Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Counting on SuperClevr Counting
Loading...
91.38
Avg@8 Accuracy
PAPO_D
54.3872
63.9911
73.595
83.1989
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
91.38
DAPO
Backbone=Qwen2.5-VL, M...
2025.07
90.05
PAPO_G
Backbone=Qwen2.5-VL, M...
2025.07
89.81
PAPO_D
Backbone=Qwen2.5-VL, M...
2025.07
83.56
PAPO_G
Backbone=Qwen3-VL (thi...
2025.07
80.63
GRPO
Backbone=Qwen3-VL (thi...
2025.07
80.13
DAPO
Backbone=Qwen2.5-VL, M...
2025.07
74.25
GRPO
Backbone=Qwen2.5-VL, M...
2025.07
73.94
PAPO_G
Backbone=Qwen2.5-VL, M...
2025.07
62.56
GRPO
Backbone=Qwen2.5-VL, M...
2025.07
55.81
Feedback
Search any
task
Search any
task