Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Mathematical Reasoning on MathVerse (testmini)
Loading...
57
Accuracy
OpenAI-o1
30.064
37.057
44.05
51.043
Jun 8, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
OpenAI-o1
#Data=/
2025.06
57
Qwen2.5-VL-72B-IT
#Data=/
2025.06
55.8
Perception-R1-7B
#Data=1.4K
2025.06
54.3
Vision-R1-7B
#Data=200K
2025.06
52.4
Claude-3.7-Sonnet
#Data=/
2025.06
52
MM-Eureka-7B
#Data=15K
2025.06
51.9
VLAA-Thinker-7B
#Data=25K
2025.06
51.2
GPT-4o
#Data=/
2025.06
50.2
SophiaVL-R1-7B
#Data=130K
2025.06
49
Qwen2.5-VL-7B-IT
#Data=/
2025.06
47.4
OpenVLThinker-7B
#Data=25K
2025.06
47.4
R1-OneVision-7B
#Data=155K
2025.06
46.5
URSA-7B
#Data=3.06M
2025.06
45.7
R1-VL-7B
#Data=260K
2025.06
40.8
InternVL2.5-8B
#Data=/
2025.06
39.5
Qwen2-VL-7B-IT
#Data=/
2025.06
31.1
Feedback
Search any
task
Search any
task