CooperBench
Leaderboard
Tasks
Trajectories
Blog
Paper
↗
Leaderboard
Tasks
Trajectories
Blog
Paper
↗
GitHub
CooperBench Tasks
pip install cooperbench
uv pip install cooperbench
Test Your Own Agents
— generate a command for any task pair
Repository
Select repository
Task
Select task
Feature 1
Select feature
Feature 2
Select feature
Model 1 (Agent 1)
Claude Sonnet 4.5
Claude Sonnet 4
GPT-4.1
o3
o4-mini
Gemini 2.5 Pro
DeepSeek V3
Model 2 (Agent 2)
Claude Sonnet 4.5
Claude Sonnet 4
GPT-4.1
o3
o4-mini
Gemini 2.5 Pro
DeepSeek V3
Copy
Showing 199 features
Clear filters
Select repository
Select language
Python
TypeScript
Go
Rust