Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical & Geometric Reasoning on MathVerse
Loading...
75.1
Accuracy@8
Qwen2.5-VL-32B + VPPO
37.556
47.303
57.05
66.797
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
75.1
Qwen2.5-VL-32B + GRPO
Model Scale=32B, Algor...
2025.10
74.2
Qwen2.5-VL-32B + DAPO
Model Scale=32B, Algor...
2025.10
73.3
NoisyRollout-32B
Model Scale=32B, Promp...
2025.10
73
MM-Eureka-32B
Model Scale=32B, Promp...
2025.10
71.8
Qwen2.5-VL-7B + VPPO
Model Scale=7B, Algori...
2025.10
71.6
VL-Rethinker-7B
Model Scale=7B, Traini...
2025.10
68.8
PAPO-D-7B
Model Scale=7B, Traini...
2025.10
68.6
Qwen2.5-VL-32B
Model Scale=32B
2025.10
68.5
Qwen2.5-VL-7B + DAPO
Model Scale=7B, Algori...
2025.10
68.3
R1-ShareVL-7B
Model Scale=7B, Traini...
2025.10
68
NoisyRollout-7B
Model Scale=7B, Traini...
2025.10
67.8
MM-Eureka-7B
Model Scale=7B, Traini...
2025.10
67.1
Qwen2.5-VL-7B + GRPO
Model Scale=7B, Algori...
2025.10
66.5
ThinkLite-7B
Model Scale=7B, Traini...
2025.10
64.2
Qwen2.5-VL-7B
Model Scale=7B
2025.10
39
Feedback
Search any
task
Search any
task