Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple-choice Visual Question Answering on PathMMU PubMed (test-all)
Loading...
75.3
Accuracy
PathChat+
38.692
48.196
57.7
67.204
Jun 26, 2025
Accuracy
95% CI (Lower Bound)
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
95% CI (Lower Bound)
PathChat+
2025.06
75.3
73.8
Gemini 2.5 pro
2025.06
72.5
70.9
GPT-5
2025.06
71.3
69.6
GPT-5-mini
2025.06
68.8
67.1
Claude Sonnet 4
2025.06
64.1
62.3
PathChat 1
2025.06
63.6
62
HuatuoGPT-Vision
2025.06
63.5
61.9
Qwen3-VL
2025.06
57.9
56.1
Llama-3.2
2025.06
53.5
51.7
LLaVA-OneVision
2025.06
48.9
47.1
Quilt-LLaVA
2025.06
41.6
39.9
PA-LLaVA
2025.06
40.1
38.4
Feedback
Search any
task
Search any
task