List your company

General-purpose Behavior on MultiChallenge

58.6ScoreQwen3-14B-as-GenRM
42.27246.51150.7554.989Feb 6, 2026

Evaluation results

MethodLinks
Qwen3-14B-as-GenRMReward Model=Qwen3-14B-as-GenRM2026.0258.6
GenRM-R-Align-14BReward Model=GenRM-R-Align-14B2026.0255.7
GenRM-RLVR-8BReward Model=GenRM-RLVR-8B2026.0255
Qwen3-8B-as-GenRMReward Model=Qwen3-8B-as-GenRM2026.0252.8
GenRM-R-Align-8BReward Model=GenRM-R-Align-8B2026.0251.7
GenRM-RLVR-14BReward Model=GenRM-RLVR-14B2026.0251.7
Qwen3-8BReward Model=Baseline2026.0242.9