Code4Scene / data /leaderboard-details.json
KoeYe's picture
Unify task examples, add chart tooltips and bound scene loading
7d419bd
Raw History Blame Contribute Delete
30.3 kB
{
"overall": [
{
"key": "astra",
"name": "GPT-6 Astra (max)",
"provider": "OpenAI",
"metrics": [
{
"label": "Overall",
"value": 0.6193352866666667,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.72382,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.5148505733333334,
"currency": false
},
{
"label": "Mean cost / case",
"value": 12.896991822966507,
"currency": true
}
]
},
{
"key": "gemini",
"name": "Gemini 3.8 Flash (high)",
"provider": "Google",
"metrics": [
{
"label": "Overall",
"value": 0.6189750266666667,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.65689,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.5810600533333334,
"currency": false
},
{
"label": "Mean cost / case",
"value": 1.9235185771258503,
"currency": true
}
]
},
{
"key": "fable",
"name": "Claude Fable 5.1 (max)",
"provider": "Anthropic",
"metrics": [
{
"label": "Overall",
"value": 0.60604898,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.78775,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.4243479600000001,
"currency": false
},
{
"label": "Mean cost / case",
"value": 10.623258766403161,
"currency": true
}
]
},
{
"key": "opus",
"name": "Claude Opus 5 (max)",
"provider": "Anthropic",
"metrics": [
{
"label": "Overall",
"value": 0.5931299933333334,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.7181599999999999,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.46809998666666675,
"currency": false
},
{
"label": "Mean cost / case",
"value": 19.47789116793412,
"currency": true
}
]
},
{
"key": "sol",
"name": "GPT-5.6 Sol (high)",
"provider": "OpenAI",
"metrics": [
{
"label": "Overall",
"value": 0.5499994666666667,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.70704,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.3929589333333333,
"currency": false
},
{
"label": "Mean cost / case",
"value": 2.9749956842592593,
"currency": true
}
]
},
{
"key": "muse",
"name": "Muse Spark 1.3 (medium)",
"provider": "Meta",
"metrics": [
{
"label": "Overall",
"value": 0.5022053666666666,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.646195,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.35821573333333334,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.0861066423076923,
"currency": true
}
]
},
{
"key": "glm",
"name": "GLM-5.3 Flash (max)",
"provider": "Z.ai",
"metrics": [
{
"label": "Overall",
"value": 0.4147088666666666,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.5094299999999999,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.3199877333333333,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.40130584861111107,
"currency": true
}
]
},
{
"key": "qwen-off",
"name": "Qwen 3.8 27B (thinking off)",
"provider": "Alibaba",
"metrics": [
{
"label": "Overall",
"value": 0.37818169333333335,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.55666,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.19970338666666668,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.38413493183103564,
"currency": true
}
]
},
{
"key": "grok",
"name": "Grok 4.6 (high)",
"provider": "xAI",
"metrics": [
{
"label": "Overall",
"value": 0.37567506,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.56721,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.18414012,
"currency": false
},
{
"label": "Mean cost / case",
"value": 2.2948689296296294,
"currency": true
}
]
},
{
"key": "qwen-on",
"name": "Qwen 3.8 27B (thinking on)",
"provider": "Alibaba",
"metrics": [
{
"label": "Overall",
"value": 0.37094399333333333,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.51571,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.2261779866666667,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.29748765575757574,
"currency": true
}
]
},
{
"key": "inkling",
"name": "Inkling (high)",
"provider": "Thinking Machines",
"metrics": [
{
"label": "Overall",
"value": 0.31150237333333336,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.42498500000000006,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.19801974666666666,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.4783280191269841,
"currency": true
}
]
},
{
"key": "gemma-on",
"name": "Gemma 4 31B (thinking on)",
"provider": "Google",
"metrics": [
{
"label": "Overall",
"value": 0.29812257999999997,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.470705,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.12554015999999998,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.026867125396825398,
"currency": true
}
]
},
{
"key": "gemma-off",
"name": "Gemma 4 31B (thinking off)",
"provider": "Google",
"metrics": [
{
"label": "Overall",
"value": 0.28498897333333334,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.45494,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.11503794666666667,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.017148714965986397,
"currency": true
}
]
},
{
"key": "deepseek",
"name": "DeepSeek V4.1 Flash (high)",
"provider": "DeepSeek",
"metrics": [
{
"label": "Overall",
"value": 0.22658958,
"currency": false
},
{
"label": "Text-to-Scene",
"value": 0.24269,
"currency": false
},
{
"label": "Image-to-Scene",
"value": 0.21048916,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.1240297601010101,
"currency": true
}
]
}
],
"t2s": [
{
"key": "fable",
"name": "Claude Fable 5.1 (max)",
"provider": "Anthropic",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.78775,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.7253149999999999,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.7717050000000001,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.898,
"currency": false
},
{
"label": "Mean cost / case",
"value": 18.1576316,
"currency": true
}
]
},
{
"key": "astra",
"name": "GPT-6 Astra (max)",
"provider": "OpenAI",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.72382,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.707165,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.733235,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.712,
"currency": false
},
{
"label": "Mean cost / case",
"value": 22.472260736842106,
"currency": true
}
]
},
{
"key": "opus",
"name": "Claude Opus 5 (max)",
"provider": "Anthropic",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.7181599999999999,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.63106,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.71617,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.811,
"currency": false
},
{
"label": "Mean cost / case",
"value": 34.49611078947368,
"currency": true
}
]
},
{
"key": "sol",
"name": "GPT-5.6 Sol (high)",
"provider": "OpenAI",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.70704,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.63186,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.710485,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.772,
"currency": false
},
{
"label": "Mean cost / case",
"value": 4.07260365,
"currency": true
}
]
},
{
"key": "gemini",
"name": "Gemini 3.8 Flash (high)",
"provider": "Google",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.65689,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.6369100000000001,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.66406,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.655,
"currency": false
},
{
"label": "Mean cost / case",
"value": 2.49471265,
"currency": true
}
]
},
{
"key": "muse",
"name": "Muse Spark 1.3 (medium)",
"provider": "Meta",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.646195,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.5981099999999999,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.660675,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.651,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.10048539999999999,
"currency": true
}
]
},
{
"key": "grok",
"name": "Grok 4.6 (high)",
"provider": "xAI",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.56721,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.52211,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.5764199999999999,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.585,
"currency": false
},
{
"label": "Mean cost / case",
"value": 4.326270533333333,
"currency": true
}
]
},
{
"key": "qwen-off",
"name": "Qwen 3.8 27B (thinking off)",
"provider": "Alibaba",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.55666,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.506755,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.529525,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.688,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.49154169999999997,
"currency": true
}
]
},
{
"key": "qwen-on",
"name": "Qwen 3.8 27B (thinking on)",
"provider": "Alibaba",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.51571,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.50522,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.45978,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.694,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.3344125,
"currency": true
}
]
},
{
"key": "glm",
"name": "GLM-5.3 Flash (max)",
"provider": "Z.ai",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.5094299999999999,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.403365,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.537015,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.533,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.710521125,
"currency": true
}
]
},
{
"key": "gemma-on",
"name": "Gemma 4 31B (thinking on)",
"provider": "Google",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.470705,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.4117,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.41593,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.694,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.0253001,
"currency": true
}
]
},
{
"key": "gemma-off",
"name": "Gemma 4 31B (thinking off)",
"provider": "Google",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.45494,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.43810000000000004,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.370465,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.725,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.0151612,
"currency": true
}
]
},
{
"key": "inkling",
"name": "Inkling (high)",
"provider": "Thinking Machines",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.42498500000000006,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.392605,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.336705,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.722,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.20252835,
"currency": true
}
]
},
{
"key": "deepseek",
"name": "DeepSeek V4.1 Flash (high)",
"provider": "DeepSeek",
"metrics": [
{
"label": "Text-to-Scene",
"value": 0.24269,
"currency": false
},
{
"label": "Detailed Alignment",
"value": 0.216595,
"currency": false
},
{
"label": "Overview Alignment",
"value": 0.16134500000000002,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.513,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.193865,
"currency": true
}
]
}
],
"i2s": [
{
"key": "gemini",
"name": "Gemini 3.8 Flash (high)",
"provider": "Google",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.5810600533333334,
"currency": false
},
{
"label": "Repair F1",
"value": 0.527,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.796,
"currency": false
},
{
"label": "Indoor",
"value": 0.71653332,
"currency": false
},
{
"label": "Outdoor",
"value": 0.5133234200000001,
"currency": false
},
{
"label": "Mean cost / case",
"value": 1.3523245042517007,
"currency": true
}
]
},
{
"key": "astra",
"name": "GPT-6 Astra (max)",
"provider": "OpenAI",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.5148505733333334,
"currency": false
},
{
"label": "Repair F1",
"value": 0.445,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.796,
"currency": false
},
{
"label": "Indoor",
"value": 0.78546656,
"currency": false
},
{
"label": "Outdoor",
"value": 0.37954258,
"currency": false
},
{
"label": "Mean cost / case",
"value": 3.3217229090909095,
"currency": true
}
]
},
{
"key": "opus",
"name": "Claude Opus 5 (max)",
"provider": "Anthropic",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.46809998666666675,
"currency": false
},
{
"label": "Repair F1",
"value": 0.389,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.786,
"currency": false
},
{
"label": "Indoor",
"value": 0.61843384,
"currency": false
},
{
"label": "Outdoor",
"value": 0.39293306,
"currency": false
},
{
"label": "Mean cost / case",
"value": 4.459671546394558,
"currency": true
}
]
},
{
"key": "fable",
"name": "Claude Fable 5.1 (max)",
"provider": "Anthropic",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.4243479600000001,
"currency": false
},
{
"label": "Repair F1",
"value": 0.332,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.795,
"currency": false
},
{
"label": "Indoor",
"value": 0.53523332,
"currency": false
},
{
"label": "Outdoor",
"value": 0.36890528000000006,
"currency": false
},
{
"label": "Mean cost / case",
"value": 3.0888859328063245,
"currency": true
}
]
},
{
"key": "sol",
"name": "GPT-5.6 Sol (high)",
"provider": "OpenAI",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.3929589333333333,
"currency": false
},
{
"label": "Repair F1",
"value": 0.319,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.689,
"currency": false
},
{
"label": "Indoor",
"value": 0.49742972,
"currency": false
},
{
"label": "Outdoor",
"value": 0.34072354,
"currency": false
},
{
"label": "Mean cost / case",
"value": 1.8773877185185188,
"currency": true
}
]
},
{
"key": "muse",
"name": "Muse Spark 1.3 (medium)",
"provider": "Meta",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.35821573333333334,
"currency": false
},
{
"label": "Repair F1",
"value": 0.246,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.807,
"currency": false
},
{
"label": "Indoor",
"value": 0.63253332,
"currency": false
},
{
"label": "Outdoor",
"value": 0.22105694,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.07172788461538461,
"currency": true
}
]
},
{
"key": "glm",
"name": "GLM-5.3 Flash (max)",
"provider": "Z.ai",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.3199877333333333,
"currency": false
},
{
"label": "Repair F1",
"value": 0.188,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.848,
"currency": false
},
{
"label": "Indoor",
"value": 0.46533411999999996,
"currency": false
},
{
"label": "Outdoor",
"value": 0.24731454,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.09209057222222222,
"currency": true
}
]
},
{
"key": "qwen-on",
"name": "Qwen 3.8 27B (thinking on)",
"provider": "Alibaba",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.2261779866666667,
"currency": false
},
{
"label": "Repair F1",
"value": 0.118,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.66,
"currency": false
},
{
"label": "Indoor",
"value": 0.29651112,
"currency": false
},
{
"label": "Outdoor",
"value": 0.19101142,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.2605628115151515,
"currency": true
}
]
},
{
"key": "deepseek",
"name": "DeepSeek V4.1 Flash (high)",
"provider": "DeepSeek",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.21048916,
"currency": false
},
{
"label": "Repair F1",
"value": 0.066,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.787,
"currency": false
},
{
"label": "Indoor",
"value": 0.18933412,
"currency": false
},
{
"label": "Outdoor",
"value": 0.22106668,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.054194520202020195,
"currency": true
}
]
},
{
"key": "qwen-off",
"name": "Qwen 3.8 27B (thinking off)",
"provider": "Alibaba",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.19970338666666668,
"currency": false
},
{
"label": "Repair F1",
"value": 0.083,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.667,
"currency": false
},
{
"label": "Indoor",
"value": 0.26629816,
"currency": false
},
{
"label": "Outdoor",
"value": 0.166406,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.27672816366207137,
"currency": true
}
]
},
{
"key": "inkling",
"name": "Inkling (high)",
"provider": "Thinking Machines",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.19801974666666666,
"currency": false
},
{
"label": "Repair F1",
"value": 0.095,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.609,
"currency": false
},
{
"label": "Indoor",
"value": 0.1690288,
"currency": false
},
{
"label": "Outdoor",
"value": 0.21251522,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.7541276882539681,
"currency": true
}
]
},
{
"key": "grok",
"name": "Grok 4.6 (high)",
"provider": "xAI",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.18414012,
"currency": false
},
{
"label": "Repair F1",
"value": 0.044,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.744,
"currency": false
},
{
"label": "Indoor",
"value": 0.1968008,
"currency": false
},
{
"label": "Outdoor",
"value": 0.17780978,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.2634673259259259,
"currency": true
}
]
},
{
"key": "gemma-on",
"name": "Gemma 4 31B (thinking on)",
"provider": "Google",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.12554015999999998,
"currency": false
},
{
"label": "Repair F1",
"value": 0.003,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.615,
"currency": false
},
{
"label": "Indoor",
"value": 0.12704028,
"currency": false
},
{
"label": "Outdoor",
"value": 0.1247901,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.028434150793650796,
"currency": true
}
]
},
{
"key": "gemma-off",
"name": "Gemma 4 31B (thinking off)",
"provider": "Google",
"metrics": [
{
"label": "Image-to-Scene",
"value": 0.11503794666666667,
"currency": false
},
{
"label": "Repair F1",
"value": 0.001,
"currency": false
},
{
"label": "Physical Safety",
"value": 0.572,
"currency": false
},
{
"label": "Indoor",
"value": 0.11239600000000001,
"currency": false
},
{
"label": "Outdoor",
"value": 0.11635892,
"currency": false
},
{
"label": "Mean cost / case",
"value": 0.01913622993197279,
"currency": true
}
]
}
]
}