Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Reasoning on MMMU Pro Vision
Loading...
51.9
Accuracy
GPT4-o
18.62
27.26
35.9
44.54
Jan 1, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT4-o
Sampling Strategy=avg@...
2026.01
51.9
Gemini-2.0-Flash
Sampling Strategy=avg@...
2026.01
51.7
CPPO
Backbone=Qwen2.5-VL-7B...
2026.01
39
Vision-SR1
Backbone=Qwen2.5-VL-7B...
2026.01
38.9
PAPO
Backbone=Qwen2.5-VL-7B...
2026.01
38.7
NoisyRollout
Backbone=Qwen2.5-VL-7B...
2026.01
38.5
PerceptionR1
Backbone=Qwen2.5-VL-7B...
2026.01
38.1
GRPO
Backbone=Qwen2.5-VL-7B...
2026.01
37.9
OpenVLThinker
Backbone=Qwen2.5-VL-7B...
2026.01
35.5
Vision-Matters
Backbone=Qwen2.5-VL-7B...
2026.01
35.5
Look-Back
Backbone=Qwen2.5-VL-7B...
2026.01
34.5
Qwen2.5-VL-7B
Backbone=Qwen2.5-VL-7B...
2026.01
33.7
CPPO
Backbone=Qwen2.5-VL-3B...
2026.01
28.5
Visionary-R1
Backbone=Qwen2.5-VL-3B...
2026.01
27.9
PAPO
Backbone=Qwen2.5-VL-3B...
2026.01
26.8
GRPO
Backbone=Qwen2.5-VL-3B...
2026.01
25.8
OpenVLThinker
Backbone=Qwen2.5-VL-3B...
2026.01
25
Qwen2.5-VL-3B
Backbone=Qwen2.5-VL-3B...
2026.01
19.9
Feedback
Search any
task
Search any
task