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 7, 2026
Published models17
Registry coverage17
MetricScore
EvidenceB
Terminal-Bench 2.1 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 88.8% | 100.0% | 17 | C | |
| 2 | MA | 88.3% | 93.8% | 17 | C | |
| 3 | OP | 87.4% | 87.5% | 17 | C | |
| 4 | AC | 86.6% | 81.3% | 17 | C | |
| 5 | OP | 84.7% | 75.0% | 17 | C | |
| 6 | AN | 84.3% | 68.8% | 17 | C | |
| 7 | XA | 83.3% | 62.5% | 17 | C | |
| 8 | DE | 82.7% | 56.3% | 17 | C | |
| 9 | ZA | 82.7% | 50.0% | 17 | C | |
| 10 | ME | 80.0% | 43.8% | 17 | C | |
| 11 | GO | 78.0% | 37.5% | 17 | C | |
| 12 | TE | 71.7% | 31.3% | 17 | C | |
| 13 | BY | 71.0% | 25.0% | 17 | C | |
| 14 | BY | 67.6% | 18.8% | 17 | C | |
| 15 | MI | 66.0% | 12.5% | 17 | C | |
| 16 | NV | 56.4% | 6.3% | 17 | C | |
| 17 | GO | 54.0% | 0.0% | 17 | C |
Score distribution
Top published rows on the benchmark's original scale.
Terminal-Bench 2.1 highlights
The top published results on this benchmark's own scale.
What is Terminal-Bench 2.1?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Terminal-Bench 2.1
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- terminal-bench-2.1|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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?
17 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.