Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Next-step Generation on Human Evaluation Subset
Loading...
65
Win Rate
CoP (Qwen2.5-VL-7B)
47.32
51.91
56.5
61.09
May 14, 2026
Win Rate
Equal Rate
Loss Rate
Updated 2mo ago
Evaluation Results
Method
Method
Links
Win Rate
Equal Rate
Loss Rate
CoP (Qwen2.5-VL-7B)
Backbone=Qwen2.5-VL-7B
2026.05
65
2
33
CoP (GPT-4o)
Backbone=GPT-4o
2026.05
48
20
31
Feedback
Search any
task
Search any
task
