Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Math Reasoning on MathVerse (avg@8 accuracy)
Loading...
68.58
Avg@8 Accuracy
PAPO_D
47.156
52.718
58.28
63.842
Jul 8, 2025
Avg@8 Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Avg@8 Accuracy
PAPO_D
Backbone=Qwen2.5-VL, M...
2025.07
68.58
PAPO_G
Backbone=Qwen2.5-VL, M...
2025.07
68.43
GRPO
Backbone=Qwen2.5-VL, M...
2025.07
66.51
PAPO_D
Backbone=Qwen2.5-VL, M...
2025.07
60.51
PAPO_G
Backbone=Qwen2.5-VL, M...
2025.07
57.14
DAPO
Backbone=Qwen2.5-VL, M...
2025.07
56.25
DAPO
Backbone=Qwen2.5-VL, M...
2025.07
55.64
GRPO
Backbone=Qwen2.5-VL, M...
2025.07
55.25
PAPO_G
Backbone=Qwen3-VL (thi...
2025.07
51.89
GRPO
Backbone=Qwen3-VL (thi...
2025.07
47.98
Feedback
Search any
task
Search any
task