List your company

Mathematics on AMC (pass@1)

87.95pass@1GT-Reward
3.366825.325947.28569.2441Oct 22, 2025Oct 24, 2025Oct 26, 2025Oct 28, 2025Oct 30, 2025Nov 1, 2025Nov 3, 2025

Evaluation results

MethodLinks
GT-RewardBase Model=Qwen3-8B-Base2025.1187.95
GT-RewardBase Model=Qwen3-4B-Base2025.1186.74
GT-RewardBase Model=Llama-3.2-3B-Instruct2025.1183.13
GT-RewardBase Model=Llama-3.1-8B-Instruct2025.1180.72
Scaf-GRPOBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.1077.5
Scaf-GRPOBase Model=Qwen2.5-Math-7B2025.1070
DeepSeek-R1-Distill-Qwen-1.5BBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.1067.5
Vanilla GRPOBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.1067.5
Oat-ZeroBase Model=Qwen2.5-Math-7B2025.1062.5
LUFFYBase Model=Qwen2.5-Math-7B2025.1062.5
Scaf-GRPOBase Model=Qwen2.5-Math-1.5B2025.1060
Vanilla GRPOBase Model=Qwen2.5-Math-7B2025.1060
Scaf-GRPOBase Model=Qwen2.5-7B2025.1060
Self-HarmonyBase Model=Qwen3-8B-Base2025.1159.04
Majority-VotingBase Model=Qwen3-8B-Base2025.1159.03
SimpleRL-ZeroBase Model=Qwen2.5-Math-7B2025.1055
GT-RewardBase Model=Qwen3-1.7B-Base2025.1153.01
Co-RewardBase Model=Qwen3-8B-Base2025.1151.8
IntuitorBase Model=Qwen3-8B-Base2025.1151.65
RentBase Model=Qwen3-8B-Base2025.1150.82
Vanilla GRPOBase Model=Qwen2.5-7B2025.1050
Self-HarmonyBase Model=Qwen3-4B-Base2025.1149.4
Majority-VotingBase Model=Qwen3-4B-Base2025.1149.32
Vanilla GRPOBase Model=Qwen2.5-Math-1.5B2025.1047.5
Co-RewardBase Model=Qwen3-4B-Base2025.1146.98
Before RLBase Model=Qwen3-8B-Base2025.1145.78
RentBase Model=Qwen3-4B-Base2025.1145.25
IntuitorBase Model=Qwen3-4B-Base2025.1143.59
Qwen2.5-Math-7BBase Model=Qwen2.5-Math-7B2025.1042.5
Self-HarmonyBase Model=Qwen3-1.7B-Base2025.1140.51
Scaf-GRPOBase Model=Llama-3.2-3B-Instruct2025.1040
Co-RewardBase Model=Qwen3-1.7B-Base2025.1139.75
Majority-VotingBase Model=Qwen3-1.7B-Base2025.1137.65
Qwen2.5-7BBase Model=Qwen2.5-7B2025.1037.5
Vanilla GRPOBase Model=Llama-3.2-3B-Instruct2025.1035
Before RLBase Model=Qwen3-4B-Base2025.1134.94
Qwen2.5-Math-1.5BBase Model=Qwen2.5-Math-1.5B2025.1032.5
RentBase Model=Qwen3-1.7B-Base2025.1132
Self-HarmonyBase Model=Llama-3.1-8B-Instruct2025.1126.51
Before RLBase Model=Qwen3-1.7B-Base2025.1126.5
Co-RewardBase Model=Llama-3.2-3B-Instruct2025.1125.3
Self-HarmonyBase Model=Llama-3.2-3B-Instruct2025.1125.3
IntuitorBase Model=Llama-3.2-3B-Instruct2025.1123.79
RentBase Model=Llama-3.2-3B-Instruct2025.1123.79
IntuitorBase Model=Qwen3-1.7B-Base2025.1123.56
RentBase Model=Llama-3.1-8B-Instruct2025.1121.98
Majority-VotingBase Model=Llama-3.1-8B-Instruct2025.1121.53
Majority-VotingBase Model=Llama-3.2-3B-Instruct2025.1120.48
Before RLBase Model=Llama-3.1-8B-Instruct2025.1120.48
Llama-3.2-3B-InstructBase Model=Llama-3.2-3B-Instruct2025.1020
Before RLBase Model=Llama-3.2-3B-Instruct2025.1119.27
Co-RewardBase Model=Llama-3.1-8B-Instruct2025.1117.84
IntuitorBase Model=Llama-3.1-8B-Instruct2025.116.62