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

Correspondence Reasoning on MomaGraph-Bench

0.812Accuracy

GPT-5

Updated 1mo ago

Evaluation Results

Method	Links
GPT-5 2025.12		0.812
MomaGraph-R1 2025.12		0.775
Qwen2.5-VL-7B-Instruct 2025.12		0.727
LLaVA-Onevision 2025.12		0.707
DeepSeek-VL2 2025.12		0.684