List your company

STEM Reasoning on AIME 2024

77.7ScoreQwen3-8B-as-GenRM
73.5474.6275.776.78Feb 6, 2026

Evaluation results

MethodLinks
Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.0277.7
Qwen3-8BReward Model=Baseline2026.0277.6
GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.0276.5
Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.0276.1
GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.0275.5
GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.0275.4
GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.0273.7