List your company

Multi-Subject on GPQA

93.4pass@1GT-Reward
-0.834423.630348.09572.5597Nov 3, 2025

Evaluation results

MethodLinks
GT-RewardBase Model=Qwen3-8B-Base2025.1193.4
GT-RewardBase Model=Qwen3-4B-Base2025.1192.89
GT-RewardBase Model=Llama-3.1-8B-Instruct2025.1189.84
GT-RewardBase Model=Llama-3.2-3B-Instruct2025.1189.34
GT-RewardBase Model=Qwen3-1.7B-Base2025.1153.8
Majority-VotingBase Model=Qwen3-8B-Base2025.1139.34
Self-HarmonyBase Model=Qwen3-8B-Base2025.1138.07
RentBase Model=Qwen3-8B-Base2025.1137.88
Self-HarmonyBase Model=Qwen3-4B-Base2025.1137.06
Majority-VotingBase Model=Qwen3-4B-Base2025.1136.51
Before RLBase Model=Qwen3-8B-Base2025.1133.44
IntuitorBase Model=Qwen3-4B-Base2025.1132.39
RentBase Model=Qwen3-4B-Base2025.1131.78
IntuitorBase Model=Qwen3-8B-Base2025.1131.56
Self-HarmonyBase Model=Llama-3.2-3B-Instruct2025.1129.95
Self-HarmonyBase Model=Llama-3.1-8B-Instruct2025.1128.93
Self-HarmonyBase Model=Qwen3-1.7B-Base2025.1127.92
Majority-VotingBase Model=Llama-3.1-8B-Instruct2025.1125.31
Majority-VotingBase Model=Qwen3-1.7B-Base2025.1124.68
Co-RewardBase Model=Qwen3-8B-Base2025.1124.42
Co-RewardBase Model=Qwen3-4B-Base2025.1124.36
Co-RewardBase Model=Llama-3.1-8B-Instruct2025.1124.36
IntuitorBase Model=Qwen3-1.7B-Base2025.1123.76
Co-RewardBase Model=Qwen3-1.7B-Base2025.1123.66
RentBase Model=Qwen3-1.7B-Base2025.1123.47
Majority-VotingBase Model=Llama-3.2-3B-Instruct2025.1122.33
Before RLBase Model=Qwen3-1.7B-Base2025.1120.3
Co-RewardBase Model=Llama-3.2-3B-Instruct2025.1119.79
Before RLBase Model=Qwen3-4B-Base2025.1116.75
IntuitorBase Model=Llama-3.1-8B-Instruct2025.1115.32
Before RLBase Model=Llama-3.1-8B-Instruct2025.1114.72
RentBase Model=Llama-3.1-8B-Instruct2025.1114.56
IntuitorBase Model=Llama-3.2-3B-Instruct2025.113.23
Before RLBase Model=Llama-3.2-3B-Instruct2025.113.04
RentBase Model=Llama-3.2-3B-Instruct2025.112.79