Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
ROI-level Visual Question Answering on SMU-VL 4
Loading...
73.1
Accuracy
PathPocket
18.292
32.521
46.75
60.979
Jun 6, 2026
Accuracy
95% Confidence Interval
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
95% Confidence Interval
PathPocket
2026.06
73.1
70.1
Qwen3-VL-8B
Model Size=8B
2026.06
71.9
68.9
Qwen3-VL-4B
Model Size=4B
2026.06
69.4
66.3
Qwen3-VL-2B
Model Size=2B
2026.06
68.5
65.4
LLaVA-Med
2026.06
22.1
19.3
Quilt-LLaVA
2026.06
20.4
17.7
Feedback
Search any
task
Search any
task