Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
ROI-level Visual Question Answering on SMU-VL 5
Loading...
75.3
Accuracy
Qwen3-VL-8B
17.268
32.334
47.4
62.466
Jun 6, 2026
Accuracy
95% CI (Lower Bound)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
95% CI (Lower Bound)
Qwen3-VL-8B
Model Size=8B
2026.06
75.3
72.5
PathPocket
2026.06
74.9
72
Qwen3-VL-4B
Model Size=4B
2026.06
70.1
67.1
Qwen3-VL-2B
Model Size=2B
2026.06
69.9
66.9
Quilt-LLaVA
2026.06
24.2
21.4
LLaVA-Med
2026.06
19.5
16.9
Feedback
Search any
task
Search any
task