Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Drusen size prediction on AREDS (test)
Loading...
67.8
Accuracy
OcularChat
38.16
45.855
53.55
61.245
Apr 28, 2026
Accuracy
F1-score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1-score
OcularChat
2026.04
67.8
64.2
Qwen2.5-VL-7B
Model size=7B
2026.04
53
41.1
Qwen2.5-VL-32B
Model size=32B
2026.04
52.8
40.9
Qwen2.5-VL-72B
Model size=72B
2026.04
52.3
41.4
GPT-o1
2026.04
49.2
42.4
MedGemma-4B
Model size=4B
2026.04
48.4
41.8
Llama-3.2-90B-Vision
Model size=90B
2026.04
43
37.8
Llama-3.2-11B-Vision
Model size=11B
2026.04
39.3
35.9
Feedback
Search any
task
Search any
task