Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical & Geometric Reasoning on We-Math
Loading...
77.7
Accuracy@8
Qwen2.5-VL-32B + VPPO
45.148
53.599
62.05
70.501
Oct 10, 2025
Accuracy@8
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy@8
Qwen2.5-VL-32B + VPPO
Model Scale=32B, Algor...
2025.10
77.7
Qwen2.5-VL-32B + GRPO
Model Scale=32B, Algor...
2025.10
76.7
Qwen2.5-VL-32B + DAPO
Model Scale=32B, Algor...
2025.10
76.2
NoisyRollout-32B
Model Scale=32B, Promp...
2025.10
75.7
MM-Eureka-32B
Model Scale=32B, Promp...
2025.10
75
Qwen2.5-VL-7B + VPPO
Model Scale=7B, Algori...
2025.10
71.5
NoisyRollout-7B
Model Scale=7B, Traini...
2025.10
71
Qwen2.5-VL-32B
Model Scale=32B
2025.10
71
R1-ShareVL-7B
Model Scale=7B, Traini...
2025.10
69.9
VL-Rethinker-7B
Model Scale=7B, Traini...
2025.10
68.9
PAPO-D-7B
Model Scale=7B, Traini...
2025.10
68.3
Qwen2.5-VL-7B + GRPO
Model Scale=7B, Algori...
2025.10
68.1
Qwen2.5-VL-7B + DAPO
Model Scale=7B, Algori...
2025.10
68
ThinkLite-7B
Model Scale=7B, Traini...
2025.10
66.5
MM-Eureka-7B
Model Scale=7B, Traini...
2025.10
65.5
Qwen2.5-VL-7B
Model Scale=7B
2025.10
46.4
Feedback
Search any
task
Search any
task