 31.6, |
| "causal_context_knowledge": 26.3, |
| "causal_disciplinary_knowledge": 22.7, |
| "spatial_relation": 12.0, |
| "spatial_structure": 17.1, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 11.4, |
| "counterfactual_anomaly_correction_and_generation": 26.7 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 66.7, |
| "T03": 30.8, |
| "T04": 30.0, |
| "T05": 12.5, |
| "T06": 28.6, |
| "T07": 0.0, |
| "T08": 18.2, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 16.7, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 33.3, |
| "C03": 28.6, |
| "C04": 20.0, |
| "C05": 12.5, |
| "C06": 30.0, |
| "C07": 40.0, |
| "C08": 12.5, |
| "C09": 31.6, |
| "C10": 41.7, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 9.1, |
| "S03": 18.2, |
| "S04": 16.7, |
| "S05": 15.4, |
| "S06": 0.0, |
| "S07": 16.7, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 16.7, |
| "S11": 53.3, |
| "S12": 3.8, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 26.1, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 18.2, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "boogu-image-0-1-edit", |
| "name": "Boogu-Image-0.1-Edit", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 42, |
| "accuracy": { |
| "temporal": 15.5, |
| "causal": 21.9, |
| "spatial": 17.6, |
| "logical": 6.1, |
| "counterfactual": 11.0, |
| "hybrid": 3.0, |
| "single": 13.6, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 27.5, |
| "appearance_consistency": 79.8, |
| "visual_plausibility": 91.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 16.5, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 18.6, |
| "causal_common_sense_knowledge": 35.4, |
| "causal_context_knowledge": 15.8, |
| "causal_disciplinary_knowledge": 10.7, |
| "spatial_relation": 15.0, |
| "spatial_structure": 20.7, |
| "logical_explicit_rule_deduction": 3.3, |
| "logical_implicit_pattern_induction": 12.3, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 22.2, |
| "T03": 30.8, |
| "T04": 15.0, |
| "T05": 37.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 25.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 25.0, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 48.4, |
| "C02": 25.9, |
| "C03": 28.6, |
| "C04": 20.0, |
| "C05": 0.0, |
| "C06": 20.0, |
| "C07": 20.0, |
| "C08": 12.5, |
| "C09": 5.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 18.2, |
| "S04": 33.3, |
| "S05": 23.1, |
| "S06": 0.0, |
| "S07": 11.1, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 16.7, |
| "S11": 20.0, |
| "S12": 23.1, |
| "S13": 23.5, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 8.6, |
| "L05": 17.9, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 13.0, |
| "F02": 33.3, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 18.2, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "step1x-edit-thinking-reflection", |
| "name": "Step1X-Edit (thinking + reflection)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 43, |
| "accuracy": { |
| "temporal": 21.4, |
| "causal": 22.9, |
| "spatial": 9.9, |
| "logical": 1.7, |
| "counterfactual": 19.0, |
| "hybrid": 1.0, |
| "single": 13.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 30.2, |
| "appearance_consistency": 68.0, |
| "visual_plausibility": 89.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 30.6, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 16.9, |
| "causal_common_sense_knowledge": 34.2, |
| "causal_context_knowledge": 15.8, |
| "causal_disciplinary_knowledge": 14.7, |
| "spatial_relation": 13.0, |
| "spatial_structure": 6.1, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 18.6, |
| "counterfactual_anomaly_correction_and_generation": 20.0 |
| }, |
| "task_types": { |
| "T01": 25.0, |
| "T02": 33.3, |
| "T03": 46.2, |
| "T04": 30.0, |
| "T05": 25.0, |
| "T06": 28.6, |
| "T07": 25.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 33.3, |
| "T15": 16.7, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 41.9, |
| "C02": 29.6, |
| "C03": 28.6, |
| "C04": 0.0, |
| "C05": 12.5, |
| "C06": 10.0, |
| "C07": 40.0, |
| "C08": 12.5, |
| "C09": 31.6, |
| "C10": 0.0, |
| "C11": 33.3, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 9.1, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 16.7, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 4.2, |
| "S11": 20.0, |
| "S12": 0.0, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 26.1, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 28.6, |
| "F05": 37.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 27.3, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "longcat-image-edit", |
| "name": "LongCat-Image-Edit", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 44, |
| "accuracy": { |
| "temporal": 10.1, |
| "causal": 20.8, |
| "spatial": 15.4, |
| "logical": 1.1, |
| "counterfactual": 9.0, |
| "hybrid": 0.0, |
| "single": 10.4, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 25.7, |
| "appearance_consistency": 62.0, |
| "visual_plausibility": 83.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 11.8, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 11.9, |
| "causal_common_sense_knowledge": 30.4, |
| "causal_context_knowledge": 18.4, |
| "causal_disciplinary_knowledge": 12.0, |
| "spatial_relation": 15.0, |
| "spatial_structure": 15.9, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 23.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 0.0, |
| "T03": 23.1, |
| "T04": 10.0, |
| "T05": 37.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 16.7, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 45.2, |
| "C02": 22.2, |
| "C03": 19.0, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 20.0, |
| "C07": 40.0, |
| "C08": 4.2, |
| "C09": 21.1, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 9.1, |
| "S04": 25.0, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 16.7, |
| "S08": 22.2, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 40.0, |
| "S12": 11.5, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 8.7, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 50.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "step1x-edit-base", |
| "name": "Step1X-Edit (base)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 45, |
| "accuracy": { |
| "temporal": 13.1, |
| "causal": 18.8, |
| "spatial": 10.4, |
| "logical": 1.1, |
| "counterfactual": 14.0, |
| "hybrid": 1.0, |
| "single": 10.2, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.0, |
| "appearance_consistency": 66.1, |
| "visual_plausibility": 87.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 17.6, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 10.2, |
| "causal_common_sense_knowledge": 27.8, |
| "causal_context_knowledge": 18.4, |
| "causal_disciplinary_knowledge": 9.3, |
| "spatial_relation": 8.0, |
| "spatial_structure": 13.4, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 16.7, |
| "T02": 33.3, |
| "T03": 23.1, |
| "T04": 15.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 18.5, |
| "C03": 23.8, |
| "C04": 30.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 30.0, |
| "C08": 4.2, |
| "C09": 15.8, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 18.2, |
| "S04": 25.0, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 26.7, |
| "S12": 7.7, |
| "S13": 11.8, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 30.4, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "internvl-u-w-cot", |
| "name": "InternVL-U (w/ CoT)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 46, |
| "accuracy": { |
| "temporal": 8.9, |
| "causal": 14.1, |
| "spatial": 4.9, |
| "logical": 1.1, |
| "counterfactual": 16.0, |
| "hybrid": 0.0, |
| "single": 7.5, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 27.8, |
| "appearance_consistency": 52.1, |
| "visual_plausibility": 71.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 11.8, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 6.8, |
| "causal_common_sense_knowledge": 19.0, |
| "causal_context_knowledge": 7.9, |
| "causal_disciplinary_knowledge": 12.0, |
| "spatial_relation": 4.0, |
| "spatial_structure": 6.1, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 17.1, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 12.5, |
| "T02": 33.3, |
| "T03": 7.7, |
| "T04": 10.0, |
| "T05": 0.0, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 0.0, |
| "T15": 16.7, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 18.5, |
| "C03": 9.5, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 8.3, |
| "C09": 26.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 11.1, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 4.2, |
| "S11": 6.7, |
| "S12": 7.7, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 34.8, |
| "F02": 22.2, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "flux-1-kontext-dev", |
| "name": "FLUX.1 Kontext Dev", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 47, |
| "accuracy": { |
| "temporal": 5.4, |
| "causal": 9.4, |
| "spatial": 12.1, |
| "logical": 1.7, |
| "counterfactual": 7.0, |
| "hybrid": 0.0, |
| "single": 6.4, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 18.6, |
| "appearance_consistency": 72.8, |
| "visual_plausibility": 91.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 7.1, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 5.1, |
| "causal_common_sense_knowledge": 12.7, |
| "causal_context_knowledge": 10.5, |
| "causal_disciplinary_knowledge": 5.3, |
| "spatial_relation": 7.0, |
| "spatial_structure": 18.3, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 6.7 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 0.0, |
| "T03": 30.8, |
| "T04": 5.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 7.4, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 30.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 27.3, |
| "S04": 0.0, |
| "S05": 15.4, |
| "S06": 0.0, |
| "S07": 11.1, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 8.3, |
| "S11": 33.3, |
| "S12": 19.2, |
| "S13": 17.6, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 17.4, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "llada-image", |
| "name": "LLaDA-Image", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 48, |
| "accuracy": { |
| "temporal": 7.1, |
| "causal": 4.7, |
| "spatial": 3.8, |
| "logical": 0.0, |
| "counterfactual": 4.0, |
| "hybrid": 0.0, |
| "single": 3.5, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 21.7, |
| "appearance_consistency": 26.7, |
| "visual_plausibility": 78.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 10.6, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 5.1, |
| "causal_common_sense_knowledge": 6.3, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 5.3, |
| "spatial_relation": 0.0, |
| "spatial_structure": 8.5, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 4.3, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 11.1, |
| "T03": 7.7, |
| "T04": 10.0, |
| "T05": 12.5, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 12.9, |
| "C02": 0.0, |
| "C03": 4.8, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 4.2, |
| "C09": 5.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 6.7, |
| "S12": 11.5, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 0.0, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "ovis-u1", |
| "name": "Ovis-U1", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 49, |
| "accuracy": { |
| "temporal": 4.8, |
| "causal": 6.3, |
| "spatial": 2.2, |
| "logical": 1.7, |
| "counterfactual": 2.0, |
| "hybrid": 0.0, |
| "single": 3.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 20.5, |
| "appearance_consistency": 32.1, |
| "visual_plausibility": 71.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 7.1, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 3.4, |
| "causal_common_sense_knowledge": 8.9, |
| "causal_context_knowledge": 5.3, |
| "causal_disciplinary_knowledge": 4.0, |
| "spatial_relation": 1.0, |
| "spatial_structure": 3.7, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 0.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 23.1, |
| "T04": 5.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 5.6, |
| "T17": 20.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 16.1, |
| "C02": 7.4, |
| "C03": 0.0, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 8.3, |
| "S11": 6.7, |
| "S12": 0.0, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 11.1, |
| "L07": null, |
| "F01": 4.3, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "internvl-u", |
| "name": "InternVL-U", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 50, |
| "accuracy": { |
| "temporal": 3.6, |
| "causal": 2.6, |
| "spatial": 3.8, |
| "logical": 0.6, |
| "counterfactual": 5.0, |
| "hybrid": 0.0, |
| "single": 2.6, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 21.0, |
| "appearance_consistency": 39.7, |
| "visual_plausibility": 63.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 5.9, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 1.7, |
| "causal_common_sense_knowledge": 3.8, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 2.7, |
| "spatial_relation": 2.0, |
| "spatial_structure": 6.1, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 0.0, |
| "T03": 15.4, |
| "T04": 10.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 6.5, |
| "C02": 3.7, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 16.7, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 8.3, |
| "S11": 0.0, |
| "S12": 11.5, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 13.0, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "unipic2-sd3-5m-kontext-2b", |
| "name": "UniPic2-SD3.5M-Kontext-2B", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 51, |
| "accuracy": { |
| "temporal": 1.2, |
| "causal": 2.1, |
| "spatial": 0.5, |
| "logical": 0.0, |
| "counterfactual": 3.0, |
| "hybrid": 0.0, |
| "single": 1.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 16.2, |
| "appearance_consistency": 34.4, |
| "visual_plausibility": 54.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 2.4, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 0.0, |
| "causal_common_sense_knowledge": 1.3, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 4.0, |
| "spatial_relation": 0.0, |
| "spatial_structure": 1.2, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 4.3, |
| "counterfactual_anomaly_correction_and_generation": 0.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 3.2, |
| "C02": 0.0, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 13.0, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "lumina-dimoo", |
| "name": "Lumina-DiMOO", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 52, |
| "accuracy": { |
| "temporal": 0.6, |
| "causal": 1.6, |
| "spatial": 0.0, |
| "logical": 0.6, |
| "counterfactual": 4.0, |
| "hybrid": 0.0, |
| "single": 1.0, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 11.2, |
| "appearance_consistency": 46.8, |
| "visual_plausibility": 63.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 1.2, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 0.0, |
| "causal_common_sense_knowledge": 2.5, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 1.3, |
| "spatial_relation": 0.0, |
| "spatial_structure": 0.0, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 4.3, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 0.0, |
| "C02": 3.7, |
| "C03": 4.8, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 0.0, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 0.0, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "uniworld-v1", |
| "name": "UniWorld-V1", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 53, |
| "accuracy": { |
| "temporal": 1.2, |
| "causal": 1.0, |
| "spatial": 0.5, |
| "logical": 0.6, |
| "counterfactual": 1.0, |
| "hybrid": 0.0, |
| "single": 0.8, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 15.8, |
| "appearance_consistency": 23.3, |
| "visual_plausibility": 58.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 2.4, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 0.0, |
| "causal_common_sense_knowledge": 2.5, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 0.0, |
| "spatial_relation": 0.0, |
| "spatial_structure": 1.2, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 0.0, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 15.4, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 3.2, |
| "C02": 3.7, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 0.0, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "rise-agent-ours", |
| "name": "RISE-Agent (Ours)", |
| "group": "agentic", |
| "multi_image": true, |
| "source_order": 54, |
| "accuracy": { |
| "temporal": 58.5, |
| "causal": 58.0, |
| "spatial": 37.5, |
| "logical": 39.0, |
| "counterfactual": 66.0, |
| "hybrid": 28.0, |
| "single": 48.3, |
| "multi": 44.9, |
| "total": 48.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 67.6, |
| "appearance_consistency": 90.6, |
| "visual_plausibility": 92.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 64.7, |
| "temporal_context_knowledge": 57.7, |
| "temporal_disciplinary_knowledge": 50.8, |
| "causal_common_sense_knowledge": 78.8, |
| "causal_context_knowledge": 40.0, |
| "causal_disciplinary_knowledge": 46.3, |
| "spatial_relation": 36.8, |
| "spatial_structure": 38.3, |
| "logical_explicit_rule_deduction": 47.2, |
| "logical_implicit_pattern_induction": 26.0, |
| "counterfactual_counterfactual_imagination": 70.0, |
| "counterfactual_anomaly_correction_and_generation": 56.7 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 88.9, |
| "T03": 61.5, |
| "T04": 70.0, |
| "T05": 62.5, |
| "T06": 57.1, |
| "T07": 75.0, |
| "T08": 60.0, |
| "T09": 42.9, |
| "T10": 80.0, |
| "T11": 37.5, |
| "T12": 50.0, |
| "T13": 50.0, |
| "T14": 55.6, |
| "T15": 58.3, |
| "T16": 50.0, |
| "T17": 20.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 87.1, |
| "C02": 74.1, |
| "C03": 72.7, |
| "C04": 20.0, |
| "C05": 40.0, |
| "C06": 60.0, |
| "C07": 40.0, |
| "C08": 28.0, |
| "C09": 65.2, |
| "C10": 83.3, |
| "C11": 33.3, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 27.3, |
| "S02": 63.6, |
| "S03": 18.2, |
| "S04": 33.3, |
| "S05": 38.5, |
| "S06": 40.0, |
| "S07": 50.0, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 41.7, |
| "S11": 66.7, |
| "S12": 38.5, |
| "S13": 21.1, |
| "S14": 20.0, |
| "L01": 33.3, |
| "L02": 63.0, |
| "L03": 48.6, |
| "L04": 42.9, |
| "L05": 23.1, |
| "L06": 16.7, |
| "L07": 40.0, |
| "F01": 69.6, |
| "F02": 100.0, |
| "F03": 75.0, |
| "F04": 42.9, |
| "F05": 87.5, |
| "F06": 71.4, |
| "F07": 0.0, |
| "F08": 75.0, |
| "F09": 80.0, |
| "F10": 45.5, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "mindbrush", |
| "name": "MindBrush", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 55, |
| "accuracy": { |
| "temporal": 35.1, |
| "causal": 33.3, |
| "spatial": 16.5, |
| "logical": 8.9, |
| "counterfactual": 32.0, |
| "hybrid": 0.0, |
| "single": 21.8, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.2, |
| "appearance_consistency": 56.4, |
| "visual_plausibility": 81.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 54.1, |
| "temporal_context_knowledge": 12.5, |
| "temporal_disciplinary_knowledge": 16.9, |
| "causal_common_sense_knowledge": 46.8, |
| "causal_context_knowledge": 7.9, |
| "causal_disciplinary_knowledge": 32.0, |
| "spatial_relation": 15.0, |
| "spatial_structure": 18.3, |
| "logical_explicit_rule_deduction": 8.9, |
| "logical_implicit_pattern_induction": 8.8, |
| "counterfactual_counterfactual_imagination": 30.0, |
| "counterfactual_anomaly_correction_and_generation": 36.7 |
| }, |
| "task_types": { |
| "T01": 37.5, |
| "T02": 88.9, |
| "T03": 69.2, |
| "T04": 55.0, |
| "T05": 50.0, |
| "T06": 42.9, |
| "T07": 50.0, |
| "T08": 9.1, |
| "T09": 16.7, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 11.1, |
| "T15": 41.7, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 54.8, |
| "C02": 48.1, |
| "C03": 33.3, |
| "C04": 10.0, |
| "C05": 12.5, |
| "C06": 0.0, |
| "C07": 10.0, |
| "C08": 20.8, |
| "C09": 57.9, |
| "C10": 41.7, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 36.4, |
| "S02": 18.2, |
| "S03": 18.2, |
| "S04": 33.3, |
| "S05": 15.4, |
| "S06": 6.7, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 25.0, |
| "S11": 20.0, |
| "S12": 19.2, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 4.2, |
| "L02": 18.5, |
| "L03": 10.8, |
| "L04": 2.9, |
| "L05": 7.7, |
| "L06": 11.1, |
| "L07": null, |
| "F01": 17.4, |
| "F02": 22.2, |
| "F03": 62.5, |
| "F04": 42.9, |
| "F05": 25.0, |
| "F06": 42.9, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 60.0, |
| "F10": 27.3, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "interleavethinker", |
| "name": "InterleaveThinker", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 56, |
| "accuracy": { |
| "temporal": 38.7, |
| "causal": 30.7, |
| "spatial": 15.9, |
| "logical": 1.7, |
| "counterfactual": 26.0, |
| "hybrid": 8.0, |
| "single": 20.6, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 40.0, |
| "appearance_consistency": 66.4, |
| "visual_plausibility": 87.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 55.3, |
| "temporal_context_knowledge": 25.0, |
| "temporal_disciplinary_knowledge": 20.3, |
| "causal_common_sense_knowledge": 35.4, |
| "causal_context_knowledge": 39.5, |
| "causal_disciplinary_knowledge": 21.3, |
| "spatial_relation": 17.0, |
| "spatial_structure": 14.6, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 22.9, |
| "counterfactual_anomaly_correction_and_generation": 33.3 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 55.6, |
| "T03": 61.5, |
| "T04": 45.0, |
| "T05": 50.0, |
| "T06": 71.4, |
| "T07": 50.0, |
| "T08": 36.4, |
| "T09": 16.7, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 25.0, |
| "T13": 50.0, |
| "T14": 11.1, |
| "T15": 25.0, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 38.7, |
| "C02": 33.3, |
| "C03": 33.3, |
| "C04": 50.0, |
| "C05": 37.5, |
| "C06": 40.0, |
| "C07": 30.0, |
| "C08": 16.7, |
| "C09": 26.3, |
| "C10": 25.0, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 18.2, |
| "S02": 9.1, |
| "S03": 0.0, |
| "S04": 33.3, |
| "S05": 0.0, |
| "S06": 13.3, |
| "S07": 22.2, |
| "S08": 44.4, |
| "S09": null, |
| "S10": 33.3, |
| "S11": 20.0, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 34.8, |
| "F02": 33.3, |
| "F03": 62.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 27.3, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "intentedit", |
| "name": "IntentEdit", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 57, |
| "accuracy": { |
| "temporal": 23.2, |
| "causal": 24.0, |
| "spatial": 11.5, |
| "logical": 1.1, |
| "counterfactual": 14.0, |
| "hybrid": 0.0, |
| "single": 13.2, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 41.0, |
| "appearance_consistency": 58.4, |
| "visual_plausibility": 78.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 34.1, |
| "temporal_context_knowledge": 20.8, |
| "temporal_disciplinary_knowledge": 8.5, |
| "causal_common_sense_knowledge": 29.1, |
| "causal_context_knowledge": 10.5, |
| "causal_disciplinary_knowledge": 25.3, |
| "spatial_relation": 7.0, |
| "spatial_structure": 17.1, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 12.9, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 33.3, |
| "T02": 66.7, |
| "T03": 23.1, |
| "T04": 45.0, |
| "T05": 25.0, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 18.2, |
| "T09": 25.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 25.9, |
| "C03": 19.0, |
| "C04": 0.0, |
| "C05": 12.5, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 20.8, |
| "C09": 47.4, |
| "C10": 33.3, |
| "C11": 33.3, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 18.2, |
| "S04": 8.3, |
| "S05": 0.0, |
| "S06": 6.7, |
| "S07": 11.1, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 29.2, |
| "S11": 20.0, |
| "S12": 7.7, |
| "S13": 11.8, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 3.7, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 17.4, |
| "F02": 11.1, |
| "F03": 25.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "imagent", |
| "name": "ImAgent", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 58, |
| "accuracy": { |
| "temporal": 5.4, |
| "causal": 4.7, |
| "spatial": 4.4, |
| "logical": 0.6, |
| "counterfactual": 5.0, |
| "hybrid": 0.0, |
| "single": 3.5, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 24.6, |
| "appearance_consistency": 29.2, |
| "visual_plausibility": 65.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 7.1, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 3.4, |
| "causal_common_sense_knowledge": 8.9, |
| "causal_context_knowledge": 5.3, |
| "causal_disciplinary_knowledge": 0.0, |
| "spatial_relation": 2.0, |
| "spatial_structure": 7.3, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 44.4, |
| "T03": 0.0, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 9.7, |
| "C02": 7.4, |
| "C03": 9.5, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 10.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 20.8, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 5.6, |
| "L07": null, |
| "F01": 17.4, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| } |
| ] |
| }, |
| "zh": { |
| "language": "Chinese", |
| "language_code": "zh", |
| "model_count": 58, |
| "groups": [ |
| { |
| "id": "closed", |
| "label": "Closed-source Models", |
| "count": 19 |
| }, |
| { |
| "id": "open", |
| "label": "Open-source Models", |
| "count": 34 |
| }, |
| { |
| "id": "agentic", |
| "label": "Agentic Methods", |
| "count": 5 |
| } |
| ], |
| "models": [ |
| { |
| "id": "gpt-image-2-5-sunburst", |
| "name": "GPT-Image-2.5 Sunburst", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 1, |
| "accuracy": { |
| "temporal": 62.5, |
| "causal": 70.5, |
| "spatial": 63.0, |
| "logical": 29.0, |
| "counterfactual": 69.0, |
| "hybrid": 36.0, |
| "single": 56.0, |
| "multi": 50.0, |
| "total": 55.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 67.6, |
| "appearance_consistency": 96.7, |
| "visual_plausibility": 97.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 69.4, |
| "temporal_context_knowledge": 65.4, |
| "temporal_disciplinary_knowledge": 50.8, |
| "causal_common_sense_knowledge": 85.0, |
| "causal_context_knowledge": 62.5, |
| "causal_disciplinary_knowledge": 60.0, |
| "spatial_relation": 62.3, |
| "spatial_structure": 63.8, |
| "logical_explicit_rule_deduction": 32.5, |
| "logical_implicit_pattern_induction": 23.4, |
| "counterfactual_counterfactual_imagination": 64.3, |
| "counterfactual_anomaly_correction_and_generation": 80.0 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 77.8, |
| "T03": 69.2, |
| "T04": 75.0, |
| "T05": 87.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 46.7, |
| "T09": 57.1, |
| "T10": 86.7, |
| "T11": 75.0, |
| "T12": 50.0, |
| "T13": 37.5, |
| "T14": 66.7, |
| "T15": 50.0, |
| "T16": 50.0, |
| "T17": 20.0, |
| "T18": 75.0, |
| "T19": 66.7, |
| "C01": 77.4, |
| "C02": 92.6, |
| "C03": 86.4, |
| "C04": 60.0, |
| "C05": 60.0, |
| "C06": 70.0, |
| "C07": 60.0, |
| "C08": 36.0, |
| "C09": 73.9, |
| "C10": 91.7, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 100.0, |
| "C14": 30.0, |
| "S01": 63.6, |
| "S02": 81.8, |
| "S03": 54.5, |
| "S04": 66.7, |
| "S05": 61.5, |
| "S06": 80.0, |
| "S07": 55.6, |
| "S08": 55.6, |
| "S09": 16.7, |
| "S10": 79.2, |
| "S11": 66.7, |
| "S12": 65.4, |
| "S13": 47.4, |
| "S14": 50.0, |
| "L01": 20.8, |
| "L02": 25.9, |
| "L03": 43.2, |
| "L04": 34.3, |
| "L05": 15.4, |
| "L06": 55.6, |
| "L07": 10.0, |
| "F01": 73.9, |
| "F02": 66.7, |
| "F03": 75.0, |
| "F04": 28.6, |
| "F05": 75.0, |
| "F06": 71.4, |
| "F07": 25.0, |
| "F08": 50.0, |
| "F09": 100.0, |
| "F10": 81.8, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "nano-banana-pro", |
| "name": "Nano Banana Pro", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 2, |
| "accuracy": { |
| "temporal": 62.5, |
| "causal": 67.0, |
| "spatial": 50.5, |
| "logical": 38.5, |
| "counterfactual": 50.0, |
| "hybrid": 27.0, |
| "single": 52.4, |
| "multi": 39.7, |
| "total": 51.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 70.6, |
| "appearance_consistency": 88.6, |
| "visual_plausibility": 96.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 68.2, |
| "temporal_context_knowledge": 63.5, |
| "temporal_disciplinary_knowledge": 54.0, |
| "causal_common_sense_knowledge": 77.5, |
| "causal_context_knowledge": 62.5, |
| "causal_disciplinary_knowledge": 58.8, |
| "spatial_relation": 54.7, |
| "spatial_structure": 45.7, |
| "logical_explicit_rule_deduction": 42.3, |
| "logical_implicit_pattern_induction": 32.5, |
| "counterfactual_counterfactual_imagination": 54.3, |
| "counterfactual_anomaly_correction_and_generation": 40.0 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 100.0, |
| "T03": 76.9, |
| "T04": 70.0, |
| "T05": 62.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 80.0, |
| "T09": 71.4, |
| "T10": 53.3, |
| "T11": 37.5, |
| "T12": 50.0, |
| "T13": 62.5, |
| "T14": 66.7, |
| "T15": 50.0, |
| "T16": 44.4, |
| "T17": 60.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 80.6, |
| "C02": 74.1, |
| "C03": 77.3, |
| "C04": 50.0, |
| "C05": 90.0, |
| "C06": 80.0, |
| "C07": 30.0, |
| "C08": 52.0, |
| "C09": 82.6, |
| "C10": 66.7, |
| "C11": 100.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 30.0, |
| "S01": 63.6, |
| "S02": 54.5, |
| "S03": 45.5, |
| "S04": 58.3, |
| "S05": 76.9, |
| "S06": 80.0, |
| "S07": 38.9, |
| "S08": 33.3, |
| "S09": 16.7, |
| "S10": 75.0, |
| "S11": 73.3, |
| "S12": 30.8, |
| "S13": 31.6, |
| "S14": 0.0, |
| "L01": 41.7, |
| "L02": 63.0, |
| "L03": 45.9, |
| "L04": 22.9, |
| "L05": 30.8, |
| "L06": 33.3, |
| "L07": 35.0, |
| "F01": 60.9, |
| "F02": 88.9, |
| "F03": 62.5, |
| "F04": 42.9, |
| "F05": 50.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 60.0, |
| "F10": 18.2, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "nano-banana-2", |
| "name": "Nano Banana 2", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 3, |
| "accuracy": { |
| "temporal": 62.0, |
| "causal": 69.0, |
| "spatial": 50.0, |
| "logical": 31.5, |
| "counterfactual": 57.0, |
| "hybrid": 28.0, |
| "single": 51.7, |
| "multi": 42.3, |
| "total": 51.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 69.7, |
| "appearance_consistency": 88.9, |
| "visual_plausibility": 96.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 74.1, |
| "temporal_context_knowledge": 51.9, |
| "temporal_disciplinary_knowledge": 54.0, |
| "causal_common_sense_knowledge": 83.8, |
| "causal_context_knowledge": 57.5, |
| "causal_disciplinary_knowledge": 60.0, |
| "spatial_relation": 47.2, |
| "spatial_structure": 53.2, |
| "logical_explicit_rule_deduction": 35.0, |
| "logical_implicit_pattern_induction": 26.0, |
| "counterfactual_counterfactual_imagination": 51.4, |
| "counterfactual_anomaly_correction_and_generation": 70.0 |
| }, |
| "task_types": { |
| "T01": 70.8, |
| "T02": 100.0, |
| "T03": 69.2, |
| "T04": 75.0, |
| "T05": 75.0, |
| "T06": 71.4, |
| "T07": 50.0, |
| "T08": 53.3, |
| "T09": 42.9, |
| "T10": 60.0, |
| "T11": 50.0, |
| "T12": 50.0, |
| "T13": 62.5, |
| "T14": 44.4, |
| "T15": 50.0, |
| "T16": 50.0, |
| "T17": 20.0, |
| "T18": 100.0, |
| "T19": 100.0, |
| "C01": 87.1, |
| "C02": 81.5, |
| "C03": 81.8, |
| "C04": 40.0, |
| "C05": 70.0, |
| "C06": 50.0, |
| "C07": 70.0, |
| "C08": 56.0, |
| "C09": 65.2, |
| "C10": 66.7, |
| "C11": 100.0, |
| "C12": 50.0, |
| "C13": 66.7, |
| "C14": 40.0, |
| "S01": 72.7, |
| "S02": 45.5, |
| "S03": 27.3, |
| "S04": 58.3, |
| "S05": 46.2, |
| "S06": 60.0, |
| "S07": 55.6, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 66.7, |
| "S11": 73.3, |
| "S12": 50.0, |
| "S13": 31.6, |
| "S14": 40.0, |
| "L01": 20.8, |
| "L02": 55.6, |
| "L03": 37.8, |
| "L04": 25.7, |
| "L05": 23.1, |
| "L06": 38.9, |
| "L07": 20.0, |
| "F01": 43.5, |
| "F02": 66.7, |
| "F03": 62.5, |
| "F04": 42.9, |
| "F05": 50.0, |
| "F06": 57.1, |
| "F07": 25.0, |
| "F08": 75.0, |
| "F09": 90.0, |
| "F10": 63.6, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "luma-uni-1", |
| "name": "Luma Uni-1", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 4, |
| "accuracy": { |
| "temporal": 65.5, |
| "causal": 67.0, |
| "spatial": 53.5, |
| "logical": 17.0, |
| "counterfactual": 56.0, |
| "hybrid": 24.0, |
| "single": 49.1, |
| "multi": 42.3, |
| "total": 48.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 63.2, |
| "appearance_consistency": 89.5, |
| "visual_plausibility": 94.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 81.2, |
| "temporal_context_knowledge": 48.1, |
| "temporal_disciplinary_knowledge": 58.7, |
| "causal_common_sense_knowledge": 75.0, |
| "causal_context_knowledge": 60.0, |
| "causal_disciplinary_knowledge": 62.5, |
| "spatial_relation": 52.8, |
| "spatial_structure": 54.3, |
| "logical_explicit_rule_deduction": 21.1, |
| "logical_implicit_pattern_induction": 10.4, |
| "counterfactual_counterfactual_imagination": 58.6, |
| "counterfactual_anomaly_correction_and_generation": 50.0 |
| }, |
| "task_types": { |
| "T01": 70.8, |
| "T02": 100.0, |
| "T03": 76.9, |
| "T04": 90.0, |
| "T05": 87.5, |
| "T06": 71.4, |
| "T07": 75.0, |
| "T08": 53.3, |
| "T09": 35.7, |
| "T10": 46.7, |
| "T11": 62.5, |
| "T12": 100.0, |
| "T13": 37.5, |
| "T14": 66.7, |
| "T15": 83.3, |
| "T16": 38.9, |
| "T17": 60.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 74.2, |
| "C02": 77.8, |
| "C03": 72.7, |
| "C04": 50.0, |
| "C05": 70.0, |
| "C06": 40.0, |
| "C07": 80.0, |
| "C08": 40.0, |
| "C09": 91.3, |
| "C10": 100.0, |
| "C11": 66.7, |
| "C12": 25.0, |
| "C13": 66.7, |
| "C14": 20.0, |
| "S01": 63.6, |
| "S02": 18.2, |
| "S03": 54.5, |
| "S04": 66.7, |
| "S05": 61.5, |
| "S06": 66.7, |
| "S07": 50.0, |
| "S08": 33.3, |
| "S09": 50.0, |
| "S10": 66.7, |
| "S11": 80.0, |
| "S12": 34.6, |
| "S13": 47.4, |
| "S14": 50.0, |
| "L01": 4.2, |
| "L02": 37.0, |
| "L03": 18.9, |
| "L04": 22.9, |
| "L05": 7.7, |
| "L06": 16.7, |
| "L07": 10.0, |
| "F01": 65.2, |
| "F02": 77.8, |
| "F03": 50.0, |
| "F04": 57.1, |
| "F05": 50.0, |
| "F06": 57.1, |
| "F07": 25.0, |
| "F08": 50.0, |
| "F09": 50.0, |
| "F10": 54.5, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "gpt-image-2", |
| "name": "GPT-Image-2", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 5, |
| "accuracy": { |
| "temporal": 57.0, |
| "causal": 62.0, |
| "spatial": 54.5, |
| "logical": 20.5, |
| "counterfactual": 61.0, |
| "hybrid": 20.0, |
| "single": 46.9, |
| "multi": 47.4, |
| "total": 46.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 61.1, |
| "appearance_consistency": 91.1, |
| "visual_plausibility": 97.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 61.2, |
| "temporal_context_knowledge": 55.8, |
| "temporal_disciplinary_knowledge": 52.4, |
| "causal_common_sense_knowledge": 76.3, |
| "causal_context_knowledge": 57.5, |
| "causal_disciplinary_knowledge": 50.0, |
| "spatial_relation": 56.6, |
| "spatial_structure": 52.1, |
| "logical_explicit_rule_deduction": 22.8, |
| "logical_implicit_pattern_induction": 16.9, |
| "counterfactual_counterfactual_imagination": 52.9, |
| "counterfactual_anomaly_correction_and_generation": 80.0 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 77.8, |
| "T03": 69.2, |
| "T04": 60.0, |
| "T05": 87.5, |
| "T06": 28.6, |
| "T07": 50.0, |
| "T08": 46.7, |
| "T09": 42.9, |
| "T10": 60.0, |
| "T11": 87.5, |
| "T12": 0.0, |
| "T13": 62.5, |
| "T14": 77.8, |
| "T15": 50.0, |
| "T16": 61.1, |
| "T17": 40.0, |
| "T18": 25.0, |
| "T19": 33.3, |
| "C01": 67.7, |
| "C02": 81.5, |
| "C03": 81.8, |
| "C04": 50.0, |
| "C05": 50.0, |
| "C06": 60.0, |
| "C07": 70.0, |
| "C08": 36.0, |
| "C09": 65.2, |
| "C10": 91.7, |
| "C11": 66.7, |
| "C12": 25.0, |
| "C13": 33.3, |
| "C14": 10.0, |
| "S01": 72.7, |
| "S02": 63.6, |
| "S03": 45.5, |
| "S04": 66.7, |
| "S05": 61.5, |
| "S06": 46.7, |
| "S07": 55.6, |
| "S08": 55.6, |
| "S09": 33.3, |
| "S10": 62.5, |
| "S11": 66.7, |
| "S12": 42.3, |
| "S13": 57.9, |
| "S14": 20.0, |
| "L01": 12.5, |
| "L02": 25.9, |
| "L03": 32.4, |
| "L04": 17.1, |
| "L05": 15.4, |
| "L06": 5.6, |
| "L07": 30.0, |
| "F01": 65.2, |
| "F02": 55.6, |
| "F03": 87.5, |
| "F04": 14.3, |
| "F05": 50.0, |
| "F06": 42.9, |
| "F07": 25.0, |
| "F08": 25.0, |
| "F09": 90.0, |
| "F10": 81.8, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "qwen-image-3-0", |
| "name": "Qwen-Image-3.0", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 6, |
| "accuracy": { |
| "temporal": 58.0, |
| "causal": 50.0, |
| "spatial": 43.0, |
| "logical": 39.0, |
| "counterfactual": 49.0, |
| "hybrid": 34.0, |
| "single": 46.1, |
| "multi": 48.7, |
| "total": 46.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 67.8, |
| "appearance_consistency": 85.6, |
| "visual_plausibility": 95.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 63.5, |
| "temporal_context_knowledge": 67.3, |
| "temporal_disciplinary_knowledge": 42.9, |
| "causal_common_sense_knowledge": 52.5, |
| "causal_context_knowledge": 57.5, |
| "causal_disciplinary_knowledge": 43.8, |
| "spatial_relation": 45.3, |
| "spatial_structure": 40.4, |
| "logical_explicit_rule_deduction": 44.7, |
| "logical_implicit_pattern_induction": 29.9, |
| "counterfactual_counterfactual_imagination": 42.9, |
| "counterfactual_anomaly_correction_and_generation": 63.3 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 88.9, |
| "T03": 69.2, |
| "T04": 60.0, |
| "T05": 75.0, |
| "T06": 71.4, |
| "T07": 0.0, |
| "T08": 60.0, |
| "T09": 71.4, |
| "T10": 73.3, |
| "T11": 62.5, |
| "T12": 75.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 50.0, |
| "T16": 61.1, |
| "T17": 20.0, |
| "T18": 75.0, |
| "T19": 33.3, |
| "C01": 51.6, |
| "C02": 55.6, |
| "C03": 50.0, |
| "C04": 40.0, |
| "C05": 60.0, |
| "C06": 60.0, |
| "C07": 70.0, |
| "C08": 40.0, |
| "C09": 47.8, |
| "C10": 66.7, |
| "C11": 66.7, |
| "C12": 0.0, |
| "C13": 66.7, |
| "C14": 20.0, |
| "S01": 63.6, |
| "S02": 63.6, |
| "S03": 9.1, |
| "S04": 25.0, |
| "S05": 61.5, |
| "S06": 60.0, |
| "S07": 50.0, |
| "S08": 33.3, |
| "S09": 16.7, |
| "S10": 29.2, |
| "S11": 80.0, |
| "S12": 46.2, |
| "S13": 26.3, |
| "S14": 20.0, |
| "L01": 25.0, |
| "L02": 63.0, |
| "L03": 54.1, |
| "L04": 34.3, |
| "L05": 25.6, |
| "L06": 27.8, |
| "L07": 40.0, |
| "F01": 56.5, |
| "F02": 44.4, |
| "F03": 25.0, |
| "F04": 14.3, |
| "F05": 50.0, |
| "F06": 28.6, |
| "F07": 25.0, |
| "F08": 75.0, |
| "F09": 70.0, |
| "F10": 72.7, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "gpt-image-2-5-flare", |
| "name": "GPT-Image-2.5 Flare", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 7, |
| "accuracy": { |
| "temporal": 52.0, |
| "causal": 66.0, |
| "spatial": 54.0, |
| "logical": 14.0, |
| "counterfactual": 61.0, |
| "hybrid": 19.0, |
| "single": 46.3, |
| "multi": 32.1, |
| "total": 45.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 58.9, |
| "appearance_consistency": 93.4, |
| "visual_plausibility": 97.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 60.0, |
| "temporal_context_knowledge": 51.9, |
| "temporal_disciplinary_knowledge": 41.3, |
| "causal_common_sense_knowledge": 80.0, |
| "causal_context_knowledge": 60.0, |
| "causal_disciplinary_knowledge": 55.0, |
| "spatial_relation": 51.9, |
| "spatial_structure": 56.4, |
| "logical_explicit_rule_deduction": 19.5, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 55.7, |
| "counterfactual_anomaly_correction_and_generation": 73.3 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 66.7, |
| "T03": 69.2, |
| "T04": 40.0, |
| "T05": 87.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 46.7, |
| "T09": 28.6, |
| "T10": 66.7, |
| "T11": 75.0, |
| "T12": 0.0, |
| "T13": 37.5, |
| "T14": 66.7, |
| "T15": 50.0, |
| "T16": 33.3, |
| "T17": 40.0, |
| "T18": 50.0, |
| "T19": 33.3, |
| "C01": 77.4, |
| "C02": 88.9, |
| "C03": 72.7, |
| "C04": 60.0, |
| "C05": 60.0, |
| "C06": 40.0, |
| "C07": 80.0, |
| "C08": 40.0, |
| "C09": 65.2, |
| "C10": 100.0, |
| "C11": 100.0, |
| "C12": 25.0, |
| "C13": 33.3, |
| "C14": 20.0, |
| "S01": 54.5, |
| "S02": 54.5, |
| "S03": 27.3, |
| "S04": 75.0, |
| "S05": 53.8, |
| "S06": 46.7, |
| "S07": 61.1, |
| "S08": 55.6, |
| "S09": 16.7, |
| "S10": 75.0, |
| "S11": 60.0, |
| "S12": 53.8, |
| "S13": 63.2, |
| "S14": 0.0, |
| "L01": 12.5, |
| "L02": 11.1, |
| "L03": 35.1, |
| "L04": 14.3, |
| "L05": 7.7, |
| "L06": 0.0, |
| "L07": 5.0, |
| "F01": 82.6, |
| "F02": 33.3, |
| "F03": 62.5, |
| "F04": 28.6, |
| "F05": 50.0, |
| "F06": 42.9, |
| "F07": 25.0, |
| "F08": 50.0, |
| "F09": 80.0, |
| "F10": 72.7, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "flux-2-max", |
| "name": "FLUX.2 Max", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 8, |
| "accuracy": { |
| "temporal": 59.5, |
| "causal": 59.0, |
| "spatial": 42.0, |
| "logical": 14.0, |
| "counterfactual": 72.0, |
| "hybrid": 18.0, |
| "single": 44.4, |
| "multi": 38.5, |
| "total": 43.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 61.1, |
| "appearance_consistency": 83.0, |
| "visual_plausibility": 95.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 65.9, |
| "temporal_context_knowledge": 63.5, |
| "temporal_disciplinary_knowledge": 47.6, |
| "causal_common_sense_knowledge": 73.8, |
| "causal_context_knowledge": 37.5, |
| "causal_disciplinary_knowledge": 55.0, |
| "spatial_relation": 34.9, |
| "spatial_structure": 50.0, |
| "logical_explicit_rule_deduction": 21.1, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 74.3, |
| "counterfactual_anomaly_correction_and_generation": 66.7 |
| }, |
| "task_types": { |
| "T01": 62.5, |
| "T02": 100.0, |
| "T03": 53.8, |
| "T04": 60.0, |
| "T05": 62.5, |
| "T06": 71.4, |
| "T07": 75.0, |
| "T08": 73.3, |
| "T09": 57.1, |
| "T10": 53.3, |
| "T11": 75.0, |
| "T12": 50.0, |
| "T13": 37.5, |
| "T14": 33.3, |
| "T15": 58.3, |
| "T16": 44.4, |
| "T17": 60.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 77.4, |
| "C02": 74.1, |
| "C03": 68.2, |
| "C04": 30.0, |
| "C05": 50.0, |
| "C06": 10.0, |
| "C07": 60.0, |
| "C08": 44.0, |
| "C09": 56.5, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 75.0, |
| "C13": 33.3, |
| "C14": 40.0, |
| "S01": 27.3, |
| "S02": 36.4, |
| "S03": 27.3, |
| "S04": 50.0, |
| "S05": 30.8, |
| "S06": 46.7, |
| "S07": 27.8, |
| "S08": 55.6, |
| "S09": 0.0, |
| "S10": 70.8, |
| "S11": 46.7, |
| "S12": 42.3, |
| "S13": 42.1, |
| "S14": 40.0, |
| "L01": 4.2, |
| "L02": 40.7, |
| "L03": 24.3, |
| "L04": 14.3, |
| "L05": 2.6, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 78.3, |
| "F02": 100.0, |
| "F03": 75.0, |
| "F04": 85.7, |
| "F05": 37.5, |
| "F06": 100.0, |
| "F07": 0.0, |
| "F08": 75.0, |
| "F09": 60.0, |
| "F10": 81.8, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "nano-banana-2-lite", |
| "name": "Nano Banana 2 Lite", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 9, |
| "accuracy": { |
| "temporal": 58.5, |
| "causal": 60.5, |
| "spatial": 41.5, |
| "logical": 12.0, |
| "counterfactual": 59.0, |
| "hybrid": 18.0, |
| "single": 42.5, |
| "multi": 38.5, |
| "total": 42.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 58.7, |
| "appearance_consistency": 88.3, |
| "visual_plausibility": 97.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 65.9, |
| "temporal_context_knowledge": 65.4, |
| "temporal_disciplinary_knowledge": 42.9, |
| "causal_common_sense_knowledge": 76.3, |
| "causal_context_knowledge": 35.0, |
| "causal_disciplinary_knowledge": 57.5, |
| "spatial_relation": 38.7, |
| "spatial_structure": 44.7, |
| "logical_explicit_rule_deduction": 13.0, |
| "logical_implicit_pattern_induction": 10.4, |
| "counterfactual_counterfactual_imagination": 60.0, |
| "counterfactual_anomaly_correction_and_generation": 56.7 |
| }, |
| "task_types": { |
| "T01": 75.0, |
| "T02": 77.8, |
| "T03": 61.5, |
| "T04": 60.0, |
| "T05": 87.5, |
| "T06": 28.6, |
| "T07": 50.0, |
| "T08": 60.0, |
| "T09": 57.1, |
| "T10": 80.0, |
| "T11": 62.5, |
| "T12": 50.0, |
| "T13": 12.5, |
| "T14": 33.3, |
| "T15": 66.7, |
| "T16": 38.9, |
| "T17": 40.0, |
| "T18": 75.0, |
| "T19": 33.3, |
| "C01": 71.0, |
| "C02": 77.8, |
| "C03": 81.8, |
| "C04": 30.0, |
| "C05": 30.0, |
| "C06": 40.0, |
| "C07": 40.0, |
| "C08": 52.0, |
| "C09": 78.3, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 54.5, |
| "S02": 54.5, |
| "S03": 27.3, |
| "S04": 25.0, |
| "S05": 46.2, |
| "S06": 53.3, |
| "S07": 27.8, |
| "S08": 33.3, |
| "S09": 16.7, |
| "S10": 66.7, |
| "S11": 60.0, |
| "S12": 42.3, |
| "S13": 26.3, |
| "S14": 10.0, |
| "L01": 12.5, |
| "L02": 18.5, |
| "L03": 10.8, |
| "L04": 11.4, |
| "L05": 7.7, |
| "L06": 22.2, |
| "L07": 5.0, |
| "F01": 65.2, |
| "F02": 66.7, |
| "F03": 75.0, |
| "F04": 71.4, |
| "F05": 37.5, |
| "F06": 57.1, |
| "F07": 0.0, |
| "F08": 75.0, |
| "F09": 80.0, |
| "F10": 36.4, |
| "F11": 55.6 |
| } |
| }, |
| { |
| "id": "gpt-image-1-5", |
| "name": "GPT-Image-1.5", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 10, |
| "accuracy": { |
| "temporal": 55.0, |
| "causal": 57.0, |
| "spatial": 35.5, |
| "logical": 4.5, |
| "counterfactual": 57.0, |
| "hybrid": 10.0, |
| "single": 37.9, |
| "multi": 28.2, |
| "total": 37.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 55.7, |
| "appearance_consistency": 80.5, |
| "visual_plausibility": 96.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 68.2, |
| "temporal_context_knowledge": 44.2, |
| "temporal_disciplinary_knowledge": 46.0, |
| "causal_common_sense_knowledge": 75.0, |
| "causal_context_knowledge": 40.0, |
| "causal_disciplinary_knowledge": 47.5, |
| "spatial_relation": 32.1, |
| "spatial_structure": 39.4, |
| "logical_explicit_rule_deduction": 4.9, |
| "logical_implicit_pattern_induction": 3.9, |
| "counterfactual_counterfactual_imagination": 52.9, |
| "counterfactual_anomaly_correction_and_generation": 66.7 |
| }, |
| "task_types": { |
| "T01": 58.3, |
| "T02": 100.0, |
| "T03": 61.5, |
| "T04": 75.0, |
| "T05": 75.0, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 40.0, |
| "T09": 42.9, |
| "T10": 53.3, |
| "T11": 37.5, |
| "T12": 50.0, |
| "T13": 25.0, |
| "T14": 66.7, |
| "T15": 50.0, |
| "T16": 50.0, |
| "T17": 40.0, |
| "T18": 25.0, |
| "T19": 33.3, |
| "C01": 80.6, |
| "C02": 77.8, |
| "C03": 63.6, |
| "C04": 40.0, |
| "C05": 40.0, |
| "C06": 30.0, |
| "C07": 50.0, |
| "C08": 44.0, |
| "C09": 60.9, |
| "C10": 66.7, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 58.3, |
| "S05": 46.2, |
| "S06": 26.7, |
| "S07": 22.2, |
| "S08": 66.7, |
| "S09": 0.0, |
| "S10": 58.3, |
| "S11": 20.0, |
| "S12": 38.5, |
| "S13": 42.1, |
| "S14": 20.0, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 10.8, |
| "L04": 2.9, |
| "L05": 7.7, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 56.5, |
| "F02": 55.6, |
| "F03": 100.0, |
| "F04": 42.9, |
| "F05": 50.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 80.0, |
| "F10": 54.5, |
| "F11": 66.7 |
| } |
| }, |
| { |
| "id": "nano-banana", |
| "name": "Nano Banana", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 11, |
| "accuracy": { |
| "temporal": 49.5, |
| "causal": 53.0, |
| "spatial": 40.0, |
| "logical": 12.0, |
| "counterfactual": 52.0, |
| "hybrid": 5.0, |
| "single": 36.6, |
| "multi": 37.2, |
| "total": 36.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 53.8, |
| "appearance_consistency": 83.8, |
| "visual_plausibility": 96.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 49.4, |
| "temporal_context_knowledge": 55.8, |
| "temporal_disciplinary_knowledge": 44.4, |
| "causal_common_sense_knowledge": 70.0, |
| "causal_context_knowledge": 35.0, |
| "causal_disciplinary_knowledge": 45.0, |
| "spatial_relation": 32.1, |
| "spatial_structure": 48.9, |
| "logical_explicit_rule_deduction": 14.6, |
| "logical_implicit_pattern_induction": 7.8, |
| "counterfactual_counterfactual_imagination": 47.1, |
| "counterfactual_anomaly_correction_and_generation": 63.3 |
| }, |
| "task_types": { |
| "T01": 66.7, |
| "T02": 55.6, |
| "T03": 23.1, |
| "T04": 45.0, |
| "T05": 50.0, |
| "T06": 28.6, |
| "T07": 75.0, |
| "T08": 40.0, |
| "T09": 64.3, |
| "T10": 60.0, |
| "T11": 62.5, |
| "T12": 25.0, |
| "T13": 62.5, |
| "T14": 44.4, |
| "T15": 41.7, |
| "T16": 50.0, |
| "T17": 20.0, |
| "T18": 25.0, |
| "T19": 66.7, |
| "C01": 61.3, |
| "C02": 85.2, |
| "C03": 63.6, |
| "C04": 30.0, |
| "C05": 40.0, |
| "C06": 10.0, |
| "C07": 60.0, |
| "C08": 40.0, |
| "C09": 60.9, |
| "C10": 66.7, |
| "C11": 33.3, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 45.5, |
| "S02": 45.5, |
| "S03": 45.5, |
| "S04": 41.7, |
| "S05": 23.1, |
| "S06": 26.7, |
| "S07": 27.8, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 54.2, |
| "S11": 53.3, |
| "S12": 46.2, |
| "S13": 52.6, |
| "S14": 30.0, |
| "L01": 4.2, |
| "L02": 29.6, |
| "L03": 10.8, |
| "L04": 14.3, |
| "L05": 7.7, |
| "L06": 11.1, |
| "L07": 5.0, |
| "F01": 69.6, |
| "F02": 55.6, |
| "F03": 37.5, |
| "F04": 14.3, |
| "F05": 50.0, |
| "F06": 28.6, |
| "F07": 25.0, |
| "F08": 25.0, |
| "F09": 80.0, |
| "F10": 63.6, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "flux-2-pro", |
| "name": "FLUX.2 Pro", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 12, |
| "accuracy": { |
| "temporal": 51.0, |
| "causal": 44.5, |
| "spatial": 38.5, |
| "logical": 8.0, |
| "counterfactual": 51.0, |
| "hybrid": 11.0, |
| "single": 33.5, |
| "multi": 47.4, |
| "total": 34.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 56.1, |
| "appearance_consistency": 73.7, |
| "visual_plausibility": 95.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 50.6, |
| "temporal_context_knowledge": 57.7, |
| "temporal_disciplinary_knowledge": 46.0, |
| "causal_common_sense_knowledge": 61.3, |
| "causal_context_knowledge": 25.0, |
| "causal_disciplinary_knowledge": 37.5, |
| "spatial_relation": 31.1, |
| "spatial_structure": 46.8, |
| "logical_explicit_rule_deduction": 12.2, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 55.7, |
| "counterfactual_anomaly_correction_and_generation": 40.0 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 66.7, |
| "T03": 38.5, |
| "T04": 40.0, |
| "T05": 62.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 60.0, |
| "T09": 35.7, |
| "T10": 73.3, |
| "T11": 62.5, |
| "T12": 75.0, |
| "T13": 50.0, |
| "T14": 22.2, |
| "T15": 58.3, |
| "T16": 44.4, |
| "T17": 60.0, |
| "T18": 50.0, |
| "T19": 0.0, |
| "C01": 61.3, |
| "C02": 74.1, |
| "C03": 45.5, |
| "C04": 10.0, |
| "C05": 40.0, |
| "C06": 30.0, |
| "C07": 20.0, |
| "C08": 12.0, |
| "C09": 56.5, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 50.0, |
| "S05": 46.2, |
| "S06": 46.7, |
| "S07": 16.7, |
| "S08": 44.4, |
| "S09": 0.0, |
| "S10": 50.0, |
| "S11": 46.7, |
| "S12": 30.8, |
| "S13": 47.4, |
| "S14": 80.0, |
| "L01": 0.0, |
| "L02": 29.6, |
| "L03": 13.5, |
| "L04": 5.7, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 52.2, |
| "F02": 77.8, |
| "F03": 50.0, |
| "F04": 71.4, |
| "F05": 25.0, |
| "F06": 71.4, |
| "F07": 0.0, |
| "F08": 100.0, |
| "F09": 30.0, |
| "F10": 54.5, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "hunyuanimage-3-5", |
| "name": "HunyuanImage-3.5", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 13, |
| "accuracy": { |
| "temporal": 44.0, |
| "causal": 39.5, |
| "spatial": 45.0, |
| "logical": 14.0, |
| "counterfactual": 42.0, |
| "hybrid": 13.0, |
| "single": 33.3, |
| "multi": 42.3, |
| "total": 34.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 51.2, |
| "appearance_consistency": 93.3, |
| "visual_plausibility": 94.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 49.4, |
| "temporal_context_knowledge": 53.8, |
| "temporal_disciplinary_knowledge": 28.6, |
| "causal_common_sense_knowledge": 43.8, |
| "causal_context_knowledge": 32.5, |
| "causal_disciplinary_knowledge": 38.8, |
| "spatial_relation": 42.5, |
| "spatial_structure": 47.9, |
| "logical_explicit_rule_deduction": 14.6, |
| "logical_implicit_pattern_induction": 13.0, |
| "counterfactual_counterfactual_imagination": 40.0, |
| "counterfactual_anomaly_correction_and_generation": 46.7 |
| }, |
| "task_types": { |
| "T01": 45.8, |
| "T02": 77.8, |
| "T03": 53.8, |
| "T04": 45.0, |
| "T05": 50.0, |
| "T06": 57.1, |
| "T07": 0.0, |
| "T08": 40.0, |
| "T09": 57.1, |
| "T10": 73.3, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 33.3, |
| "T15": 58.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 45.2, |
| "C02": 44.4, |
| "C03": 40.9, |
| "C04": 20.0, |
| "C05": 30.0, |
| "C06": 40.0, |
| "C07": 40.0, |
| "C08": 24.0, |
| "C09": 52.2, |
| "C10": 66.7, |
| "C11": 33.3, |
| "C12": 50.0, |
| "C13": 33.3, |
| "C14": 10.0, |
| "S01": 63.6, |
| "S02": 36.4, |
| "S03": 45.5, |
| "S04": 50.0, |
| "S05": 53.8, |
| "S06": 60.0, |
| "S07": 33.3, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 62.5, |
| "S11": 40.0, |
| "S12": 30.8, |
| "S13": 36.8, |
| "S14": 90.0, |
| "L01": 4.2, |
| "L02": 25.9, |
| "L03": 16.2, |
| "L04": 11.4, |
| "L05": 10.3, |
| "L06": 33.3, |
| "L07": 0.0, |
| "F01": 52.2, |
| "F02": 77.8, |
| "F03": 25.0, |
| "F04": 14.3, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 25.0, |
| "F08": 75.0, |
| "F09": 60.0, |
| "F10": 36.4, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "wan2-7-image-pro", |
| "name": "Wan2.7-Image-Pro", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 14, |
| "accuracy": { |
| "temporal": 40.5, |
| "causal": 44.5, |
| "spatial": 37.5, |
| "logical": 9.5, |
| "counterfactual": 47.0, |
| "hybrid": 13.0, |
| "single": 32.4, |
| "multi": 32.1, |
| "total": 32.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 50.4, |
| "appearance_consistency": 85.3, |
| "visual_plausibility": 93.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 55.3, |
| "temporal_context_knowledge": 30.8, |
| "temporal_disciplinary_knowledge": 28.6, |
| "causal_common_sense_knowledge": 57.5, |
| "causal_context_knowledge": 42.5, |
| "causal_disciplinary_knowledge": 32.5, |
| "spatial_relation": 37.7, |
| "spatial_structure": 37.2, |
| "logical_explicit_rule_deduction": 11.4, |
| "logical_implicit_pattern_induction": 6.5, |
| "counterfactual_counterfactual_imagination": 44.3, |
| "counterfactual_anomaly_correction_and_generation": 53.3 |
| }, |
| "task_types": { |
| "T01": 45.8, |
| "T02": 88.9, |
| "T03": 46.2, |
| "T04": 55.0, |
| "T05": 37.5, |
| "T06": 85.7, |
| "T07": 50.0, |
| "T08": 26.7, |
| "T09": 21.4, |
| "T10": 33.3, |
| "T11": 50.0, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 44.4, |
| "T15": 33.3, |
| "T16": 38.9, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 58.1, |
| "C02": 66.7, |
| "C03": 45.5, |
| "C04": 40.0, |
| "C05": 50.0, |
| "C06": 30.0, |
| "C07": 50.0, |
| "C08": 16.0, |
| "C09": 47.8, |
| "C10": 66.7, |
| "C11": 33.3, |
| "C12": 50.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 45.5, |
| "S02": 45.5, |
| "S03": 18.2, |
| "S04": 58.3, |
| "S05": 38.5, |
| "S06": 33.3, |
| "S07": 50.0, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 33.3, |
| "S11": 60.0, |
| "S12": 30.8, |
| "S13": 21.1, |
| "S14": 60.0, |
| "L01": 0.0, |
| "L02": 22.2, |
| "L03": 16.2, |
| "L04": 5.7, |
| "L05": 2.6, |
| "L06": 22.2, |
| "L07": 0.0, |
| "F01": 52.2, |
| "F02": 44.4, |
| "F03": 75.0, |
| "F04": 28.6, |
| "F05": 37.5, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 60.0, |
| "F10": 63.6, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "qwen-image-2-0", |
| "name": "Qwen-Image-2.0", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 15, |
| "accuracy": { |
| "temporal": 51.5, |
| "causal": 37.0, |
| "spatial": 30.5, |
| "logical": 9.0, |
| "counterfactual": 37.0, |
| "hybrid": 1.0, |
| "single": 28.7, |
| "multi": 37.2, |
| "total": 29.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.5, |
| "appearance_consistency": 77.4, |
| "visual_plausibility": 90.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 61.2, |
| "temporal_context_knowledge": 57.7, |
| "temporal_disciplinary_knowledge": 33.3, |
| "causal_common_sense_knowledge": 43.8, |
| "causal_context_knowledge": 27.5, |
| "causal_disciplinary_knowledge": 35.0, |
| "spatial_relation": 23.6, |
| "spatial_structure": 38.3, |
| "logical_explicit_rule_deduction": 9.8, |
| "logical_implicit_pattern_induction": 7.8, |
| "counterfactual_counterfactual_imagination": 34.3, |
| "counterfactual_anomaly_correction_and_generation": 43.3 |
| }, |
| "task_types": { |
| "T01": 41.7, |
| "T02": 88.9, |
| "T03": 53.8, |
| "T04": 80.0, |
| "T05": 62.5, |
| "T06": 57.1, |
| "T07": 50.0, |
| "T08": 73.3, |
| "T09": 42.9, |
| "T10": 60.0, |
| "T11": 50.0, |
| "T12": 25.0, |
| "T13": 25.0, |
| "T14": 33.3, |
| "T15": 41.7, |
| "T16": 33.3, |
| "T17": 0.0, |
| "T18": 50.0, |
| "T19": 66.7, |
| "C01": 54.8, |
| "C02": 37.0, |
| "C03": 36.4, |
| "C04": 30.0, |
| "C05": 40.0, |
| "C06": 20.0, |
| "C07": 20.0, |
| "C08": 28.0, |
| "C09": 43.5, |
| "C10": 58.3, |
| "C11": 66.7, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 27.3, |
| "S02": 9.1, |
| "S03": 27.3, |
| "S04": 33.3, |
| "S05": 30.8, |
| "S06": 20.0, |
| "S07": 33.3, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 37.5, |
| "S11": 53.3, |
| "S12": 26.9, |
| "S13": 21.1, |
| "S14": 80.0, |
| "L01": 0.0, |
| "L02": 11.1, |
| "L03": 13.5, |
| "L04": 11.4, |
| "L05": 10.3, |
| "L06": 11.1, |
| "L07": 0.0, |
| "F01": 43.5, |
| "F02": 44.4, |
| "F03": 62.5, |
| "F04": 14.3, |
| "F05": 25.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 25.0, |
| "F09": 40.0, |
| "F10": 45.5, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "seedream-4-5", |
| "name": "Seedream 4.5", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 16, |
| "accuracy": { |
| "temporal": 44.0, |
| "causal": 45.0, |
| "spatial": 26.5, |
| "logical": 8.5, |
| "counterfactual": 35.0, |
| "hybrid": 10.0, |
| "single": 29.9, |
| "multi": 21.8, |
| "total": 29.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 50.6, |
| "appearance_consistency": 78.1, |
| "visual_plausibility": 94.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 54.1, |
| "temporal_context_knowledge": 40.4, |
| "temporal_disciplinary_knowledge": 33.3, |
| "causal_common_sense_knowledge": 56.3, |
| "causal_context_knowledge": 42.5, |
| "causal_disciplinary_knowledge": 35.0, |
| "spatial_relation": 23.6, |
| "spatial_structure": 29.8, |
| "logical_explicit_rule_deduction": 10.6, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 32.9, |
| "counterfactual_anomaly_correction_and_generation": 40.0 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 77.8, |
| "T03": 46.2, |
| "T04": 50.0, |
| "T05": 50.0, |
| "T06": 42.9, |
| "T07": 75.0, |
| "T08": 33.3, |
| "T09": 35.7, |
| "T10": 46.7, |
| "T11": 50.0, |
| "T12": 25.0, |
| "T13": 50.0, |
| "T14": 11.1, |
| "T15": 50.0, |
| "T16": 38.9, |
| "T17": 20.0, |
| "T18": 0.0, |
| "T19": 33.3, |
| "C01": 54.8, |
| "C02": 59.3, |
| "C03": 54.5, |
| "C04": 50.0, |
| "C05": 40.0, |
| "C06": 30.0, |
| "C07": 50.0, |
| "C08": 28.0, |
| "C09": 43.5, |
| "C10": 66.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 30.0, |
| "S01": 27.3, |
| "S02": 27.3, |
| "S03": 27.3, |
| "S04": 41.7, |
| "S05": 30.8, |
| "S06": 20.0, |
| "S07": 16.7, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 37.5, |
| "S11": 40.0, |
| "S12": 34.6, |
| "S13": 10.5, |
| "S14": 20.0, |
| "L01": 0.0, |
| "L02": 18.5, |
| "L03": 16.2, |
| "L04": 5.7, |
| "L05": 5.1, |
| "L06": 5.6, |
| "L07": 5.0, |
| "F01": 30.4, |
| "F02": 55.6, |
| "F03": 75.0, |
| "F04": 14.3, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 40.0, |
| "F10": 45.5, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "seedream-5-0", |
| "name": "Seedream 5.0", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 17, |
| "accuracy": { |
| "temporal": 40.5, |
| "causal": 39.5, |
| "spatial": 28.0, |
| "logical": 11.5, |
| "counterfactual": 30.0, |
| "hybrid": 7.0, |
| "single": 27.7, |
| "multi": 26.9, |
| "total": 27.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.1, |
| "appearance_consistency": 73.2, |
| "visual_plausibility": 94.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 51.8, |
| "temporal_context_knowledge": 40.4, |
| "temporal_disciplinary_knowledge": 25.4, |
| "causal_common_sense_knowledge": 46.3, |
| "causal_context_knowledge": 37.5, |
| "causal_disciplinary_knowledge": 33.8, |
| "spatial_relation": 20.8, |
| "spatial_structure": 36.2, |
| "logical_explicit_rule_deduction": 13.8, |
| "logical_implicit_pattern_induction": 7.8, |
| "counterfactual_counterfactual_imagination": 28.6, |
| "counterfactual_anomaly_correction_and_generation": 33.3 |
| }, |
| "task_types": { |
| "T01": 50.0, |
| "T02": 66.7, |
| "T03": 61.5, |
| "T04": 45.0, |
| "T05": 62.5, |
| "T06": 42.9, |
| "T07": 25.0, |
| "T08": 33.3, |
| "T09": 35.7, |
| "T10": 60.0, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 11.1, |
| "T15": 33.3, |
| "T16": 33.3, |
| "T17": 20.0, |
| "T18": 25.0, |
| "T19": 33.3, |
| "C01": 54.8, |
| "C02": 48.1, |
| "C03": 31.8, |
| "C04": 40.0, |
| "C05": 30.0, |
| "C06": 40.0, |
| "C07": 40.0, |
| "C08": 16.0, |
| "C09": 56.5, |
| "C10": 41.7, |
| "C11": 33.3, |
| "C12": 75.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 36.4, |
| "S02": 27.3, |
| "S03": 18.2, |
| "S04": 33.3, |
| "S05": 15.4, |
| "S06": 6.7, |
| "S07": 16.7, |
| "S08": 22.2, |
| "S09": 16.7, |
| "S10": 37.5, |
| "S11": 60.0, |
| "S12": 23.1, |
| "S13": 31.6, |
| "S14": 40.0, |
| "L01": 0.0, |
| "L02": 18.5, |
| "L03": 18.9, |
| "L04": 14.3, |
| "L05": 15.4, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 30.4, |
| "F02": 33.3, |
| "F03": 50.0, |
| "F04": 0.0, |
| "F05": 25.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 50.0, |
| "F10": 18.2, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "gpt-image-1", |
| "name": "GPT-Image-1", |
| "group": "closed", |
| "multi_image": true, |
| "source_order": 18, |
| "accuracy": { |
| "temporal": 43.5, |
| "causal": 40.0, |
| "spatial": 24.5, |
| "logical": 5.5, |
| "counterfactual": 37.0, |
| "hybrid": 8.0, |
| "single": 28.1, |
| "multi": 16.7, |
| "total": 27.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 50.1, |
| "appearance_consistency": 72.7, |
| "visual_plausibility": 94.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 58.8, |
| "temporal_context_knowledge": 28.8, |
| "temporal_disciplinary_knowledge": 34.9, |
| "causal_common_sense_knowledge": 60.0, |
| "causal_context_knowledge": 22.5, |
| "causal_disciplinary_knowledge": 28.8, |
| "spatial_relation": 14.2, |
| "spatial_structure": 36.2, |
| "logical_explicit_rule_deduction": 5.7, |
| "logical_implicit_pattern_induction": 5.2, |
| "counterfactual_counterfactual_imagination": 38.6, |
| "counterfactual_anomaly_correction_and_generation": 33.3 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 77.8, |
| "T03": 61.5, |
| "T04": 55.0, |
| "T05": 75.0, |
| "T06": 57.1, |
| "T07": 25.0, |
| "T08": 33.3, |
| "T09": 35.7, |
| "T10": 20.0, |
| "T11": 25.0, |
| "T12": 25.0, |
| "T13": 12.5, |
| "T14": 66.7, |
| "T15": 41.7, |
| "T16": 38.9, |
| "T17": 0.0, |
| "T18": 50.0, |
| "T19": 0.0, |
| "C01": 71.0, |
| "C02": 63.0, |
| "C03": 40.9, |
| "C04": 20.0, |
| "C05": 20.0, |
| "C06": 10.0, |
| "C07": 40.0, |
| "C08": 12.0, |
| "C09": 30.4, |
| "C10": 83.3, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 25.0, |
| "S05": 15.4, |
| "S06": 33.3, |
| "S07": 5.6, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 54.2, |
| "S11": 33.3, |
| "S12": 34.6, |
| "S13": 31.6, |
| "S14": 10.0, |
| "L01": 4.2, |
| "L02": 3.7, |
| "L03": 10.8, |
| "L04": 2.9, |
| "L05": 7.7, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 39.1, |
| "F02": 66.7, |
| "F03": 50.0, |
| "F04": 14.3, |
| "F05": 50.0, |
| "F06": 42.9, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 60.0, |
| "F10": 36.4, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "step-image-edit-2", |
| "name": "Step Image Edit 2", |
| "group": "closed", |
| "multi_image": false, |
| "source_order": 19, |
| "accuracy": { |
| "temporal": 14.9, |
| "causal": 19.3, |
| "spatial": 22.5, |
| "logical": 2.2, |
| "counterfactual": 12.0, |
| "hybrid": 0.0, |
| "single": 12.9, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 29.8, |
| "appearance_consistency": 67.9, |
| "visual_plausibility": 84.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 25.9, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 5.1, |
| "causal_common_sense_knowledge": 26.6, |
| "causal_context_knowledge": 18.4, |
| "causal_disciplinary_knowledge": 12.0, |
| "spatial_relation": 24.0, |
| "spatial_structure": 20.7, |
| "logical_explicit_rule_deduction": 2.4, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 10.0, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 22.2, |
| "T03": 46.2, |
| "T04": 25.0, |
| "T05": 50.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 18.5, |
| "C03": 28.6, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 20.0, |
| "C07": 50.0, |
| "C08": 8.3, |
| "C09": 10.5, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 18.2, |
| "S02": 36.4, |
| "S03": 36.4, |
| "S04": 25.0, |
| "S05": 23.1, |
| "S06": 13.3, |
| "S07": 22.2, |
| "S08": 22.2, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 20.0, |
| "S12": 34.6, |
| "S13": 11.8, |
| "S14": null, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 21.7, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 18.2, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "hunyuanimage-3-0-instruct", |
| "name": "HunyuanImage-3.0-Instruct", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 20, |
| "accuracy": { |
| "temporal": 28.0, |
| "causal": 32.0, |
| "spatial": 35.0, |
| "logical": 8.5, |
| "counterfactual": 20.0, |
| "hybrid": 0.0, |
| "single": 22.3, |
| "multi": 26.9, |
| "total": 22.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 38.9, |
| "appearance_consistency": 75.4, |
| "visual_plausibility": 87.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 40.0, |
| "temporal_context_knowledge": 23.1, |
| "temporal_disciplinary_knowledge": 15.9, |
| "causal_common_sense_knowledge": 46.3, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 26.3, |
| "spatial_relation": 32.1, |
| "spatial_structure": 38.3, |
| "logical_explicit_rule_deduction": 11.4, |
| "logical_implicit_pattern_induction": 3.9, |
| "counterfactual_counterfactual_imagination": 15.7, |
| "counterfactual_anomaly_correction_and_generation": 30.0 |
| }, |
| "task_types": { |
| "T01": 25.0, |
| "T02": 77.8, |
| "T03": 53.8, |
| "T04": 50.0, |
| "T05": 25.0, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 20.0, |
| "T09": 7.1, |
| "T10": 40.0, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 33.3, |
| "T15": 8.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 41.9, |
| "C02": 55.6, |
| "C03": 40.9, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 50.0, |
| "C08": 20.0, |
| "C09": 34.8, |
| "C10": 66.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 45.5, |
| "S02": 45.5, |
| "S03": 45.5, |
| "S04": 41.7, |
| "S05": 38.5, |
| "S06": 13.3, |
| "S07": 27.8, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 45.8, |
| "S11": 33.3, |
| "S12": 26.9, |
| "S13": 26.3, |
| "S14": 80.0, |
| "L01": 16.7, |
| "L02": 3.7, |
| "L03": 8.1, |
| "L04": 17.1, |
| "L05": 7.7, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 17.4, |
| "F02": 33.3, |
| "F03": 12.5, |
| "F04": 14.3, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 50.0, |
| "F10": 18.2, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "qwen-image-2-1", |
| "name": "Qwen-Image-2.1", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 21, |
| "accuracy": { |
| "temporal": 22.5, |
| "causal": 23.0, |
| "spatial": 25.0, |
| "logical": 6.5, |
| "counterfactual": 16.0, |
| "hybrid": 0.0, |
| "single": 15.8, |
| "multi": 30.8, |
| "total": 17.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 33.2, |
| "appearance_consistency": 77.7, |
| "visual_plausibility": 85.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 23.5, |
| "temporal_context_knowledge": 32.7, |
| "temporal_disciplinary_knowledge": 12.7, |
| "causal_common_sense_knowledge": 32.5, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 15.0, |
| "spatial_relation": 23.6, |
| "spatial_structure": 26.6, |
| "logical_explicit_rule_deduction": 6.5, |
| "logical_implicit_pattern_induction": 6.5, |
| "counterfactual_counterfactual_imagination": 15.7, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 66.7, |
| "T03": 23.1, |
| "T04": 30.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 20.0, |
| "T09": 14.3, |
| "T10": 60.0, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 33.3, |
| "C03": 22.7, |
| "C04": 20.0, |
| "C05": 20.0, |
| "C06": 20.0, |
| "C07": 20.0, |
| "C08": 4.0, |
| "C09": 21.7, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 36.4, |
| "S03": 18.2, |
| "S04": 25.0, |
| "S05": 30.8, |
| "S06": 13.3, |
| "S07": 22.2, |
| "S08": 22.2, |
| "S09": 33.3, |
| "S10": 16.7, |
| "S11": 40.0, |
| "S12": 30.8, |
| "S13": 26.3, |
| "S14": 20.0, |
| "L01": 4.2, |
| "L02": 3.7, |
| "L03": 0.0, |
| "L04": 17.1, |
| "L05": 7.7, |
| "L06": 11.1, |
| "L07": 0.0, |
| "F01": 34.8, |
| "F02": 22.2, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 27.3, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "firered-image-edit-1-1", |
| "name": "FireRed-Image-Edit-1.1", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 22, |
| "accuracy": { |
| "temporal": 21.0, |
| "causal": 24.5, |
| "spatial": 25.0, |
| "logical": 1.0, |
| "counterfactual": 15.0, |
| "hybrid": 4.0, |
| "single": 15.6, |
| "multi": 23.1, |
| "total": 16.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 32.8, |
| "appearance_consistency": 63.8, |
| "visual_plausibility": 92.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 27.1, |
| "temporal_context_knowledge": 26.9, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 33.8, |
| "causal_context_knowledge": 22.5, |
| "causal_disciplinary_knowledge": 16.3, |
| "spatial_relation": 26.4, |
| "spatial_structure": 23.4, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 30.0 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 44.4, |
| "T03": 30.8, |
| "T04": 30.0, |
| "T05": 75.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 26.7, |
| "T09": 0.0, |
| "T10": 53.3, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 40.7, |
| "C03": 18.2, |
| "C04": 20.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 60.0, |
| "C08": 12.0, |
| "C09": 17.4, |
| "C10": 41.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 27.3, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 58.3, |
| "S05": 23.1, |
| "S06": 6.7, |
| "S07": 38.9, |
| "S08": 22.2, |
| "S09": 0.0, |
| "S10": 4.2, |
| "S11": 40.0, |
| "S12": 34.6, |
| "S13": 15.8, |
| "S14": 30.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 5.0, |
| "F01": 17.4, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 36.4, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "flux-2-dev", |
| "name": "FLUX.2 Dev", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 23, |
| "accuracy": { |
| "temporal": 21.0, |
| "causal": 26.0, |
| "spatial": 16.5, |
| "logical": 1.5, |
| "counterfactual": 13.0, |
| "hybrid": 4.0, |
| "single": 13.3, |
| "multi": 30.8, |
| "total": 14.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.0, |
| "appearance_consistency": 57.8, |
| "visual_plausibility": 93.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 18.8, |
| "temporal_context_knowledge": 32.7, |
| "temporal_disciplinary_knowledge": 14.3, |
| "causal_common_sense_knowledge": 32.5, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 22.5, |
| "spatial_relation": 12.3, |
| "spatial_structure": 21.3, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 11.4, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 55.6, |
| "T03": 15.4, |
| "T04": 15.0, |
| "T05": 37.5, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 20.0, |
| "T09": 14.3, |
| "T10": 60.0, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 0.0, |
| "T15": 16.7, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 33.3, |
| "C03": 31.8, |
| "C04": 0.0, |
| "C05": 10.0, |
| "C06": 10.0, |
| "C07": 60.0, |
| "C08": 16.0, |
| "C09": 26.1, |
| "C10": 41.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 36.4, |
| "S04": 25.0, |
| "S05": 15.4, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 11.1, |
| "S09": 16.7, |
| "S10": 25.0, |
| "S11": 26.7, |
| "S12": 15.4, |
| "S13": 10.5, |
| "S14": 40.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 55.6, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 18.2, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "qwen-image-edit-2511", |
| "name": "Qwen-Image-Edit-2511", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 24, |
| "accuracy": { |
| "temporal": 19.5, |
| "causal": 19.5, |
| "spatial": 23.0, |
| "logical": 2.0, |
| "counterfactual": 10.0, |
| "hybrid": 0.0, |
| "single": 13.7, |
| "multi": 15.4, |
| "total": 13.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 32.8, |
| "appearance_consistency": 57.6, |
| "visual_plausibility": 85.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 24.7, |
| "temporal_context_knowledge": 15.4, |
| "temporal_disciplinary_knowledge": 15.9, |
| "causal_common_sense_knowledge": 33.8, |
| "causal_context_knowledge": 10.0, |
| "causal_disciplinary_knowledge": 10.0, |
| "spatial_relation": 22.6, |
| "spatial_structure": 23.4, |
| "logical_explicit_rule_deduction": 2.4, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 4.3, |
| "counterfactual_anomaly_correction_and_generation": 23.3 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 33.3, |
| "T03": 61.5, |
| "T04": 15.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 13.3, |
| "T09": 0.0, |
| "T10": 26.7, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 22.2, |
| "T15": 16.7, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 38.7, |
| "C02": 33.3, |
| "C03": 27.3, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 30.0, |
| "C08": 4.0, |
| "C09": 8.7, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 36.4, |
| "S03": 45.5, |
| "S04": 8.3, |
| "S05": 30.8, |
| "S06": 6.7, |
| "S07": 27.8, |
| "S08": 22.2, |
| "S09": 16.7, |
| "S10": 8.3, |
| "S11": 46.7, |
| "S12": 30.8, |
| "S13": 15.8, |
| "S14": 20.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 5.4, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 45.5, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "qwen-image-edit-2509", |
| "name": "Qwen-Image-Edit-2509", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 25, |
| "accuracy": { |
| "temporal": 17.5, |
| "causal": 19.0, |
| "spatial": 21.5, |
| "logical": 1.5, |
| "counterfactual": 15.0, |
| "hybrid": 3.0, |
| "single": 13.7, |
| "multi": 14.1, |
| "total": 13.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 30.9, |
| "appearance_consistency": 53.6, |
| "visual_plausibility": 83.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 24.7, |
| "temporal_context_knowledge": 17.3, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 28.8, |
| "causal_context_knowledge": 17.5, |
| "causal_disciplinary_knowledge": 10.0, |
| "spatial_relation": 22.6, |
| "spatial_structure": 20.2, |
| "logical_explicit_rule_deduction": 2.4, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 33.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 11.1, |
| "T03": 46.2, |
| "T04": 20.0, |
| "T05": 50.0, |
| "T06": 42.9, |
| "T07": 25.0, |
| "T08": 13.3, |
| "T09": 7.1, |
| "T10": 26.7, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 25.9, |
| "C03": 36.4, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 60.0, |
| "C08": 8.0, |
| "C09": 8.7, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 36.4, |
| "S04": 25.0, |
| "S05": 23.1, |
| "S06": 13.3, |
| "S07": 22.2, |
| "S08": 33.3, |
| "S09": 16.7, |
| "S10": 12.5, |
| "S11": 33.3, |
| "S12": 23.1, |
| "S13": 26.3, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 8.6, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 27.3, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "firered-image-edit-1-0", |
| "name": "FireRed-Image-Edit-1.0", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 26, |
| "accuracy": { |
| "temporal": 19.5, |
| "causal": 16.5, |
| "spatial": 25.0, |
| "logical": 0.5, |
| "counterfactual": 11.0, |
| "hybrid": 2.0, |
| "single": 13.2, |
| "multi": 17.9, |
| "total": 13.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.9, |
| "appearance_consistency": 59.8, |
| "visual_plausibility": 94.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 29.4, |
| "temporal_context_knowledge": 21.2, |
| "temporal_disciplinary_knowledge": 4.8, |
| "causal_common_sense_knowledge": 26.3, |
| "causal_context_knowledge": 17.5, |
| "causal_disciplinary_knowledge": 6.3, |
| "spatial_relation": 23.6, |
| "spatial_structure": 26.6, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 4.3, |
| "counterfactual_anomaly_correction_and_generation": 26.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 33.3, |
| "T03": 38.5, |
| "T04": 35.0, |
| "T05": 62.5, |
| "T06": 14.3, |
| "T07": 50.0, |
| "T08": 26.7, |
| "T09": 0.0, |
| "T10": 33.3, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 22.6, |
| "C02": 33.3, |
| "C03": 22.7, |
| "C04": 0.0, |
| "C05": 10.0, |
| "C06": 30.0, |
| "C07": 30.0, |
| "C08": 4.0, |
| "C09": 4.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 36.4, |
| "S03": 27.3, |
| "S04": 50.0, |
| "S05": 30.8, |
| "S06": 6.7, |
| "S07": 16.7, |
| "S08": 22.2, |
| "S09": 16.7, |
| "S10": 16.7, |
| "S11": 46.7, |
| "S12": 34.6, |
| "S13": 10.5, |
| "S14": 30.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 18.2, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "sensenova-u1-a3b-mot-sft", |
| "name": "SenseNova-U1-A3B-MoT-SFT", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 27, |
| "accuracy": { |
| "temporal": 21.5, |
| "causal": 28.0, |
| "spatial": 7.0, |
| "logical": 3.0, |
| "counterfactual": 11.0, |
| "hybrid": 0.0, |
| "single": 14.0, |
| "multi": 1.3, |
| "total": 13.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 38.3, |
| "appearance_consistency": 54.3, |
| "visual_plausibility": 57.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 38.8, |
| "temporal_context_knowledge": 5.8, |
| "temporal_disciplinary_knowledge": 11.1, |
| "causal_common_sense_knowledge": 35.0, |
| "causal_context_knowledge": 5.0, |
| "causal_disciplinary_knowledge": 32.5, |
| "spatial_relation": 5.7, |
| "spatial_structure": 8.5, |
| "logical_explicit_rule_deduction": 3.3, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 54.2, |
| "T02": 55.6, |
| "T03": 23.1, |
| "T04": 50.0, |
| "T05": 12.5, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 20.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 0.0, |
| "T15": 16.7, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 37.0, |
| "C03": 36.4, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 20.0, |
| "C08": 24.0, |
| "C09": 39.1, |
| "C10": 66.7, |
| "C11": 66.7, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 8.3, |
| "S11": 20.0, |
| "S12": 11.5, |
| "S13": 0.0, |
| "S14": 0.0, |
| "L01": 8.3, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 2.6, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 17.4, |
| "F02": 33.3, |
| "F03": 25.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "joyai-image-edit-plus", |
| "name": "JoyAI-Image-Edit-Plus", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 28, |
| "accuracy": { |
| "temporal": 14.5, |
| "causal": 19.5, |
| "spatial": 19.0, |
| "logical": 5.0, |
| "counterfactual": 9.0, |
| "hybrid": 4.0, |
| "single": 11.2, |
| "multi": 33.3, |
| "total": 12.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.0, |
| "appearance_consistency": 78.8, |
| "visual_plausibility": 91.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 4.7, |
| "temporal_context_knowledge": 36.5, |
| "temporal_disciplinary_knowledge": 9.5, |
| "causal_common_sense_knowledge": 31.3, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 10.0, |
| "spatial_relation": 16.0, |
| "spatial_structure": 22.3, |
| "logical_explicit_rule_deduction": 4.1, |
| "logical_implicit_pattern_induction": 6.5, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 11.1, |
| "T03": 15.4, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 26.7, |
| "T09": 14.3, |
| "T10": 60.0, |
| "T11": 50.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 41.9, |
| "C02": 25.9, |
| "C03": 22.7, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 20.0, |
| "C07": 30.0, |
| "C08": 12.0, |
| "C09": 8.7, |
| "C10": 8.3, |
| "C11": 33.3, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 9.1, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 23.1, |
| "S06": 6.7, |
| "S07": 22.2, |
| "S08": 11.1, |
| "S09": 16.7, |
| "S10": 16.7, |
| "S11": 33.3, |
| "S12": 15.4, |
| "S13": 21.1, |
| "S14": 40.0, |
| "L01": 0.0, |
| "L02": 3.7, |
| "L03": 0.0, |
| "L04": 11.4, |
| "L05": 10.3, |
| "L06": 5.6, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "flux-2-klein-9b", |
| "name": "FLUX.2 Klein 9B", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 29, |
| "accuracy": { |
| "temporal": 22.0, |
| "causal": 16.0, |
| "spatial": 16.5, |
| "logical": 3.5, |
| "counterfactual": 9.0, |
| "hybrid": 3.0, |
| "single": 11.1, |
| "multi": 33.3, |
| "total": 12.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 28.8, |
| "appearance_consistency": 65.7, |
| "visual_plausibility": 91.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 21.2, |
| "temporal_context_knowledge": 34.6, |
| "temporal_disciplinary_knowledge": 12.7, |
| "causal_common_sense_knowledge": 23.8, |
| "causal_context_knowledge": 20.0, |
| "causal_disciplinary_knowledge": 6.3, |
| "spatial_relation": 12.3, |
| "spatial_structure": 21.3, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 9.1, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 12.5, |
| "T02": 33.3, |
| "T03": 30.8, |
| "T04": 20.0, |
| "T05": 50.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 33.3, |
| "T09": 7.1, |
| "T10": 60.0, |
| "T11": 37.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 22.2, |
| "C03": 22.7, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 20.0, |
| "C07": 60.0, |
| "C08": 0.0, |
| "C09": 4.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 9.1, |
| "S04": 41.7, |
| "S05": 15.4, |
| "S06": 6.7, |
| "S07": 11.1, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 12.5, |
| "S11": 20.0, |
| "S12": 26.9, |
| "S13": 10.5, |
| "S14": 50.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 15.4, |
| "L06": 0.0, |
| "L07": 5.0, |
| "F01": 8.7, |
| "F02": 33.3, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "bagel-w-cot", |
| "name": "BAGEL (w/ CoT)", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 30, |
| "accuracy": { |
| "temporal": 19.0, |
| "causal": 18.0, |
| "spatial": 16.5, |
| "logical": 0.0, |
| "counterfactual": 6.0, |
| "hybrid": 0.0, |
| "single": 9.8, |
| "multi": 29.5, |
| "total": 11.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 31.8, |
| "appearance_consistency": 61.0, |
| "visual_plausibility": 73.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 18.8, |
| "temporal_context_knowledge": 26.9, |
| "temporal_disciplinary_knowledge": 12.7, |
| "causal_common_sense_knowledge": 28.8, |
| "causal_context_knowledge": 17.5, |
| "causal_disciplinary_knowledge": 7.5, |
| "spatial_relation": 9.4, |
| "spatial_structure": 24.5, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 6.7 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 22.2, |
| "T03": 15.4, |
| "T04": 15.0, |
| "T05": 12.5, |
| "T06": 42.9, |
| "T07": 0.0, |
| "T08": 20.0, |
| "T09": 14.3, |
| "T10": 46.7, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 25.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 29.0, |
| "C02": 25.9, |
| "C03": 31.8, |
| "C04": 20.0, |
| "C05": 20.0, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 0.0, |
| "C09": 8.7, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 11.1, |
| "S08": 0.0, |
| "S09": 16.7, |
| "S10": 29.2, |
| "S11": 6.7, |
| "S12": 15.4, |
| "S13": 31.6, |
| "S14": 50.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "hidream-o1-image", |
| "name": "HiDream-O1-Image", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 31, |
| "accuracy": { |
| "temporal": 18.5, |
| "causal": 13.5, |
| "spatial": 17.5, |
| "logical": 0.5, |
| "counterfactual": 7.0, |
| "hybrid": 0.0, |
| "single": 8.8, |
| "multi": 33.3, |
| "total": 10.7 |
| }, |
| "metrics": { |
| "instruction_reasoning": 27.1, |
| "appearance_consistency": 54.6, |
| "visual_plausibility": 84.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 21.2, |
| "temporal_context_knowledge": 26.9, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 25.0, |
| "causal_context_knowledge": 2.5, |
| "causal_disciplinary_knowledge": 7.5, |
| "spatial_relation": 9.4, |
| "spatial_structure": 26.6, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 16.7, |
| "T02": 22.2, |
| "T03": 30.8, |
| "T04": 35.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 26.7, |
| "T09": 7.1, |
| "T10": 46.7, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 29.6, |
| "C03": 18.2, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 10.0, |
| "C08": 0.0, |
| "C09": 8.7, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 0.0, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 8.3, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 16.7, |
| "S08": 0.0, |
| "S09": 16.7, |
| "S10": 8.3, |
| "S11": 33.3, |
| "S12": 19.2, |
| "S13": 15.8, |
| "S14": 100.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 0.0, |
| "F03": 12.5, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 0.0, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "flux-2-klein-4b", |
| "name": "FLUX.2 Klein 4B", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 32, |
| "accuracy": { |
| "temporal": 16.5, |
| "causal": 12.5, |
| "spatial": 14.5, |
| "logical": 4.0, |
| "counterfactual": 10.0, |
| "hybrid": 1.0, |
| "single": 8.0, |
| "multi": 41.0, |
| "total": 10.6 |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.1, |
| "appearance_consistency": 72.2, |
| "visual_plausibility": 90.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 10.6, |
| "temporal_context_knowledge": 36.5, |
| "temporal_disciplinary_knowledge": 7.9, |
| "causal_common_sense_knowledge": 15.0, |
| "causal_context_knowledge": 15.0, |
| "causal_disciplinary_knowledge": 8.8, |
| "spatial_relation": 9.4, |
| "spatial_structure": 20.2, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 7.8, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 11.1, |
| "T03": 30.8, |
| "T04": 10.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 26.7, |
| "T09": 14.3, |
| "T10": 80.0, |
| "T11": 12.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 22.6, |
| "C02": 14.8, |
| "C03": 4.5, |
| "C04": 10.0, |
| "C05": 10.0, |
| "C06": 10.0, |
| "C07": 30.0, |
| "C08": 0.0, |
| "C09": 13.0, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 20.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 18.2, |
| "S04": 8.3, |
| "S05": 15.4, |
| "S06": 13.3, |
| "S07": 0.0, |
| "S08": 33.3, |
| "S09": 0.0, |
| "S10": 4.2, |
| "S11": 26.7, |
| "S12": 15.4, |
| "S13": 10.5, |
| "S14": 80.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 10.3, |
| "L06": 0.0, |
| "L07": 10.0, |
| "F01": 4.3, |
| "F02": 55.6, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 18.2, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "uniworld-v2", |
| "name": "UniWorld-V2", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 33, |
| "accuracy": { |
| "temporal": 13.5, |
| "causal": 17.0, |
| "spatial": 15.5, |
| "logical": 0.0, |
| "counterfactual": 12.0, |
| "hybrid": 1.0, |
| "single": 10.7, |
| "multi": 7.7, |
| "total": 10.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 30.6, |
| "appearance_consistency": 46.0, |
| "visual_plausibility": 85.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 18.8, |
| "temporal_context_knowledge": 9.6, |
| "temporal_disciplinary_knowledge": 9.5, |
| "causal_common_sense_knowledge": 30.0, |
| "causal_context_knowledge": 10.0, |
| "causal_disciplinary_knowledge": 7.5, |
| "spatial_relation": 16.0, |
| "spatial_structure": 14.9, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 23.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 44.4, |
| "T03": 7.7, |
| "T04": 20.0, |
| "T05": 25.0, |
| "T06": 42.9, |
| "T07": 0.0, |
| "T08": 13.3, |
| "T09": 0.0, |
| "T10": 13.3, |
| "T11": 12.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 16.7, |
| "T17": 20.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 35.5, |
| "C02": 29.6, |
| "C03": 22.7, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 30.0, |
| "C08": 8.0, |
| "C09": 8.7, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 18.2, |
| "S02": 0.0, |
| "S03": 18.2, |
| "S04": 16.7, |
| "S05": 38.5, |
| "S06": 6.7, |
| "S07": 22.2, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 4.2, |
| "S11": 26.7, |
| "S12": 26.9, |
| "S13": 5.3, |
| "S14": 10.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 33.3, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 9.1, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "sensenova-u1-8b-mot-sft", |
| "name": "SenseNova-U1-8B-MoT-SFT", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 34, |
| "accuracy": { |
| "temporal": 16.0, |
| "causal": 21.0, |
| "spatial": 3.5, |
| "logical": 3.5, |
| "counterfactual": 15.0, |
| "hybrid": 0.0, |
| "single": 11.1, |
| "multi": 1.3, |
| "total": 10.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 34.6, |
| "appearance_consistency": 57.3, |
| "visual_plausibility": 60.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 27.1, |
| "temporal_context_knowledge": 5.8, |
| "temporal_disciplinary_knowledge": 9.5, |
| "causal_common_sense_knowledge": 31.3, |
| "causal_context_knowledge": 12.5, |
| "causal_disciplinary_knowledge": 15.0, |
| "spatial_relation": 2.8, |
| "spatial_structure": 4.3, |
| "logical_explicit_rule_deduction": 4.1, |
| "logical_implicit_pattern_induction": 2.6, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 29.2, |
| "T02": 55.6, |
| "T03": 15.4, |
| "T04": 25.0, |
| "T05": 0.0, |
| "T06": 42.9, |
| "T07": 25.0, |
| "T08": 20.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 27.8, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 33.3, |
| "C03": 27.3, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 40.0, |
| "C08": 8.0, |
| "C09": 17.4, |
| "C10": 41.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 5.6, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 8.3, |
| "S11": 6.7, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": 0.0, |
| "L01": 12.5, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 0.0, |
| "L06": 11.1, |
| "L07": 0.0, |
| "F01": 17.4, |
| "F02": 33.3, |
| "F03": 25.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 40.0, |
| "F10": 0.0, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "unipic-3-0", |
| "name": "UniPic 3.0", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 35, |
| "accuracy": { |
| "temporal": 7.0, |
| "causal": 14.0, |
| "spatial": 12.5, |
| "logical": 0.0, |
| "counterfactual": 7.0, |
| "hybrid": 0.0, |
| "single": 7.5, |
| "multi": 6.4, |
| "total": 7.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 24.8, |
| "appearance_consistency": 55.4, |
| "visual_plausibility": 80.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 10.6, |
| "temporal_context_knowledge": 3.8, |
| "temporal_disciplinary_knowledge": 4.8, |
| "causal_common_sense_knowledge": 22.5, |
| "causal_context_knowledge": 7.5, |
| "causal_disciplinary_knowledge": 8.8, |
| "spatial_relation": 11.3, |
| "spatial_structure": 13.8, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 11.1, |
| "T03": 7.7, |
| "T04": 15.0, |
| "T05": 12.5, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 6.7, |
| "T09": 0.0, |
| "T10": 6.7, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 22.2, |
| "C03": 18.2, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 30.0, |
| "C08": 8.0, |
| "C09": 8.7, |
| "C10": 16.7, |
| "C11": 33.3, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 18.2, |
| "S02": 9.1, |
| "S03": 9.1, |
| "S04": 8.3, |
| "S05": 23.1, |
| "S06": 6.7, |
| "S07": 11.1, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 12.5, |
| "S11": 13.3, |
| "S12": 15.4, |
| "S13": 15.8, |
| "S14": 10.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 14.3, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "bagel", |
| "name": "BAGEL", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 36, |
| "accuracy": { |
| "temporal": 10.0, |
| "causal": 7.0, |
| "spatial": 10.0, |
| "logical": 1.0, |
| "counterfactual": 8.0, |
| "hybrid": 0.0, |
| "single": 4.8, |
| "multi": 25.6, |
| "total": 6.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.3, |
| "appearance_consistency": 54.9, |
| "visual_plausibility": 75.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 7.1, |
| "temporal_context_knowledge": 23.1, |
| "temporal_disciplinary_knowledge": 3.2, |
| "causal_common_sense_knowledge": 13.8, |
| "causal_context_knowledge": 5.0, |
| "causal_disciplinary_knowledge": 1.3, |
| "spatial_relation": 5.7, |
| "spatial_structure": 14.9, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 8.6, |
| "counterfactual_anomaly_correction_and_generation": 6.7 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 22.2, |
| "T03": 15.4, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 26.7, |
| "T09": 7.1, |
| "T10": 33.3, |
| "T11": 25.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 19.4, |
| "C02": 14.8, |
| "C03": 4.5, |
| "C04": 0.0, |
| "C05": 10.0, |
| "C06": 10.0, |
| "C07": 0.0, |
| "C08": 4.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 27.3, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 11.1, |
| "S09": 0.0, |
| "S10": 16.7, |
| "S11": 6.7, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": 80.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 13.0, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 0.0, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "omnigen2", |
| "name": "OmniGen2", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 37, |
| "accuracy": { |
| "temporal": 6.0, |
| "causal": 5.5, |
| "spatial": 6.0, |
| "logical": 0.0, |
| "counterfactual": 6.0, |
| "hybrid": 0.0, |
| "single": 2.9, |
| "multi": 17.9, |
| "total": 4.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 14.7, |
| "appearance_consistency": 57.6, |
| "visual_plausibility": 81.5 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 3.5, |
| "temporal_context_knowledge": 13.5, |
| "temporal_disciplinary_knowledge": 3.2, |
| "causal_common_sense_knowledge": 5.0, |
| "causal_context_knowledge": 10.0, |
| "causal_disciplinary_knowledge": 3.8, |
| "spatial_relation": 0.9, |
| "spatial_structure": 11.7, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 7.1, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 15.4, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 13.3, |
| "T09": 7.1, |
| "T10": 20.0, |
| "T11": 12.5, |
| "T12": 0.0, |
| "T13": 12.5, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 6.5, |
| "C02": 7.4, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 20.0, |
| "C06": 0.0, |
| "C07": 20.0, |
| "C08": 4.0, |
| "C09": 4.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 0.0, |
| "S10": 4.2, |
| "S11": 6.7, |
| "S12": 3.8, |
| "S13": 21.1, |
| "S14": 40.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 13.0, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "omnigen", |
| "name": "OmniGen", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 38, |
| "accuracy": { |
| "temporal": 7.0, |
| "causal": 2.5, |
| "spatial": 5.0, |
| "logical": 3.0, |
| "counterfactual": 4.0, |
| "hybrid": 0.0, |
| "single": 2.7, |
| "multi": 17.9, |
| "total": 3.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 12.1, |
| "appearance_consistency": 58.4, |
| "visual_plausibility": 74.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 2.4, |
| "temporal_context_knowledge": 15.4, |
| "temporal_disciplinary_knowledge": 6.3, |
| "causal_common_sense_knowledge": 1.3, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 5.0, |
| "spatial_relation": 2.8, |
| "spatial_structure": 7.4, |
| "logical_explicit_rule_deduction": 4.1, |
| "logical_implicit_pattern_induction": 1.3, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 6.7 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 13.3, |
| "T09": 14.3, |
| "T10": 20.0, |
| "T11": 12.5, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 0.0, |
| "C02": 3.7, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 13.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 33.3, |
| "S10": 4.2, |
| "S11": 0.0, |
| "S12": 7.7, |
| "S13": 15.8, |
| "S14": 10.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 14.3, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 0.0, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 0.0, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "emu2-gen", |
| "name": "Emu2-Gen", |
| "group": "open", |
| "multi_image": true, |
| "source_order": 39, |
| "accuracy": { |
| "temporal": 2.5, |
| "causal": 1.0, |
| "spatial": 1.0, |
| "logical": 0.0, |
| "counterfactual": 2.0, |
| "hybrid": 0.0, |
| "single": 1.0, |
| "multi": 2.6, |
| "total": 1.1 |
| }, |
| "metrics": { |
| "instruction_reasoning": 10.0, |
| "appearance_consistency": 25.7, |
| "visual_plausibility": 64.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 3.5, |
| "temporal_context_knowledge": 1.9, |
| "temporal_disciplinary_knowledge": 1.6, |
| "causal_common_sense_knowledge": 1.3, |
| "causal_context_knowledge": 2.5, |
| "causal_disciplinary_knowledge": 0.0, |
| "spatial_relation": 0.9, |
| "spatial_structure": 1.1, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 1.4, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 11.1, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 6.7, |
| "T11": 0.0, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 0.0, |
| "C02": 0.0, |
| "C03": 4.5, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": 16.7, |
| "S10": 4.2, |
| "S11": 0.0, |
| "S12": 0.0, |
| "S13": 0.0, |
| "S14": 0.0, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": 0.0, |
| "F01": 4.3, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 0.0, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "joyai-image-edit", |
| "name": "JoyAI-Image-Edit", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 40, |
| "accuracy": { |
| "temporal": 13.7, |
| "causal": 24.0, |
| "spatial": 15.4, |
| "logical": 1.1, |
| "counterfactual": 21.0, |
| "hybrid": 4.0, |
| "single": 13.4, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 30.6, |
| "appearance_consistency": 70.4, |
| "visual_plausibility": 91.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 17.6, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 11.9, |
| "causal_common_sense_knowledge": 39.2, |
| "causal_context_knowledge": 21.1, |
| "causal_disciplinary_knowledge": 9.3, |
| "spatial_relation": 14.0, |
| "spatial_structure": 17.1, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 36.7 |
| }, |
| "task_types": { |
| "T01": 12.5, |
| "T02": 22.2, |
| "T03": 38.5, |
| "T04": 15.0, |
| "T05": 25.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 16.7, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 45.2, |
| "C02": 25.9, |
| "C03": 47.6, |
| "C04": 20.0, |
| "C05": 12.5, |
| "C06": 10.0, |
| "C07": 40.0, |
| "C08": 4.2, |
| "C09": 10.5, |
| "C10": 33.3, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 45.5, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 22.2, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 8.3, |
| "S11": 20.0, |
| "S12": 30.8, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 21.7, |
| "F02": 22.2, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 60.0, |
| "F10": 36.4, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "boogu-image-0-1-edit", |
| "name": "Boogu-Image-0.1-Edit", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 41, |
| "accuracy": { |
| "temporal": 13.1, |
| "causal": 22.4, |
| "spatial": 17.0, |
| "logical": 2.2, |
| "counterfactual": 17.0, |
| "hybrid": 1.0, |
| "single": 12.8, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 27.1, |
| "appearance_consistency": 80.7, |
| "visual_plausibility": 91.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 14.1, |
| "temporal_context_knowledge": 8.3, |
| "temporal_disciplinary_knowledge": 13.6, |
| "causal_common_sense_knowledge": 35.4, |
| "causal_context_knowledge": 18.4, |
| "causal_disciplinary_knowledge": 10.7, |
| "spatial_relation": 14.0, |
| "spatial_structure": 20.7, |
| "logical_explicit_rule_deduction": 2.4, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 23.3 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 11.1, |
| "T03": 30.8, |
| "T04": 10.0, |
| "T05": 25.0, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 18.2, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 25.0, |
| "T13": 0.0, |
| "T14": 33.3, |
| "T15": 8.3, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 48.1, |
| "C03": 23.8, |
| "C04": 0.0, |
| "C05": 12.5, |
| "C06": 20.0, |
| "C07": 40.0, |
| "C08": 8.3, |
| "C09": 15.8, |
| "C10": 8.3, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 27.3, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 15.4, |
| "S06": 6.7, |
| "S07": 11.1, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 20.8, |
| "S11": 20.0, |
| "S12": 15.4, |
| "S13": 29.4, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 3.7, |
| "L03": 2.7, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 34.8, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 27.3, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "step1x-edit-thinking-reflection", |
| "name": "Step1X-Edit (thinking + reflection)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 42, |
| "accuracy": { |
| "temporal": 17.3, |
| "causal": 18.2, |
| "spatial": 11.0, |
| "logical": 1.1, |
| "counterfactual": 14.0, |
| "hybrid": 2.0, |
| "single": 11.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.3, |
| "appearance_consistency": 65.7, |
| "visual_plausibility": 89.2 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 27.1, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 10.2, |
| "causal_common_sense_knowledge": 21.5, |
| "causal_context_knowledge": 23.7, |
| "causal_disciplinary_knowledge": 12.0, |
| "spatial_relation": 11.0, |
| "spatial_structure": 11.0, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 12.9, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 37.5, |
| "T02": 44.4, |
| "T03": 23.1, |
| "T04": 25.0, |
| "T05": 12.5, |
| "T06": 14.3, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 50.0, |
| "T19": 0.0, |
| "C01": 19.4, |
| "C02": 29.6, |
| "C03": 14.3, |
| "C04": 20.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 60.0, |
| "C08": 4.2, |
| "C09": 26.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 5.6, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 4.2, |
| "S11": 33.3, |
| "S12": 7.7, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 30.4, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 9.1, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "step1x-edit-thinking", |
| "name": "Step1X-Edit (thinking)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 43, |
| "accuracy": { |
| "temporal": 14.3, |
| "causal": 15.1, |
| "spatial": 13.2, |
| "logical": 2.2, |
| "counterfactual": 17.0, |
| "hybrid": 2.0, |
| "single": 10.8, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 25.5, |
| "appearance_consistency": 67.5, |
| "visual_plausibility": 88.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 18.8, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 11.9, |
| "causal_common_sense_knowledge": 21.5, |
| "causal_context_knowledge": 7.9, |
| "causal_disciplinary_knowledge": 12.0, |
| "spatial_relation": 11.0, |
| "spatial_structure": 15.9, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 15.7, |
| "counterfactual_anomaly_correction_and_generation": 20.0 |
| }, |
| "task_types": { |
| "T01": 25.0, |
| "T02": 22.2, |
| "T03": 15.4, |
| "T04": 15.0, |
| "T05": 12.5, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 0.0, |
| "T09": 8.3, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 25.0, |
| "T13": 25.0, |
| "T14": 11.1, |
| "T15": 8.3, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 22.2, |
| "C03": 14.3, |
| "C04": 0.0, |
| "C05": 12.5, |
| "C06": 0.0, |
| "C07": 20.0, |
| "C08": 8.3, |
| "C09": 15.8, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 33.3, |
| "C14": 10.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 0.0, |
| "S06": 6.7, |
| "S07": 22.2, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 8.3, |
| "S11": 33.3, |
| "S12": 11.5, |
| "S13": 17.6, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 26.1, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 12.5, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 22.2 |
| } |
| }, |
| { |
| "id": "step1x-edit-base", |
| "name": "Step1X-Edit (base)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 44, |
| "accuracy": { |
| "temporal": 13.1, |
| "causal": 16.1, |
| "spatial": 12.6, |
| "logical": 0.6, |
| "counterfactual": 15.0, |
| "hybrid": 1.0, |
| "single": 10.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 24.2, |
| "appearance_consistency": 68.1, |
| "visual_plausibility": 86.6 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 17.6, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 11.9, |
| "causal_common_sense_knowledge": 24.1, |
| "causal_context_knowledge": 13.2, |
| "causal_disciplinary_knowledge": 9.3, |
| "spatial_relation": 13.0, |
| "spatial_structure": 12.2, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 14.3, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 20.8, |
| "T02": 33.3, |
| "T03": 30.8, |
| "T04": 5.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 25.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 0.0, |
| "T16": 22.2, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 25.8, |
| "C02": 25.9, |
| "C03": 19.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 50.0, |
| "C08": 8.3, |
| "C09": 10.5, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 9.1, |
| "S03": 36.4, |
| "S04": 16.7, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 22.2, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 20.0, |
| "S12": 7.7, |
| "S13": 11.8, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 2.7, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 21.7, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 28.6, |
| "F05": 12.5, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 9.1, |
| "F11": 33.3 |
| } |
| }, |
| { |
| "id": "longcat-image-edit", |
| "name": "LongCat-Image-Edit", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 45, |
| "accuracy": { |
| "temporal": 13.7, |
| "causal": 16.1, |
| "spatial": 13.2, |
| "logical": 1.1, |
| "counterfactual": 9.0, |
| "hybrid": 0.0, |
| "single": 9.7, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 27.5, |
| "appearance_consistency": 55.8, |
| "visual_plausibility": 84.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 21.2, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 6.8, |
| "causal_common_sense_knowledge": 22.8, |
| "causal_context_knowledge": 18.4, |
| "causal_disciplinary_knowledge": 8.0, |
| "spatial_relation": 13.0, |
| "spatial_structure": 13.4, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 8.3, |
| "T02": 22.2, |
| "T03": 46.2, |
| "T04": 15.0, |
| "T05": 37.5, |
| "T06": 28.6, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 22.2, |
| "T15": 8.3, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 32.3, |
| "C02": 14.8, |
| "C03": 19.0, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 20.0, |
| "C07": 40.0, |
| "C08": 8.3, |
| "C09": 5.3, |
| "C10": 25.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 25.0, |
| "S05": 7.7, |
| "S06": 6.7, |
| "S07": 11.1, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 12.5, |
| "S11": 20.0, |
| "S12": 15.4, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 8.7, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 14.3, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "flux-1-kontext-dev", |
| "name": "FLUX.1 Kontext Dev", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 46, |
| "accuracy": { |
| "temporal": 3.0, |
| "causal": 3.6, |
| "spatial": 3.8, |
| "logical": 3.3, |
| "counterfactual": 7.0, |
| "hybrid": 1.0, |
| "single": 3.6, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 9.8, |
| "appearance_consistency": 70.7, |
| "visual_plausibility": 82.9 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 1.2, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 6.8, |
| "causal_common_sense_knowledge": 5.1, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 4.0, |
| "spatial_relation": 1.0, |
| "spatial_structure": 7.3, |
| "logical_explicit_rule_deduction": 4.1, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 6.5, |
| "C02": 3.7, |
| "C03": 4.8, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 33.3, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 11.5, |
| "S13": 17.6, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 14.3, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 8.7, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "llada-image", |
| "name": "LLaDA-Image", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 47, |
| "accuracy": { |
| "temporal": 4.8, |
| "causal": 5.7, |
| "spatial": 2.2, |
| "logical": 0.6, |
| "counterfactual": 8.0, |
| "hybrid": 0.0, |
| "single": 3.5, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 20.2, |
| "appearance_consistency": 25.0, |
| "visual_plausibility": 81.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 5.9, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 3.4, |
| "causal_common_sense_knowledge": 10.1, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 4.0, |
| "spatial_relation": 2.0, |
| "spatial_structure": 2.4, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 1.8, |
| "counterfactual_counterfactual_imagination": 5.7, |
| "counterfactual_anomaly_correction_and_generation": 13.3 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 0.0, |
| "T03": 15.4, |
| "T04": 5.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 11.1, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 12.9, |
| "C02": 11.1, |
| "C03": 4.8, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 16.7, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 6.7, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 7.7, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 2.6, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 0.0, |
| "F02": 22.2, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "internvl-u-w-cot", |
| "name": "InternVL-U (w/ CoT)", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 48, |
| "accuracy": { |
| "temporal": 6.0, |
| "causal": 3.1, |
| "spatial": 2.2, |
| "logical": 0.0, |
| "counterfactual": 4.0, |
| "hybrid": 1.0, |
| "single": 2.7, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 20.4, |
| "appearance_consistency": 41.4, |
| "visual_plausibility": 66.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 8.2, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 5.1, |
| "causal_common_sense_knowledge": 6.3, |
| "causal_context_knowledge": 2.6, |
| "causal_disciplinary_knowledge": 0.0, |
| "spatial_relation": 0.0, |
| "spatial_structure": 4.9, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 1.4, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 11.1, |
| "T03": 15.4, |
| "T04": 15.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 5.6, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 9.7, |
| "C02": 0.0, |
| "C03": 9.5, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 6.7, |
| "S12": 7.7, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 4.3, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 20.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "ovis-u1", |
| "name": "Ovis-U1", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 49, |
| "accuracy": { |
| "temporal": 3.6, |
| "causal": 5.7, |
| "spatial": 2.2, |
| "logical": 0.6, |
| "counterfactual": 2.0, |
| "hybrid": 0.0, |
| "single": 2.6, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 16.9, |
| "appearance_consistency": 41.1, |
| "visual_plausibility": 67.3 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 5.9, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 1.7, |
| "causal_common_sense_knowledge": 7.6, |
| "causal_context_knowledge": 5.3, |
| "causal_disciplinary_knowledge": 4.0, |
| "spatial_relation": 0.0, |
| "spatial_structure": 4.9, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 1.4, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 22.2, |
| "T03": 15.4, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 8.3, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 16.1, |
| "C02": 3.7, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 10.0, |
| "C08": 8.3, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 8.3, |
| "S11": 6.7, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 4.3, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "internvl-u", |
| "name": "InternVL-U", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 50, |
| "accuracy": { |
| "temporal": 3.6, |
| "causal": 4.2, |
| "spatial": 1.1, |
| "logical": 0.6, |
| "counterfactual": 5.0, |
| "hybrid": 0.0, |
| "single": 2.4, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 19.5, |
| "appearance_consistency": 39.3, |
| "visual_plausibility": 68.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 5.9, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 1.7, |
| "causal_common_sense_knowledge": 7.6, |
| "causal_context_knowledge": 2.6, |
| "causal_disciplinary_knowledge": 1.3, |
| "spatial_relation": 0.0, |
| "spatial_structure": 2.4, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 15.4, |
| "T04": 15.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 12.9, |
| "C02": 7.4, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 10.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 4.2, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 4.3, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 18.2, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "lumina-dimoo", |
| "name": "Lumina-DiMOO", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 51, |
| "accuracy": { |
| "temporal": 1.8, |
| "causal": 2.6, |
| "spatial": 2.2, |
| "logical": 2.2, |
| "counterfactual": 4.0, |
| "hybrid": 0.0, |
| "single": 2.2, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 10.9, |
| "appearance_consistency": 49.6, |
| "visual_plausibility": 60.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 2.4, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 0.0, |
| "causal_common_sense_knowledge": 5.1, |
| "causal_context_knowledge": 2.6, |
| "causal_disciplinary_knowledge": 0.0, |
| "spatial_relation": 3.0, |
| "spatial_structure": 1.2, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 6.7 |
| }, |
| "task_types": { |
| "T01": 4.2, |
| "T02": 11.1, |
| "T03": 0.0, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 6.5, |
| "C02": 3.7, |
| "C03": 4.8, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 10.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 0.0, |
| "S03": 9.1, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 4.3, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "uniworld-v1", |
| "name": "UniWorld-V1", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 52, |
| "accuracy": { |
| "temporal": 3.0, |
| "causal": 1.0, |
| "spatial": 1.6, |
| "logical": 0.0, |
| "counterfactual": 3.0, |
| "hybrid": 0.0, |
| "single": 1.4, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 10.7, |
| "appearance_consistency": 25.1, |
| "visual_plausibility": 56.8 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 3.5, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 3.4, |
| "causal_common_sense_knowledge": 1.3, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 1.3, |
| "spatial_relation": 1.0, |
| "spatial_structure": 2.4, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 2.9, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 11.1, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 12.5, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 0.0, |
| "C02": 3.7, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 5.3, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 0.0, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 13.3, |
| "S12": 0.0, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 0.0, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 25.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 10.0, |
| "F10": 0.0, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "unipic2-sd3-5m-kontext-2b", |
| "name": "UniPic2-SD3.5M-Kontext-2B", |
| "group": "open", |
| "multi_image": false, |
| "source_order": 53, |
| "accuracy": { |
| "temporal": 0.0, |
| "causal": 1.0, |
| "spatial": 1.6, |
| "logical": 1.1, |
| "counterfactual": 2.0, |
| "hybrid": 1.0, |
| "single": 1.1, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 10.3, |
| "appearance_consistency": 37.9, |
| "visual_plausibility": 48.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 0.0, |
| "temporal_context_knowledge": 0.0, |
| "temporal_disciplinary_knowledge": 0.0, |
| "causal_common_sense_knowledge": 1.3, |
| "causal_context_knowledge": 0.0, |
| "causal_disciplinary_knowledge": 1.3, |
| "spatial_relation": 1.0, |
| "spatial_structure": 2.4, |
| "logical_explicit_rule_deduction": 1.6, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 1.4, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 0.0, |
| "T02": 0.0, |
| "T03": 0.0, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 0.0, |
| "T07": 0.0, |
| "T08": 0.0, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 3.2, |
| "C02": 0.0, |
| "C03": 0.0, |
| "C04": 0.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 0.0, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 10.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 0.0, |
| "S11": 0.0, |
| "S12": 7.7, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 5.7, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 0.0, |
| "F02": 11.1, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| }, |
| { |
| "id": "rise-agent-ours", |
| "name": "RISE-Agent (Ours)", |
| "group": "agentic", |
| "multi_image": true, |
| "source_order": 54, |
| "accuracy": { |
| "temporal": 51.0, |
| "causal": 57.0, |
| "spatial": 34.0, |
| "logical": 25.0, |
| "counterfactual": 54.0, |
| "hybrid": 15.0, |
| "single": 40.6, |
| "multi": 37.2, |
| "total": 40.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 63.8, |
| "appearance_consistency": 85.3, |
| "visual_plausibility": 93.4 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 65.9, |
| "temporal_context_knowledge": 46.2, |
| "temporal_disciplinary_knowledge": 34.9, |
| "causal_common_sense_knowledge": 67.5, |
| "causal_context_knowledge": 45.0, |
| "causal_disciplinary_knowledge": 52.5, |
| "spatial_relation": 31.1, |
| "spatial_structure": 37.2, |
| "logical_explicit_rule_deduction": 30.9, |
| "logical_implicit_pattern_induction": 15.6, |
| "counterfactual_counterfactual_imagination": 55.7, |
| "counterfactual_anomaly_correction_and_generation": 50.0 |
| }, |
| "task_types": { |
| "T01": 66.7, |
| "T02": 88.9, |
| "T03": 53.8, |
| "T04": 55.0, |
| "T05": 75.0, |
| "T06": 85.7, |
| "T07": 50.0, |
| "T08": 60.0, |
| "T09": 21.4, |
| "T10": 60.0, |
| "T11": 37.5, |
| "T12": 25.0, |
| "T13": 12.5, |
| "T14": 55.6, |
| "T15": 41.7, |
| "T16": 38.9, |
| "T17": 20.0, |
| "T18": 25.0, |
| "T19": 33.3, |
| "C01": 74.2, |
| "C02": 63.0, |
| "C03": 63.6, |
| "C04": 40.0, |
| "C05": 30.0, |
| "C06": 60.0, |
| "C07": 50.0, |
| "C08": 40.0, |
| "C09": 69.6, |
| "C10": 83.3, |
| "C11": 66.7, |
| "C12": 50.0, |
| "C13": 33.3, |
| "C14": 10.0, |
| "S01": 18.2, |
| "S02": 27.3, |
| "S03": 45.5, |
| "S04": 41.7, |
| "S05": 23.1, |
| "S06": 20.0, |
| "S07": 33.3, |
| "S08": 44.4, |
| "S09": 33.3, |
| "S10": 41.7, |
| "S11": 46.7, |
| "S12": 30.8, |
| "S13": 42.1, |
| "S14": 20.0, |
| "L01": 12.5, |
| "L02": 40.7, |
| "L03": 27.0, |
| "L04": 40.0, |
| "L05": 17.9, |
| "L06": 0.0, |
| "L07": 25.0, |
| "F01": 60.9, |
| "F02": 55.6, |
| "F03": 75.0, |
| "F04": 28.6, |
| "F05": 50.0, |
| "F06": 85.7, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 70.0, |
| "F10": 63.6, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "mindbrush", |
| "name": "MindBrush", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 55, |
| "accuracy": { |
| "temporal": 43.5, |
| "causal": 33.9, |
| "spatial": 19.8, |
| "logical": 4.4, |
| "counterfactual": 36.0, |
| "hybrid": 0.0, |
| "single": 23.6, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.9, |
| "appearance_consistency": 61.2, |
| "visual_plausibility": 80.0 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 54.1, |
| "temporal_context_knowledge": 37.5, |
| "temporal_disciplinary_knowledge": 30.5, |
| "causal_common_sense_knowledge": 43.0, |
| "causal_context_knowledge": 13.2, |
| "causal_disciplinary_knowledge": 34.7, |
| "spatial_relation": 18.0, |
| "spatial_structure": 22.0, |
| "logical_explicit_rule_deduction": 4.9, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 44.3, |
| "counterfactual_anomaly_correction_and_generation": 16.7 |
| }, |
| "task_types": { |
| "T01": 50.0, |
| "T02": 55.6, |
| "T03": 46.2, |
| "T04": 55.0, |
| "T05": 75.0, |
| "T06": 71.4, |
| "T07": 25.0, |
| "T08": 45.5, |
| "T09": 33.3, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 50.0, |
| "T14": 33.3, |
| "T15": 41.7, |
| "T16": 27.8, |
| "T17": 40.0, |
| "T18": 25.0, |
| "T19": 0.0, |
| "C01": 51.6, |
| "C02": 44.4, |
| "C03": 28.6, |
| "C04": 10.0, |
| "C05": 12.5, |
| "C06": 10.0, |
| "C07": 20.0, |
| "C08": 25.0, |
| "C09": 52.6, |
| "C10": 66.7, |
| "C11": 66.7, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 27.3, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 25.0, |
| "S05": 15.4, |
| "S06": 13.3, |
| "S07": 11.1, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 25.0, |
| "S11": 33.3, |
| "S12": 11.5, |
| "S13": 23.5, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 11.1, |
| "L03": 5.4, |
| "L04": 2.9, |
| "L05": 2.6, |
| "L06": 5.6, |
| "L07": null, |
| "F01": 39.1, |
| "F02": 88.9, |
| "F03": 37.5, |
| "F04": 57.1, |
| "F05": 25.0, |
| "F06": 57.1, |
| "F07": 0.0, |
| "F08": 25.0, |
| "F09": 30.0, |
| "F10": 9.1, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "interleavethinker", |
| "name": "InterleaveThinker", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 56, |
| "accuracy": { |
| "temporal": 25.0, |
| "causal": 28.1, |
| "spatial": 19.2, |
| "logical": 0.6, |
| "counterfactual": 28.0, |
| "hybrid": 4.0, |
| "single": 17.8, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 36.9, |
| "appearance_consistency": 60.7, |
| "visual_plausibility": 82.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 34.1, |
| "temporal_context_knowledge": 12.5, |
| "temporal_disciplinary_knowledge": 16.9, |
| "causal_common_sense_knowledge": 30.4, |
| "causal_context_knowledge": 23.7, |
| "causal_disciplinary_knowledge": 28.0, |
| "spatial_relation": 16.0, |
| "spatial_structure": 23.2, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 24.3, |
| "counterfactual_anomaly_correction_and_generation": 36.7 |
| }, |
| "task_types": { |
| "T01": 25.0, |
| "T02": 33.3, |
| "T03": 38.5, |
| "T04": 45.0, |
| "T05": 25.0, |
| "T06": 42.9, |
| "T07": 25.0, |
| "T08": 18.2, |
| "T09": 8.3, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 25.0, |
| "T13": 50.0, |
| "T14": 11.1, |
| "T15": 0.0, |
| "T16": 16.7, |
| "T17": 20.0, |
| "T18": 0.0, |
| "T19": 66.7, |
| "C01": 29.0, |
| "C02": 37.0, |
| "C03": 23.8, |
| "C04": 10.0, |
| "C05": 12.5, |
| "C06": 20.0, |
| "C07": 50.0, |
| "C08": 25.0, |
| "C09": 47.4, |
| "C10": 41.7, |
| "C11": 0.0, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 18.2, |
| "S03": 27.3, |
| "S04": 16.7, |
| "S05": 23.1, |
| "S06": 20.0, |
| "S07": 11.1, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 37.5, |
| "S11": 46.7, |
| "S12": 11.5, |
| "S13": 0.0, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 26.1, |
| "F02": 11.1, |
| "F03": 62.5, |
| "F04": 28.6, |
| "F05": 0.0, |
| "F06": 14.3, |
| "F07": 0.0, |
| "F08": 50.0, |
| "F09": 30.0, |
| "F10": 36.4, |
| "F11": 44.4 |
| } |
| }, |
| { |
| "id": "intentedit", |
| "name": "IntentEdit", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 57, |
| "accuracy": { |
| "temporal": 22.6, |
| "causal": 24.0, |
| "spatial": 14.3, |
| "logical": 1.7, |
| "counterfactual": 14.0, |
| "hybrid": 0.0, |
| "single": 13.8, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 41.1, |
| "appearance_consistency": 58.3, |
| "visual_plausibility": 76.7 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 34.1, |
| "temporal_context_knowledge": 12.5, |
| "temporal_disciplinary_knowledge": 10.2, |
| "causal_common_sense_knowledge": 36.7, |
| "causal_context_knowledge": 7.9, |
| "causal_disciplinary_knowledge": 18.7, |
| "spatial_relation": 12.0, |
| "spatial_structure": 17.1, |
| "logical_explicit_rule_deduction": 0.8, |
| "logical_implicit_pattern_induction": 3.5, |
| "counterfactual_counterfactual_imagination": 15.7, |
| "counterfactual_anomaly_correction_and_generation": 10.0 |
| }, |
| "task_types": { |
| "T01": 12.5, |
| "T02": 77.8, |
| "T03": 23.1, |
| "T04": 60.0, |
| "T05": 0.0, |
| "T06": 57.1, |
| "T07": 0.0, |
| "T08": 18.2, |
| "T09": 8.3, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 25.0, |
| "T14": 22.2, |
| "T15": 25.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 35.5, |
| "C02": 29.6, |
| "C03": 47.6, |
| "C04": 10.0, |
| "C05": 0.0, |
| "C06": 0.0, |
| "C07": 20.0, |
| "C08": 12.5, |
| "C09": 31.6, |
| "C10": 25.0, |
| "C11": 33.3, |
| "C12": 25.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 9.1, |
| "S02": 9.1, |
| "S03": 18.2, |
| "S04": 8.3, |
| "S05": 23.1, |
| "S06": 0.0, |
| "S07": 16.7, |
| "S08": 11.1, |
| "S09": null, |
| "S10": 25.0, |
| "S11": 6.7, |
| "S12": 15.4, |
| "S13": 17.6, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 2.9, |
| "L05": 5.1, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 17.4, |
| "F02": 11.1, |
| "F03": 12.5, |
| "F04": 42.9, |
| "F05": 0.0, |
| "F06": 28.6, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 18.2, |
| "F11": 11.1 |
| } |
| }, |
| { |
| "id": "imagent", |
| "name": "ImAgent", |
| "group": "agentic", |
| "multi_image": false, |
| "source_order": 58, |
| "accuracy": { |
| "temporal": 4.2, |
| "causal": 3.6, |
| "spatial": 2.2, |
| "logical": 0.0, |
| "counterfactual": 2.0, |
| "hybrid": 0.0, |
| "single": 2.2, |
| "multi": null, |
| "total": null |
| }, |
| "metrics": { |
| "instruction_reasoning": 24.2, |
| "appearance_consistency": 23.3, |
| "visual_plausibility": 65.1 |
| }, |
| "subcategories": { |
| "temporal_common_sense_knowledge": 7.1, |
| "temporal_context_knowledge": 4.2, |
| "temporal_disciplinary_knowledge": 0.0, |
| "causal_common_sense_knowledge": 6.3, |
| "causal_context_knowledge": 2.6, |
| "causal_disciplinary_knowledge": 1.3, |
| "spatial_relation": 1.0, |
| "spatial_structure": 3.7, |
| "logical_explicit_rule_deduction": 0.0, |
| "logical_implicit_pattern_induction": 0.0, |
| "counterfactual_counterfactual_imagination": 1.4, |
| "counterfactual_anomaly_correction_and_generation": 3.3 |
| }, |
| "task_types": { |
| "T01": 12.5, |
| "T02": 0.0, |
| "T03": 7.7, |
| "T04": 0.0, |
| "T05": 0.0, |
| "T06": 14.3, |
| "T07": 25.0, |
| "T08": 9.1, |
| "T09": 0.0, |
| "T10": 0.0, |
| "T11": null, |
| "T12": 0.0, |
| "T13": 0.0, |
| "T14": 0.0, |
| "T15": 0.0, |
| "T16": 0.0, |
| "T17": 0.0, |
| "T18": 0.0, |
| "T19": 0.0, |
| "C01": 9.7, |
| "C02": 3.7, |
| "C03": 4.8, |
| "C04": 0.0, |
| "C05": 12.5, |
| "C06": 0.0, |
| "C07": 0.0, |
| "C08": 4.2, |
| "C09": 0.0, |
| "C10": 0.0, |
| "C11": 0.0, |
| "C12": 0.0, |
| "C13": 0.0, |
| "C14": 0.0, |
| "S01": 0.0, |
| "S02": 0.0, |
| "S03": 0.0, |
| "S04": 0.0, |
| "S05": 7.7, |
| "S06": 0.0, |
| "S07": 0.0, |
| "S08": 0.0, |
| "S09": null, |
| "S10": 4.2, |
| "S11": 0.0, |
| "S12": 3.8, |
| "S13": 5.9, |
| "S14": null, |
| "L01": 0.0, |
| "L02": 0.0, |
| "L03": 0.0, |
| "L04": 0.0, |
| "L05": 0.0, |
| "L06": 0.0, |
| "L07": null, |
| "F01": 4.3, |
| "F02": 0.0, |
| "F03": 0.0, |
| "F04": 0.0, |
| "F05": 0.0, |
| "F06": 0.0, |
| "F07": 0.0, |
| "F08": 0.0, |
| "F09": 0.0, |
| "F10": 9.1, |
| "F11": 0.0 |
| } |
| } |
| ] |
| } |
| } |
| }, |
| { |
| "id": "risebench", |
| "name": "RISEBench", |
| "case_count": 360, |
| "available_result_languages": [ |
| "en" |
| ], |
| "accuracy_unit": "%", |
| "metric_unit": "/100", |
| "score_decimals": 1, |
| "default_sort": "total", |
| "dimensions": [ |
| { |
| "key": "temporal", |
| "label": "Temporal", |
| "description": "Infer how a scene changes over time." |
| }, |
| { |
| "key": "causal", |
| "label": "Causal", |
| "description": "Reason about causes, actions, and their consequences." |
| }, |
| { |
| "key": "spatial", |
| "label": "Spatial", |
| "description": "Reason about spatial relationships and transformations." |
| }, |
| { |
| "key": "logical", |
| "label": "Logical", |
| "description": "Apply explicit rules, patterns, and logical constraints." |
| } |
| ], |
| "metrics": [ |
| { |
| "key": "instruction_reasoning", |
| "label": "Instruction Reasoning", |
| "description": "Whether the edit realizes the intended reasoning outcome." |
| }, |
| { |
| "key": "appearance_consistency", |
| "label": "Appearance Consistency", |
| "description": "Whether content that should remain unchanged is preserved." |
| }, |
| { |
| "key": "visual_plausibility", |
| "label": "Visual Plausibility", |
| "description": "Visual quality and plausibility; logical tasks are excluded." |
| } |
| ], |
| "accuracy_columns": [ |
| { |
| "key": "temporal", |
| "label": "Temporal", |
| "description": "Infer how a scene changes over time." |
| }, |
| { |
| "key": "causal", |
| "label": "Causal", |
| "description": "Reason about causes, actions, and their consequences." |
| }, |
| { |
| "key": "spatial", |
| "label": "Spatial", |
| "description": "Reason about spatial relationships and transformations." |
| }, |
| { |
| "key": "logical", |
| "label": "Logical", |
| "description": "Apply explicit rules, patterns, and logical constraints." |
| }, |
| { |
| "key": "total", |
| "label": "Overall", |
| "description": "Accuracy on the complete RISEBench-360 benchmark." |
| } |
| ], |
| "links": { |
| "paper": "https://arxiv.org/abs/2504.02826", |
| "data": "https://huggingface.co/datasets/PhoenixZ/RISEBench", |
| "outputs": "https://huggingface.co/datasets/zpy777/RISEBench_Outputs", |
| "github": "https://github.com/VisionXLab/RISEBench/tree/main/RISEBench" |
| }, |
| "judges": { |
| "instruction_reasoning": "GPT-4o", |
| "appearance_consistency": "GPT-4o", |
| "visual_plausibility": "GPT-4o" |
| }, |
| "results_by_language": { |
| "en": { |
| "language": "Original published results", |
| "language_code": "en", |
| "model_count": 20, |
| "groups": [], |
| "models": [ |
| { |
| "id": "gpt-image-1-5", |
| "name": "GPT-Image-1.5", |
| "group": null, |
| "multi_image": null, |
| "source_order": 1, |
| "accuracy": { |
| "temporal": 57.6, |
| "causal": 62.2, |
| "spatial": 62.0, |
| "logical": 21.2, |
| "total": 51.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 69.7, |
| "appearance_consistency": 92.5, |
| "visual_plausibility": 94.9 |
| } |
| }, |
| { |
| "id": "gpt-image-2", |
| "name": "GPT-Image-2", |
| "group": null, |
| "multi_image": null, |
| "source_order": 2, |
| "accuracy": { |
| "temporal": 45.9, |
| "causal": 66.7, |
| "spatial": 50.0, |
| "logical": 34.1, |
| "total": 49.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 73.8, |
| "appearance_consistency": 89.3, |
| "visual_plausibility": 94.9 |
| } |
| }, |
| { |
| "id": "gemini-3-pro-image-preview-nano-banana-pro", |
| "name": "Gemini-3-pro-image-preview (Nano Banana-pro)", |
| "group": null, |
| "multi_image": null, |
| "source_order": 3, |
| "accuracy": { |
| "temporal": 43.5, |
| "causal": 63.3, |
| "spatial": 48.0, |
| "logical": 37.6, |
| "total": 48.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 77.0, |
| "appearance_consistency": 85.5, |
| "visual_plausibility": 94.4 |
| } |
| }, |
| { |
| "id": "gemini-2-5-flash-image-nano-banana", |
| "name": "Gemini-2.5-Flash-Image (Nano Banana)", |
| "group": null, |
| "multi_image": null, |
| "source_order": 4, |
| "accuracy": { |
| "temporal": 29.4, |
| "causal": 48.9, |
| "spatial": 37.0, |
| "logical": 18.8, |
| "total": 33.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 61.2, |
| "appearance_consistency": 86.0, |
| "visual_plausibility": 91.3 |
| } |
| }, |
| { |
| "id": "gpt-image-1", |
| "name": "GPT-Image-1", |
| "group": null, |
| "multi_image": null, |
| "source_order": 5, |
| "accuracy": { |
| "temporal": 36.5, |
| "causal": 34.4, |
| "spatial": 37.0, |
| "logical": 10.6, |
| "total": 30.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 62.8, |
| "appearance_consistency": 80.2, |
| "visual_plausibility": 94.9 |
| } |
| }, |
| { |
| "id": "gpt-image-1-mini", |
| "name": "GPT-Image-1-mini", |
| "group": null, |
| "multi_image": null, |
| "source_order": 6, |
| "accuracy": { |
| "temporal": 25.9, |
| "causal": 31.1, |
| "spatial": 33.0, |
| "logical": 9.4, |
| "total": 25.3 |
| }, |
| "metrics": { |
| "instruction_reasoning": 54.1, |
| "appearance_consistency": 71.5, |
| "visual_plausibility": 93.7 |
| } |
| }, |
| { |
| "id": "qwen-image-edit-2511", |
| "name": "Qwen-Image-Edit-2511", |
| "group": null, |
| "multi_image": null, |
| "source_order": 7, |
| "accuracy": { |
| "temporal": 21.2, |
| "causal": 18.9, |
| "spatial": 31.0, |
| "logical": 4.7, |
| "total": 19.4 |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.9, |
| "appearance_consistency": 71.0, |
| "visual_plausibility": 91.5 |
| } |
| }, |
| { |
| "id": "bagel-w-cot", |
| "name": "BAGEL (w/ CoT)", |
| "group": null, |
| "multi_image": null, |
| "source_order": 8, |
| "accuracy": { |
| "temporal": 11.8, |
| "causal": 27.8, |
| "spatial": 21.0, |
| "logical": 1.2, |
| "total": 15.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 47.6, |
| "appearance_consistency": 75.6, |
| "visual_plausibility": 81.7 |
| } |
| }, |
| { |
| "id": "gemini-2-0-flash-exp", |
| "name": "Gemini-2.0-Flash-exp", |
| "group": null, |
| "multi_image": null, |
| "source_order": 9, |
| "accuracy": { |
| "temporal": 9.4, |
| "causal": 16.7, |
| "spatial": 23.0, |
| "logical": 4.7, |
| "total": 13.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 48.9, |
| "appearance_consistency": 68.2, |
| "visual_plausibility": 82.7 |
| } |
| }, |
| { |
| "id": "seedream-4-0", |
| "name": "Seedream-4.0", |
| "group": null, |
| "multi_image": null, |
| "source_order": 10, |
| "accuracy": { |
| "temporal": 17.6, |
| "causal": 13.3, |
| "spatial": 11.0, |
| "logical": 7.1, |
| "total": 12.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 58.9, |
| "appearance_consistency": 67.4, |
| "visual_plausibility": 91.2 |
| } |
| }, |
| { |
| "id": "gemini-2-0-flash-pre", |
| "name": "Gemini-2.0-Flash-pre", |
| "group": null, |
| "multi_image": null, |
| "source_order": 11, |
| "accuracy": { |
| "temporal": 11.8, |
| "causal": 14.4, |
| "spatial": 11.0, |
| "logical": 2.4, |
| "total": 10.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 49.9, |
| "appearance_consistency": 68.4, |
| "visual_plausibility": 84.9 |
| } |
| }, |
| { |
| "id": "qwen-image-edit-2509", |
| "name": "Qwen-Image-Edit-2509", |
| "group": null, |
| "multi_image": null, |
| "source_order": 12, |
| "accuracy": { |
| "temporal": 4.7, |
| "causal": 11.1, |
| "spatial": 17.0, |
| "logical": 2.4, |
| "total": 9.2 |
| }, |
| "metrics": { |
| "instruction_reasoning": 37.2, |
| "appearance_consistency": 66.4, |
| "visual_plausibility": 86.9 |
| } |
| }, |
| { |
| "id": "bagel", |
| "name": "BAGEL", |
| "group": null, |
| "multi_image": null, |
| "source_order": 13, |
| "accuracy": { |
| "temporal": 3.5, |
| "causal": 4.4, |
| "spatial": 14.0, |
| "logical": 0.0, |
| "total": 5.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 36.4, |
| "appearance_consistency": 58.7, |
| "visual_plausibility": 72.0 |
| } |
| }, |
| { |
| "id": "flux-1-kontext-dev", |
| "name": "FLUX.1-Kontext-Dev", |
| "group": null, |
| "multi_image": null, |
| "source_order": 14, |
| "accuracy": { |
| "temporal": 2.3, |
| "causal": 5.5, |
| "spatial": 13.0, |
| "logical": 1.2, |
| "total": 5.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 26.0, |
| "appearance_consistency": 71.6, |
| "visual_plausibility": 85.2 |
| } |
| }, |
| { |
| "id": "ovis-u1", |
| "name": "Ovis-U1", |
| "group": null, |
| "multi_image": null, |
| "source_order": 15, |
| "accuracy": { |
| "temporal": 1.1, |
| "causal": 3.3, |
| "spatial": 4.0, |
| "logical": 2.4, |
| "total": 2.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 33.9, |
| "appearance_consistency": 52.7, |
| "visual_plausibility": 72.9 |
| } |
| }, |
| { |
| "id": "step1x-edit", |
| "name": "Step1X-Edit", |
| "group": null, |
| "multi_image": null, |
| "source_order": 16, |
| "accuracy": { |
| "temporal": 0.0, |
| "causal": 2.2, |
| "spatial": 2.0, |
| "logical": 3.5, |
| "total": 1.9 |
| }, |
| "metrics": { |
| "instruction_reasoning": 25.1, |
| "appearance_consistency": 41.5, |
| "visual_plausibility": 73.5 |
| } |
| }, |
| { |
| "id": "omnigen", |
| "name": "OmniGen", |
| "group": null, |
| "multi_image": null, |
| "source_order": 17, |
| "accuracy": { |
| "temporal": 1.2, |
| "causal": 1.1, |
| "spatial": 0.0, |
| "logical": 1.2, |
| "total": 0.8 |
| }, |
| "metrics": { |
| "instruction_reasoning": 22.0, |
| "appearance_consistency": 32.6, |
| "visual_plausibility": 55.3 |
| } |
| }, |
| { |
| "id": "emu2", |
| "name": "EMU2", |
| "group": null, |
| "multi_image": null, |
| "source_order": 18, |
| "accuracy": { |
| "temporal": 1.2, |
| "causal": 1.1, |
| "spatial": 0.0, |
| "logical": 0.0, |
| "total": 0.5 |
| }, |
| "metrics": { |
| "instruction_reasoning": 22.6, |
| "appearance_consistency": 38.2, |
| "visual_plausibility": 78.3 |
| } |
| }, |
| { |
| "id": "hidream-edit", |
| "name": "HiDream-Edit", |
| "group": null, |
| "multi_image": null, |
| "source_order": 19, |
| "accuracy": { |
| "temporal": 0.0, |
| "causal": 0.0, |
| "spatial": 0.0, |
| "logical": 0.0, |
| "total": 0.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 30.3, |
| "appearance_consistency": 12.6, |
| "visual_plausibility": 74.9 |
| } |
| }, |
| { |
| "id": "flux-1-canny", |
| "name": "FLUX.1-Canny", |
| "group": null, |
| "multi_image": null, |
| "source_order": 20, |
| "accuracy": { |
| "temporal": 0.0, |
| "causal": 0.0, |
| "spatial": 0.0, |
| "logical": 0.0, |
| "total": 0.0 |
| }, |
| "metrics": { |
| "instruction_reasoning": 20.2, |
| "appearance_consistency": 13.1, |
| "visual_plausibility": 77.5 |
| } |
| } |
| ] |
| } |
| } |
| } |
| ] |
| } |
|
|
