List your company

STEM Reasoning on AIME 2025

67.6ScoreQwen3-8B
57.92860.43962.9565.461Feb 6, 2026

Evaluation results

MethodLinks
Qwen3-8BReward Model=Baseline2026.0267.6
GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.0267.2
Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.0264.8
GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.0264.8
GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.0264.2
Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.0264.1
GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.0258.3