Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Expert/Academic Reasoning on MMMU-Pro (Pass@5, Avg@5)
Loading...
64.81
Pass@5
ViGOS
46.5892
51.3196
56.05
60.7804
Jun 17, 2026
Pass@5
Avg@5
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@5
Avg@5
ViGOS
Backbone=Qwen2.5-VL 7B
2026.06
64.81
36.48
Baseline
Backbone=Qwen2.5-VL 7B
2026.06
63.85
37.41
OPSD
Backbone=Qwen2.5-VL 7B
2026.06
63.37
36.91
OPSD
Backbone=Qwen2.5-VL 3B
2026.06
57.04
26.24
ViGOS
Backbone=Qwen2.5-VL 3B
2026.06
56.44
26.16
Baseline
Backbone=Qwen2.5-VL 3B
2026.06
55
22.55
Visionary-R1-3B
Method Category=RL Method
2026.06
52.71
27.1
Vision-R1-7B
Method Category=RL Method
2026.06
47.29
31.48
Feedback
Search any
task
Search any
task