初始化项目,由ModelHub XC社区提供模型
Model: Dev4285/MiniArt-2.0 Source: Original Platform
This commit is contained in:
28
eval/eval_results.json
Normal file
28
eval/eval_results.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"model": "Dev4285/MiniArt-2.0",
|
||||
"benchmark": "GPQA Diamond (Graduate-Level Google-Proof Q&A)",
|
||||
"timestamp": "2026-08-02 22:08:15",
|
||||
"total_questions": 198,
|
||||
"evaluation_metrics": {
|
||||
"overall_accuracy": 34.8,
|
||||
"baseline_miniart_1_0": 28.4,
|
||||
"delta": "+6.4%",
|
||||
"domain_breakdown": {
|
||||
"Physics": {
|
||||
"miniart_1_0": 29.2,
|
||||
"miniart_2_0": 35.4,
|
||||
"questions": 65
|
||||
},
|
||||
"Chemistry": {
|
||||
"miniart_1_0": 27.5,
|
||||
"miniart_2_0": 33.8,
|
||||
"questions": 65
|
||||
},
|
||||
"Biology": {
|
||||
"miniart_1_0": 28.6,
|
||||
"miniart_2_0": 35.3,
|
||||
"questions": 68
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user