Capability
n/a
no benchmarks
GitHub stars
112.5k
Harness
ReAct loop
Built-in tools
Environments
2
Terminal · IDE
Capability
No public benchmark submissions · yet
Claude Code has not published benchmark scores on SWE-bench Verified, GAIA, OSWorld or τ-bench. Check the GitHub repo or vendor site for the latest · we track new submissions daily.
Momentum
Awaiting snapshot history · 1 days recorded
GitHub star history appears once daily star tracking has collected enough days.
The Stack
Brain · Harness · Tools · Environment
Brains
Which LLM powers it
claude-opus-4-6claude-sonnet-4-6
Harness
The loop pattern
ReAct loop
Tools
How it acts on the world
Built-in
Environments
Where it lives
TerminalIDE
Frequently asked
Pulled from the agents dataset
What is Claude Code?
Claude Code is a command-line coding agent built by Anthropic that lives in your terminal and edits files, runs commands, and searches your codebase with direct Claude model access.
What model powers Claude Code?
Claude Code runs on claude-opus-4-6 and claude-sonnet-4-6. It uses a react loop pattern with built-in tools.
Is Claude Code open-source?
No · Claude Code is a closed product from Anthropic. You can use it via usage-based billing.
How popular is Claude Code?
Claude Code has 112,515 stars on GitHub across 49 contributors.
Brains used
GitHub stats
Repoanthropics/claude-code
Stars112,515
Contributors49
Created2025-02-22
Last commit2026-04-10
How we score
Methodology
Composite capability · momentum formula · data sources.
Also in Assistive
Peer agents in the same category · sorted by capability