Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Perception-demanding tasks on BLINK
Loading...
61
Accuracy
Phi4-multimodal + DRScaffold
41.656
46.678
51.7
56.722
May 25, 2026
Accuracy
Updated 8d ago
Evaluation Results
Method
Method
Links
Accuracy
Phi4-multimodal + DRScaffold
Scale=5.6B
2026.05
61
Phi4-multimodal
Scale=5.6B
2026.05
60.6
Qwen2.5-VL
Scale=32B
2026.05
58.1
Qwen2.5-VL + DRScaffold
Scale=3B
2026.05
48.8
Qwen2.5-VL
Scale=3B
2026.05
47.9
InternVL2.5
Scale=2B
2026.05
44.2
InternVL2.5 + DRScaffold
Scale=2B
2026.05
42.4
Feedback
Search any
task
Search any
task