Views
No views yet
| id | Dataset | Metric | Samples | bf16 | w4a16 |
|---|---|---|---|---|---|
| 1 | aime25 | AveragePass@1 | 30 | 0.7666 | 0.8334 |
| 2 | gpqa_diamond | AveragePass@1 | 198 | 0.6869 | 0.6313 |
| 3 | mmlu_pro | AverageAccuracy | 1196 | 0.7784 | 0.7617 |
| 4 | ifeval | prompt_level_strict_acc | 541 | 0.8521 | 0.8503 |
| 5 | live_code_bench | Pass@1 | 1055 | 0.7922 | 0.7687 |