Accuracy on AIME 120
71AccuracyBaseline
Evaluation Results
| Method | Links | |
|---|---|---|
| BaselineModel=Qwen3-8B2026.05 | 71 | |
| NVFP4Model=Qwen3-8B2026.05 | 63.7 | |
| ScaleSearchModel=Qwen3-8B2026.05 | 63 | |
| BaselineModel=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 24.5 | |
| ScaleSearchModel=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 19.8 | |
| NVFP4Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 18.7 |