Mathematical Reasoning on AIME 25 (Pass@1, Maj@128, DeepConf@128, Chronos@128)
78.67Pass@1Pass@1
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Pass@1Model=Qwen3-4B, Number of repeated trials=162026.02 | 78.67 | — | — | — | |
| Pass@1Model=DeepSeek-8B, Number of repeated trials=162026.02 | 75.21 | — | — | — | |
| Pass@1Model=DeepSeek-1.5B, Number of repeated trials=162026.02 | 24.58 | — | — | — | |
| Chronos@128Model=DeepSeek-1.5B, Number of repeated trials=16, Trajectories=1282026.02 | — | — | — | 44.17 | |
| Chronos@128Model=Qwen3-4B, Number of repeated trials=16, Trajectories=1282026.02 | — | — | — | 86.67 | |
| Chronos@128Model=DeepSeek-8B, Number of repeated trials=16, Trajectories=1282026.02 | — | — | — | 88.75 | |
| DeepConf@128Model=DeepSeek-1.5B, Number of repeated trials=16, Trajectories=1282026.02 | — | — | 40.21 | — | |
| DeepConf@128Model=Qwen3-4B, Number of repeated trials=16, Trajectories=1282026.02 | — | — | 85.83 | — | |
| DeepConf@128Model=DeepSeek-8B, Number of repeated trials=16, Trajectories=1282026.02 | — | — | 86.46 | — | |
| Maj@128Model=DeepSeek-1.5B, Number of repeated trials=16, Trajectories=1282026.02 | — | 37.5 | — | — | |
| Maj@128Model=Qwen3-4B, Number of repeated trials=16, Trajectories=1282026.02 | — | 86.67 | — | — | |
| Maj@128Model=DeepSeek-8B, Number of repeated trials=16, Trajectories=1282026.02 | — | 83.96 | — | — |