Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Visual Language Performance on MM-Vet (Pass@5)
Loading...
73.39
Pass@5
Vision-R1-7B
61.95
64.92
67.89
70.86
Jun 17, 2026
Pass@5
Average Score (@5)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@5
Average Score (@5)
Vision-R1-7B
Method Category=RL Method
2026.06
73.39
59.54
ViGOS
Backbone=Qwen2.5-VL 7B
2026.06
72.02
54.4
OPSD
Backbone=Qwen2.5-VL 7B
2026.06
70.18
52.75
Baseline
Backbone=Qwen2.5-VL 7B
2026.06
69.72
52.94
OPSD
Backbone=Qwen2.5-VL 3B
2026.06
68.81
45.69
ViGOS
Backbone=Qwen2.5-VL 3B
2026.06
65.6
43.76
Visionary-R1-3B
Method Category=RL Method
2026.06
64.22
49.27
Baseline
Backbone=Qwen2.5-VL 3B
2026.06
62.39
34.68
Feedback
Search any
task
Search any
task