List your company

STEM Reasoning on GPQA

60.9ScoreQwen3-8B
56.94857.9745960.026Feb 6, 2026

Evaluation results

MethodLinks
Qwen3-8BReward Model=Baseline2026.0260.9
GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.0260.3
Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.0259.7
Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.0259.5
GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.0259
GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.0258.7
GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.0257.1