General-purpose Behavior on MultiChallenge
58.6ScoreQwen3-14B-as-GenRM
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.02 | 58.6 | |
| GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.02 | 55.7 | |
| GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.02 | 55 | |
| Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.02 | 52.8 | |
| GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.02 | 51.7 | |
| GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.02 | 51.7 | |
| Qwen3-8BReward Model=Baseline2026.02 | 42.9 |