Leaderboard Data
Leaderboards / Terminal-Bench

Terminal-Bench

Agents completing tasks in a terminal. Terminal-Bench 2.0 leaderboard entries are a Hugging Face dataset.

Operator
Stanford / Laude Institute (Harbor)
Leaderboard
tbench.ai
Category
Coding agents
How results are made
Outside submissions
Checked
2026-10-31

Raw data

FormatWhere
HF datasethuggingface.co/datasets/harborframework/terminal-bench-2-leaderboard
Terminal-Bench 2.0 leaderboard submissions.

Licence / reuse: Reuse with attribution

Apache-2.0. A licence or terms allow reuse if you credit the source (for example CC BY 4.0, MIT, Apache-2.0).

“license: apache-2.0”

Source: huggingface.co/datasets/harborframework/terminal-bench-2-leaderboard/raw/main/README.md

Submissions: Closed

The operator says submissions are closed or the board is retired.

“SUBMISSIONS CLOSED - All PRs opened before May 14th have been reviewed and merged if valid.”

Source: huggingface.co/datasets/harborframework/terminal-bench-2-leaderboard/raw/main/README.md

“We are working on a new submission process for the Terminal Bench 2.0 Leaderboard.”

Source: huggingface.co/datasets/harborframework/terminal-bench-2-leaderboard/raw/main/README.md

Last updated: 2026-05-15 169 days old

This page lists where the data lives and what the licence says. It does not copy any scores; open the leaderboard for those. Not legal advice. Something wrong? Use the bug link in the footer. Back to all leaderboards.