STEM Reasoning on AIME 2025
67.6ScoreQwen3-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-8BReward Model=Baseline2026.02 | 67.6 | |
| GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.02 | 67.2 | |
| Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.02 | 64.8 | |
| GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.02 | 64.8 | |
| GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.02 | 64.2 | |
| Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.02 | 64.1 | |
| GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.02 | 58.3 |