Benchmark
Terminal-Bench
What is Terminal-Bench?
Environment image, timeout and permitted commands change results independently of the model. Version and harness both matter: 2.0 and 2.1 are different…
- Released
- 2025-05-19
- Evaluates
- agent
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 20
Source provenance
- Original evidence https://www.tbench.ai/
Terminal-Bench links
- Website https://www.tbench.ai/
Terminal-Bench results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Opus 4 | Anthropic | 43.2 | 2025-05-22 | evidence |
| DeepSeek-V4-Flash | DeepSeek | 56.9 | 2026-06-25 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 59.1 | 2026-04-22 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 63.3 | 2026-04-22 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 67.9 | 2026-04-22 | evidence |
| DeepSeek-V4-Pro-0813 | DeepSeek | 87.9 | 2026-08-13 | evidence |
| DeepSeek-V4.1-Flash | DeepSeek | 90.6 | 2026-09-10 | evidence |
| DeepSeek-V4.1-Flash | DeepSeek | 30.0 | 2026-09-10 | evidence |
| DeepSeek-V4.1-Flash | DeepSeek | 31.2 | 2026-09-10 | evidence |
| Gemini 3.1 Pro | 68.5 | 2026-02-19 | evidence | |
| GLM-5 | Z.ai | 56.2 | 2026-02-11 | evidence |
| GLM-5.1 | Z.ai | 63.5 | 2026-04-03 | evidence |
| GLM-5.2 | Z.ai | 81.0 | 2026-06-16 | evidence |
| GLM-5.3-Flash | Z.ai | 84.3 | 2026-08-27 | evidence |
| Grok 4.5 | xAI | 83.3 | 2026-07-08 | evidence |
| Hy4 preview | Tencent | 85.4 | 2026-08-28 | evidence |
| Kimi K3 | Moonshot AI | 88.3 | 2026-06-13 | evidence |
| Qwen3.5-397B-A17B | Qwen | 52.5 | 2026-02-16 | evidence |
| Seed2.0 Lite | ByteDance | 45.0 | 2026-02-14 | evidence |
| Seed2.0 Pro | ByteDance | 55.8 | 2026-02-14 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite Terminal-Bench?
- DeepSeek-V4.1-Flash DeepSeek, 2026-09-10
- Hy4 preview Tencent, 2026-08-28
- GLM-5.3-Flash Z.ai, 2026-08-27
- DeepSeek-V4-Pro-0813 DeepSeek, 2026-08-13
- Qwen3.8-27B Qwen, 2026-08-05
- Claude Opus 5 Anthropic, 2026-07-24
- GPT-5.6 (Sol, Terra, Luna) OpenAI, 2026-07-09
- Grok 4.5 xAI, 2026-07-08
- GPT-5.6 OpenAI, 2026-06-26
- DeepSeek-V4 DeepSeek, 2026-06-25
- GLM-5.2 Z.ai, 2026-06-16
- Kimi K3 Moonshot AI, 2026-06-13
21 source documents cite this benchmark.