STEM Reasoning on AIME 2024
77.7ScoreQwen3-8B-as-GenRM
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.02 | 77.7 | |
| Qwen3-8BReward Model=Baseline2026.02 | 77.6 | |
| GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.02 | 76.5 | |
| Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.02 | 76.1 | |
| GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.02 | 75.5 | |
| GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.02 | 75.4 | |
| GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.02 | 73.7 |