Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple-choice Visual Question Answering on PathMMU SocialPath tiny n=229 (test)
Loading...
75.1
Accuracy
PathChat+
42.86
51.23
59.6
67.97
Jun 26, 2025
Accuracy
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
PathChat+
2025.06
75.1
GPT-5
2025.06
73.8
Expert performance
2025.06
71.5
Gemini 2.5 pro
2025.06
70.3
Claude Sonnet 4
2025.06
66.8
GPT-5-mini
2025.06
66.8
Qwen3-VL
2025.06
64.2
PathChat 1
2025.06
63.8
HuatuoGPT-Vision
2025.06
57.6
Llama-3.2
2025.06
52
LLaVA-OneVision
2025.06
48.9
PA-LLaVA
2025.06
45.4
Quilt-LLaVA
2025.06
44.1
Feedback
Search any
task
Search any
task