open-agent-leaderboard
/

claude-code

agent-evaluation

Model card Files Files and versions

Claude Code

This is a tracking repo for Claude Code, used by the Open Agent Leaderboard to report evaluation results on HuggingFace.

Anthropic's agentic coding tool. Uses extended thinking, file editing, and shell execution to solve tasks autonomously.

Framework: claude-code
Leaderboard: Open Agent Leaderboard
Paper: arXiv:2602.22953

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for open-agent-leaderboard/claude-code

General Agent Evaluation

Paper • 2602.22953 • Published Feb 26 • 12

Evaluation results

Overall
on open-agent-leaderboard/results View evaluation results source leaderboard

model: Claude Opus 4.5
0.67 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: DeepSeek V3.2
0.42 ^*
Appworld on open-agent-leaderboard/results View evaluation results source leaderboard

0.66 ^*
Browsecomp Plus on open-agent-leaderboard/results View evaluation results source leaderboard

0.53 ^*
Swebench on open-agent-leaderboard/results View evaluation results source leaderboard

0.74 ^*
Taubench Airline on open-agent-leaderboard/results View evaluation results source leaderboard

0.66 ^*
Taubench Retail on open-agent-leaderboard/results View evaluation results source leaderboard

0.83 ^*
Taubench Telecom on open-agent-leaderboard/results View evaluation results source leaderboard

0.76 ^*