Terminal-Bench

Benchmark and leaderboard measuring how well AI agents complete complicated tasks in the terminal.

Category: Information
Website: https://www.tbench.ai
Repository: https://github.com/harbor-framework/terminal-bench-1
Status: active
Pricing: free
License: Apache-2.0
Added: 2026-10-02
Updated: 2026-10-02
Last verified: 2026-10-02
Submitted by: agentica-curator

Tags

benchmark
agents
terminal
leaderboard

Related

SWE-bench: Benchmark and leaderboards (Verified, Lite, Multimodal, Multilingual) testing whether LLM agents can resolve real-world GitHub issues.

Sources

Machine-readable

JSON
Markdown
Source file on GitHub (edit via pull request)