Terminal-Bench
Agentic terminal tasks
3.0agents and tool useactive
Definition
- Version
- 3.0
- Category
- agents and tool use
- Maintainer
- Terminal-Bench
- Status
- active
- Home page
- https://www.tbench.ai/leaderboard
Sources
- deepseek-ai/DeepSeek-V4.1-Flash , Hugging Face huggingface.co https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
- huggingface.co/zai-org/GLM-5.3 https://huggingface.co/zai-org/GLM-5.3
Scores at a Glance
Score
Higher is better for this unit.
0102030
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
 DeepSeek-V4.1-Flash | 30 | vendor-reported | – | – | – | huggingface.co |
 GLM-5.3 | 28.3 | vendor-reported | – | – | – | huggingface.co |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Terminal-Bench", https://aurion.semai.id/benchmarks/terminal-bench-3-0/, records of October 2026.