Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended Visual Question Answering on Retina
Loading...
67.8
F1 Score
EyExIn
45.0136
50.9293
56.845
62.7607
Mar 7, 2026
F1 Score
Recall
Precision
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Recall
Precision
EyExIn
Model Category=Fine-Tuned
2026.03
67.8
62.3
96.15
Gemini3-Pro
Model Category=Proprie...
2026.03
61.42
45.68
95.83
ChatGPT-5.2
Model Category=Proprie...
2026.03
60.28
51.23
87.66
Qwen3-VL-Max
Model Category=Proprie...
2026.03
53
48.77
73.74
Qwen2.5-VL
Model Category=Fine-Tuned
2026.03
52.63
61.73
46.9
LLaVA
Model Category=Fine-Tuned
2026.03
45.89
54.3
41.55
Feedback
Search any
task
Search any
task