Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on MathVision MVisionm
Loading...
41.3
Accuracy
Gemini-2.0-Flash
18.628
24.514
30.4
36.286
Jan 1, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini-2.0-Flash
Sampling Strategy=avg@...
2026.01
41.3
GPT4-o
Sampling Strategy=avg@...
2026.01
30.6
CPPO
Backbone=Qwen2.5-VL-7B...
2026.01
29.9
NoisyRollout
Backbone=Qwen2.5-VL-7B...
2026.01
29.4
Vision-SR1
Backbone=Qwen2.5-VL-7B...
2026.01
28
PerceptionR1
Backbone=Qwen2.5-VL-7B...
2026.01
27.6
GRPO
Backbone=Qwen2.5-VL-7B...
2026.01
27.6
OpenVLThinker
Backbone=Qwen2.5-VL-7B...
2026.01
27.5
PAPO
Backbone=Qwen2.5-VL-7B...
2026.01
26.5
Look-Back
Backbone=Qwen2.5-VL-7B...
2026.01
25.8
CPPO
Backbone=Qwen2.5-VL-3B...
2026.01
25.3
Vision-Matters
Backbone=Qwen2.5-VL-7B...
2026.01
25.2
GRPO
Backbone=Qwen2.5-VL-3B...
2026.01
25.1
Qwen2.5-VL-7B
Backbone=Qwen2.5-VL-7B...
2026.01
24.5
PAPO
Backbone=Qwen2.5-VL-3B...
2026.01
24.3
OpenVLThinker
Backbone=Qwen2.5-VL-3B...
2026.01
22.3
Visionary-R1
Backbone=Qwen2.5-VL-3B...
2026.01
19.7
Qwen2.5-VL-3B
Backbone=Qwen2.5-VL-3B...
2026.01
19.5
Feedback
Search any
task
Search any
task