Terminal-Bench 2.0

Terminal-Bench 2.0 evaluates agents completing software, science and system tasks in Docker environments.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryagentic
SubcategoryAgent execution on real terminal tasks in containers
Page statusunknown
Metrictask success verified by tests
Directionhigher_is_better
Unit%
Dataset licenceApache-2.0
PublisherTerminal-Bench Team

What it measures

Terminal-Bench 2.0 evaluates agents completing software, science and system tasks in Docker environments. The benchmark gives an agent an English task, a terminal environment and a verification procedure; success depends on completing the task and passing its tests.

Task format

Agent interacts with a containerized terminal; task-specific tests determine success.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub