Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Multimodal Reasoning on MMStar (val)
Loading...
70.8
Accuracy
Qwen2.5-VL-72B-IT
55.408
59.404
63.4
67.396
Jun 8, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-VL-72B-IT
#Data=/
2025.06
70.8
Claude-3.7-Sonnet
#Data=/
2025.06
65.1
Perception-R1-7B
#Data=1.4K
2025.06
64.5
MM-Eureka-7B
#Data=15K
2025.06
64.2
OpenVLThinker-7B
#Data=25K
2025.06
63.8
Qwen2.5-VL-7B-IT
#Data=/
2025.06
63.1
SophiaVL-R1-7B
#Data=130K
2025.06
63.1
InternVL2.5-8B
#Data=/
2025.06
62.8
VLAA-Thinker-7B
#Data=25K
2025.06
62.7
Vision-R1-7B
#Data=200K
2025.06
62.6
R1-OneVision-7B
#Data=155K
2025.06
58.9
R1-VL-7B
#Data=260K
2025.06
56.7
Qwen2-VL-7B-IT
#Data=/
2025.06
56
Feedback
Search any
task
Search any
task