Spaces:
Running
Running
| { | |
| "Mistral-3.1-24B-2503": { | |
| "comprehension_score": 4.707142857142857, | |
| "structure_score": 4.796428571428572, | |
| "prose_style_score": 4.2178571428571425, | |
| "creativity_score": 3.914285714285714, | |
| "depth_score": 3.9035714285714285, | |
| "helpfulness_score": 4.242857142857143, | |
| "overall_score": 4.203571428571428 | |
| }, | |
| "Phi-4-14B": { | |
| "comprehension_score": 4.735714285714286, | |
| "structure_score": 4.889285714285714, | |
| "prose_style_score": 4.460714285714285, | |
| "creativity_score": 4.242857142857143, | |
| "depth_score": 4.178571428571429, | |
| "helpfulness_score": 4.317857142857143, | |
| "overall_score": 4.296428571428572 | |
| }, | |
| "gpt-4o-mini-2024-07-18": { | |
| "comprehension_score": 4.760714285714286, | |
| "structure_score": 4.9, | |
| "prose_style_score": 4.542857142857143, | |
| "creativity_score": 4.289285714285715, | |
| "depth_score": 4.082142857142857, | |
| "helpfulness_score": 4.35, | |
| "overall_score": 4.321428571428571 | |
| }, | |
| "gpt-4.1-mini-2025-04-14": { | |
| "comprehension_score": 5.042857142857143, | |
| "structure_score": 4.935714285714286, | |
| "prose_style_score": 4.675, | |
| "creativity_score": 4.335714285714285, | |
| "depth_score": 4.2, | |
| "helpfulness_score": 4.564285714285714, | |
| "overall_score": 4.435714285714286 | |
| }, | |
| "Qwen3-30B-A3B": { | |
| "comprehension_score": 5.146428571428571, | |
| "structure_score": 5.289285714285715, | |
| "prose_style_score": 4.853571428571429, | |
| "creativity_score": 4.714285714285714, | |
| "depth_score": 4.5321428571428575, | |
| "helpfulness_score": 4.925, | |
| "overall_score": 4.814285714285714 | |
| }, | |
| "Qwen3-8B": { | |
| "comprehension_score": 5.146428571428571, | |
| "structure_score": 5.260714285714286, | |
| "prose_style_score": 4.910714285714286, | |
| "creativity_score": 4.689285714285714, | |
| "depth_score": 4.496428571428571, | |
| "helpfulness_score": 4.8464285714285715, | |
| "overall_score": 4.817857142857143 | |
| }, | |
| "gpt-4o-2024-11-20": { | |
| "comprehension_score": 5.2785714285714285, | |
| "structure_score": 5.3464285714285715, | |
| "prose_style_score": 5.207142857142857, | |
| "creativity_score": 5.082142857142857, | |
| "depth_score": 4.746428571428571, | |
| "helpfulness_score": 5.010714285714286, | |
| "overall_score": 4.985714285714286 | |
| }, | |
| "gemma3-27b": { | |
| "comprehension_score": 5.428571428571429, | |
| "structure_score": 5.535714285714286, | |
| "prose_style_score": 5.0285714285714285, | |
| "creativity_score": 5.121428571428571, | |
| "depth_score": 4.8464285714285715, | |
| "helpfulness_score": 5.2178571428571425, | |
| "overall_score": 5.082142857142857 | |
| }, | |
| "Qwen3-32B": { | |
| "comprehension_score": 5.457142857142857, | |
| "structure_score": 5.628571428571429, | |
| "prose_style_score": 5.285714285714286, | |
| "creativity_score": 5.078571428571428, | |
| "depth_score": 4.882142857142857, | |
| "helpfulness_score": 5.314285714285714, | |
| "overall_score": 5.2214285714285715 | |
| }, | |
| "Mistral-3.2-24B-2506": { | |
| "comprehension_score": 5.5321428571428575, | |
| "structure_score": 5.817857142857143, | |
| "prose_style_score": 5.5321428571428575, | |
| "creativity_score": 5.607142857142857, | |
| "depth_score": 5.010714285714286, | |
| "helpfulness_score": 5.3464285714285715, | |
| "overall_score": 5.3464285714285715 | |
| }, | |
| "o4-mini-2025-04-16": { | |
| "comprehension_score": 5.803571428571429, | |
| "structure_score": 5.696428571428571, | |
| "prose_style_score": 5.589285714285714, | |
| "creativity_score": 5.442857142857143, | |
| "depth_score": 5.1, | |
| "helpfulness_score": 5.582142857142857, | |
| "overall_score": 5.542857142857143 | |
| }, | |
| "Qwen3-235B": { | |
| "comprehension_score": 5.735714285714286, | |
| "structure_score": 5.875, | |
| "prose_style_score": 5.628571428571429, | |
| "creativity_score": 5.514285714285714, | |
| "depth_score": 5.214285714285714, | |
| "helpfulness_score": 5.55, | |
| "overall_score": 5.5928571428571425 | |
| }, | |
| "Gemini-2.5-Flash": { | |
| "comprehension_score": 6.196428571428571, | |
| "structure_score": 6.2214285714285715, | |
| "prose_style_score": 6.0, | |
| "creativity_score": 5.828571428571428, | |
| "depth_score": 5.75, | |
| "helpfulness_score": 6.0321428571428575, | |
| "overall_score": 6.007142857142857 | |
| }, | |
| "Qwen3-30B-A3B-Thinking": { | |
| "comprehension_score": 5.914285714285715, | |
| "structure_score": 6.053571428571429, | |
| "prose_style_score": 6.5321428571428575, | |
| "creativity_score": 6.5285714285714285, | |
| "depth_score": 5.65, | |
| "helpfulness_score": 5.817857142857143, | |
| "overall_score": 6.064285714285714 | |
| }, | |
| "Deepseek-V3-0324": { | |
| "comprehension_score": 6.082142857142857, | |
| "structure_score": 6.242857142857143, | |
| "prose_style_score": 6.560714285714286, | |
| "creativity_score": 6.610714285714286, | |
| "depth_score": 5.796428571428572, | |
| "helpfulness_score": 5.957142857142857, | |
| "overall_score": 6.203571428571428 | |
| }, | |
| "Qwen3-32B-Thinking": { | |
| "comprehension_score": 6.339285714285714, | |
| "structure_score": 6.425, | |
| "prose_style_score": 7.089285714285714, | |
| "creativity_score": 7.185714285714286, | |
| "depth_score": 6.192857142857143, | |
| "helpfulness_score": 6.182142857142857, | |
| "overall_score": 6.578571428571428 | |
| }, | |
| "Qwen3-235B-Thinking": { | |
| "comprehension_score": 6.385714285714286, | |
| "structure_score": 6.45, | |
| "prose_style_score": 7.296428571428572, | |
| "creativity_score": 7.435714285714286, | |
| "depth_score": 6.321428571428571, | |
| "helpfulness_score": 6.285714285714286, | |
| "overall_score": 6.660714285714286 | |
| }, | |
| "Deepseek-R1-0528": { | |
| "comprehension_score": 6.7178571428571425, | |
| "structure_score": 6.703571428571428, | |
| "prose_style_score": 7.0964285714285715, | |
| "creativity_score": 7.021428571428571, | |
| "depth_score": 6.5964285714285715, | |
| "helpfulness_score": 6.575, | |
| "overall_score": 6.771428571428571 | |
| }, | |
| "o3-2025-04-16": { | |
| "comprehension_score": 6.914285714285715, | |
| "structure_score": 6.746428571428571, | |
| "prose_style_score": 7.05, | |
| "creativity_score": 6.896428571428571, | |
| "depth_score": 6.439285714285714, | |
| "helpfulness_score": 6.742857142857143, | |
| "overall_score": 6.946428571428571 | |
| }, | |
| "gpt-5.4": { | |
| "comprehension_score": 7.035714285714286, | |
| "structure_score": 6.975, | |
| "prose_style_score": 7.128571428571429, | |
| "creativity_score": 6.9035714285714285, | |
| "depth_score": 6.760714285714286, | |
| "helpfulness_score": 7.025, | |
| "overall_score": 7.060714285714286 | |
| }, | |
| "Gemini-3.1-Flash": { | |
| "comprehension_score": 6.414285714285715, | |
| "structure_score": 6.625, | |
| "prose_style_score": 6.75, | |
| "creativity_score": 6.660714285714286, | |
| "depth_score": 6.057142857142857, | |
| "helpfulness_score": 6.414285714285715, | |
| "overall_score": 6.5285714285714285 | |
| }, | |
| "Gemini-3.1-Pro": { | |
| "comprehension_score": 6.767857142857143, | |
| "structure_score": 6.867857142857143, | |
| "prose_style_score": 7.114285714285714, | |
| "creativity_score": 6.875, | |
| "depth_score": 6.325, | |
| "helpfulness_score": 6.757142857142857, | |
| "overall_score": 6.864285714285714 | |
| }, | |
| "MiniMax-M2.5": { | |
| "comprehension_score": 6.364285714285714, | |
| "structure_score": 6.428571428571429, | |
| "prose_style_score": 6.021428571428571, | |
| "creativity_score": 6.075, | |
| "depth_score": 5.853571428571429, | |
| "helpfulness_score": 6.275, | |
| "overall_score": 6.260714285714286 | |
| }, | |
| "Qwen3.5-Plus": { | |
| "comprehension_score": 6.7821428571428575, | |
| "structure_score": 6.75, | |
| "prose_style_score": 6.925, | |
| "creativity_score": 6.735714285714286, | |
| "depth_score": 6.296428571428572, | |
| "helpfulness_score": 6.714285714285714, | |
| "overall_score": 6.796428571428572 | |
| }, | |
| "GLM-5": { | |
| "comprehension_score": 6.410714285714286, | |
| "structure_score": 6.5285714285714285, | |
| "prose_style_score": 6.689285714285714, | |
| "creativity_score": 6.507142857142857, | |
| "depth_score": 5.996428571428571, | |
| "helpfulness_score": 6.360714285714286, | |
| "overall_score": 6.492857142857143 | |
| }, | |
| "step-3.5-flash": { | |
| "comprehension_score": 6.696428571428571, | |
| "structure_score": 6.814285714285714, | |
| "prose_style_score": 7.175, | |
| "creativity_score": 7.260714285714286, | |
| "depth_score": 6.714285714285714, | |
| "helpfulness_score": 6.628571428571429, | |
| "overall_score": 6.828571428571428 | |
| } | |
| } |