Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Commonsense Reasoning on M3IT VCR (test)
Loading...
67.1
F1 Score
vLCM
13.436
27.368
41.3
55.232
Mar 1, 2026
F1 Score
Similarity Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Similarity Score
vLCM
2026.03
67.1
52.9
Qwen-2
Model size=7B
2026.03
50.2
51.3
PLM
Model size=8B
2026.03
44.1
43.2
LCM
2026.03
38.5
25.8
InterVL2
Model size=8B
2026.03
32.5
34
Qwen-2.5
Model size=7B
2026.03
27.5
40.2
InterVL2.5
Model size=8B
2026.03
15.5
15.8
Feedback
Search any
task
Search any
task