Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended Visual Question Answering on ODIR
Loading...
56.7
F1 Score
EyExIn
30.648
37.4115
44.175
50.9385
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
56.7
55.2
60.4
Qwen2.5-VL
Model Category=Fine-Tuned
2026.03
39.09
42.02
46.28
ChatGPT-5.2
Model Category=Proprie...
2026.03
36.42
36.73
42.54
LLaVA
Model Category=Fine-Tuned
2026.03
34.9
36.15
40.8
Gemini3-Pro
Model Category=Proprie...
2026.03
32.13
24.54
75.7
Qwen3-VL-Max
Model Category=Proprie...
2026.03
31.65
30.73
53.58
Feedback
Search any
task
Search any
task