Terminal-Bench 2.0

Terminal-Bench tests whether a model can operate a computer through a terminal as an agent: it gets a Linux container and has to solve hands-on tasks (installing packages, inspecting files, writing scripts) purely via shell commands within a time limit. The score is the share of tasks completed successfully, averaged over several runs.

Terminal-Bench 2.0 measures how well a model works as an autonomous coding agent. In detail, it checks:

• planning and executing multi-step shell workflows
• installing, configuring and debugging software in a container
• handling timeouts and failing commands
• finishing the task within the given compute and time budget

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

What is the Terminal-Bench 2.0 benchmark?

Terminal-Bench tests whether a model can operate a computer through a terminal as an agent: it gets a Linux container and has to solve hands-on tasks (installing packages, inspecting files, writing scripts) purely via shell commands within a time limit. The score is the share of tasks completed successfully, averaged over several runs.

What does Terminal-Bench 2.0 test?

Terminal-Bench 2.0 mainly measures how well a model works as an autonomous coding agent. Concretely, it checks: planning and executing multi-step shell workflows; installing, configuring and debugging software in a container; handling timeouts and failing commands.

How is the Terminal-Bench 2.0 score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get Terminal-Bench 2.0 data and scores?

The official source is https://artificialanalysis.ai/evaluations/terminalbench-v2-1. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/terminal-bench-2/scores) or pull it directly from the Open LLM Radar API with any HTTP client.