Share your thoughts, 1 month free Claude Pro on usSee more

Mathematics on AMC (pass@1)

87.95pass@1

GT-Reward

Updated 1mo ago

Evaluation Results

Method	Links
GT-Reward 2025.11		87.95
GT-Reward 2025.11		86.74
GT-Reward 2025.11		83.13
GT-Reward 2025.11		80.72
Scaf-GRPO 2025.10		77.5
Scaf-GRPO 2025.10		70
DeepSeek-R1-Distill-Qwen-1.5B 2025.10		67.5
Vanilla GRPO 2025.10		67.5
Oat-Zero 2025.10		62.5
LUFFY 2025.10		62.5
Scaf-GRPO 2025.10		60
Vanilla GRPO 2025.10		60
Scaf-GRPO 2025.10		60
Self-Harmony 2025.11		59.04
Majority-Voting 2025.11		59.03
SimpleRL-Zero 2025.10		55
GT-Reward 2025.11		53.01
Co-Reward 2025.11		51.8
Intuitor 2025.11		51.65
Rent 2025.11		50.82
Vanilla GRPO 2025.10		50
Self-Harmony 2025.11		49.4
Majority-Voting 2025.11		49.32
Vanilla GRPO 2025.10		47.5
Co-Reward 2025.11		46.98
Before RL 2025.11		45.78
Rent 2025.11		45.25
Intuitor 2025.11		43.59
Qwen2.5-Math-7B 2025.10		42.5
Self-Harmony 2025.11		40.51
Scaf-GRPO 2025.10		40
Co-Reward 2025.11		39.75
Majority-Voting 2025.11		37.65
Qwen2.5-7B 2025.10		37.5
Vanilla GRPO 2025.10		35
Before RL 2025.11		34.94
Qwen2.5-Math-1.5B 2025.10		32.5
Rent 2025.11		32
Self-Harmony 2025.11		26.51
Before RL 2025.11		26.5
Co-Reward 2025.11		25.3
Self-Harmony 2025.11		25.3
Intuitor 2025.11		23.79
Rent 2025.11		23.79
Intuitor 2025.11		23.56
Rent 2025.11		21.98
Majority-Voting 2025.11		21.53
Majority-Voting 2025.11		20.48
Before RL 2025.11		20.48
Llama-3.2-3B-Instruct 2025.10		20
Before RL 2025.11		19.27
Co-Reward 2025.11		17.84
Intuitor 2025.11		6.62