Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple-choice Visual Question Answering on PathMMU SocialPath n=1,796 (test)
Loading...
71.7
Accuracy
PathChat+
39.772
48.061
56.35
64.639
Jun 26, 2025
Accuracy
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
PathChat+
2025.06
71.7
GPT-5
2025.06
69.4
Gemini 2.5 pro
2025.06
66.3
GPT-5-mini
2025.06
65.5
Claude Sonnet 4
2025.06
62.5
PathChat 1
2025.06
61.4
HuatuoGPT-Vision
2025.06
59.6
Qwen3-VL
2025.06
56.1
Llama-3.2
2025.06
52.1
LLaVA-OneVision
2025.06
48.9
Quilt-LLaVA
2025.06
45.4
PA-LLaVA
2025.06
41
Feedback
Search any
task
Search any
task