reasoning benchmark
Terminal-Bench 2.1
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.
Updated Aug 11, 2026
Models19
Model coverage19
MetricScore
EvidenceB
Terminal-Bench 2.1 Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 88.8% | 100.0% | 19 | C | |
| 02 | MA | 88.3% | 94.4% | 19 | C | |
| 03 | OP | 87.4% | 88.9% | 19 | C | |
| 04 | AC | 86.6% | 83.3% | 19 | C | |
| 05 | OP | 84.7% | 77.8% | 19 | C | |
| 06 | AN | 84.3% | 72.2% | 19 | C | |
| 07 | XA | 83.3% | 66.7% | 19 | C | |
| 08 | ME | 82.9% | 61.1% | 19 | C | |
| 09 | DE | 82.7% | 55.6% | 19 | C | |
| 10 | ZA | 82.7% | 50.0% | 19 | C | |
| 11 | ME | 80.0% | 44.4% | 19 | C | |
| 12 | GO | 78.0% | 38.9% | 19 | C | |
| 13 | TE | 71.7% | 33.3% | 19 | C | |
| 14 | BY | 71.0% | 27.8% | 19 | C | |
| 15 | BY | 67.6% | 22.2% | 19 | C | |
| 16 | MI | 66.0% | 16.7% | 19 | C | |
| 17 | NV | 56.4% | 11.1% | 19 | C | |
| 18 | GO | 54.0% | 5.6% | 19 | C | |
| 19 | ME | 51.7% | 0.0% | 19 | C |
Terminal-Bench 2.1 Score Distribution
A closer view of the leading scores on this benchmark.
Terminal-Bench 2.1 Highlights
The leading models and scores on this benchmark.
What is Terminal-Bench 2.1?
What Terminal-Bench 2.1 measures and how its scores work.
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Terminal-Bench 2.1
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- terminal-bench-2.1|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Terminal-Bench 2.1.
Which model scores highest on Terminal-Bench 2.1?
GPT-5.6 Sol is currently ranked first with 88.8%.
What does Terminal-Bench 2.1 measure?
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
19 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.