Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Mathematical Reasoning on DynaMath worst
Loading...
34.9
Score
OpenMMReasoner
7.964
14.957
21.95
28.943
Mar 18, 2026
Score
Updated 29d ago
Evaluation Results
Method
Method
Links
Score
OpenMMReasoner
Size=7B
2026.03
34.9
GPT-4o
Size=-
2026.03
34.5
Insight-V++ (Qwen2.5-VL + Self-Evolving)
Size=7B
2026.03
33.6
Open-Vision-Reasoner
Size=7B
2026.03
33.5
GPT-4o mini
Size=-
2026.03
31.6
Insight-V (Qwen2.5-VL + Multi-Agent RL)
Size=7B
2026.03
31.4
MMR1
Size=7B
2026.03
27.9
InternVL3-8B
Size=8B
2026.03
23
MM-Eureka-Qwen
Size=7B
2026.03
23
VLAA-Thinker-Qwen2.5
Size=7B
2026.03
22.4
Qwen2.5-VL
Size=7B
2026.03
21.8
LLaVA-OneVision-1.5
Size=8B
2026.03
19.8
VL-Rethinker
Size=7B
2026.03
17.8
OpenVLThinker
Size=7B
2026.03
16.8
ThinkLite-VL
Size=7B
2026.03
16.5
LLaVA-OneVision
Size=7B
2026.03
9
Feedback
Search any
task
Search any
task