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

LLM Judging Agreement on Reasoning Agreement Benchmark 2,500 samples

100Parsing Success Rate

GPT-4o

Updated 1mo ago

Evaluation Results

Method	Links
GPT-4o 2025.07		100	-
Master-RM-32B 2025.07		100	0.89
Master-RM-7B 2025.07		100	0.91
Multi-sub RM 2025.07		100	0.91
Omni-Judge 2025.07		100	0.81
Qwen2.5-72B-Instruct 2025.07		100	0.89
Qwen2.5-32B-Instruct 2025.07		100	0.9
Qwen2.5-14B-Instruct 2025.07		100	0.92
Qwen2.5-7B-Instruct 2025.07		100	0.85
Qwen2.5-3B-Instruct 2025.07		100	0.81
Qwen2.5-1.5B-Instruct 2025.07		100	0.83
Qwen2.5-0.5B-Instruct 2025.07		100	0.1
LLaMA3-70B-Instruct 2025.07		100	0.82
LLaMA3-8B-Instruct 2025.07		100	0.73
General-Verifier 2025.07		99.8	0.72