Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple-choice question answering on PathMMU EduContent n=255 (test-tiny)
Loading...
76.9
Accuracy
PathChat+
41.02
50.335
59.65
68.965
Jun 26, 2025
Accuracy
Accuracy 95% CI (Lower Bound)
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
Accuracy 95% CI (Lower Bound)
PathChat+
2025.06
76.9
71.8
GPT-5
2025.06
75.7
70.6
GPT-5-mini
2025.06
75.7
70.6
Gemini 2.5 pro
2025.06
71.8
65.9
Expert performance
2025.06
69
-
PathChat 1
2025.06
67.8
61.6
Claude Sonnet 4
2025.06
66.7
61.2
HuatuoGPT-Vision
2025.06
62
55.7
Qwen3-VL
2025.06
61.2
55.3
LLaVA-OneVision
2025.06
57.3
51.4
Llama-3.2
2025.06
56.5
50.6
Quilt-LLaVA
2025.06
49.8
43.1
PA-LLaVA
2025.06
42.4
36.1
Feedback
Search any
task
Search any
task