Terminal-Bench 3.0
Terminal-Bench 3.0 agentic terminal tasks, evaluated with the Claude Code 2.1.207 harness (reasoning effort=max, 400K context, 128K max output), avg@3 over three rollouts per task scored by the task's official verifier. Open-source SOTA for GLM-5.3 per the GLM-5.3 model card.
Category
Agentic Coding
Score type
percent
Scale
100%
higher is better
Models tested
4
What is Terminal-Bench 3.0?
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.
What does it test?
Terminal-Bench 3.0 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
How to read the score
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Frequently asked questions
What is the Terminal-Bench 3.0 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 3.0 test?
Terminal-Bench 3.0 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 3.0 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 3.0 data and scores?
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-3-0/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Benchmark dataset
The question/task data itself — download and evaluate locally
Benchmark metadata (JSON)
This page's benchmark record from the Open LLM Radar API
All model scores (JSON download)
Full score table as JSON; paginate with limit/offset params
Open LLM Radar API docs
Swagger UI to explore and reuse all radar API endpoints