AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Terminal-Bench
Terminal-Bench is a benchmark for testing AI agents in real terminal environments. It evaluates how well agents can handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, security tasks, data science workflows, and cybersecurity vulnerabilities. The benchmark consists of a dataset of ~100 hand-crafted, human-verified tasks and an execution harness that connects language models to a terminal sandbox.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- 2025-01-17
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 25
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Claude Sonnet 4.5 | 0.5 | Not recorded | Not recorded | 2025-09-29 · model_announcement | LLM Stats |
| MiniMax M2.1 | 0.479 | Not recorded | Not recorded | 2025-12-23 · model_announcement | LLM Stats |
| Kimi K2-Thinking-0905 | 0.471 | Not recorded | Not recorded | 2025-09-05 · model_announcement | LLM Stats |
| MiniMax M2 | 0.463 | Not recorded | Not recorded | 2025-10-27 · model_announcement | LLM Stats |
| Claude Opus 4.1 | 0.433 | Not recorded | Not recorded | 2025-08-05 · model_announcement | LLM Stats |
| Nova 2 Pro | 0.413 | Not recorded | Not recorded | 2025-12-02 · model_announcement | LLM Stats |
| Claude Haiku 4.5 | 0.41 | Not recorded | Not recorded | 2025-10-15 · model_announcement | LLM Stats |
| GLM-4.6 | 0.405 | Not recorded | Not recorded | 2025-09-30 · model_announcement | LLM Stats |
| LongCat-Flash-Chat | 0.3951 | Not recorded | Not recorded | 2025-08-29 · model_announcement | LLM Stats |
| Claude Opus 4 | 0.392 | Not recorded | Not recorded | 2025-05-22 · model_announcement | LLM Stats |
| DeepSeek-V3.2-Exp | 0.377 | Not recorded | Not recorded | 2025-09-29 · model_announcement | LLM Stats |
| GLM-4.5 | 0.375 | Not recorded | Not recorded | 2025-07-28 · model_announcement | LLM Stats |
| Claude Sonnet 4 | 0.355 | Not recorded | Not recorded | 2025-05-22 · model_announcement | LLM Stats |
| Claude 3.7 Sonnet | 0.352 | Not recorded | Not recorded | 2025-02-24 · model_announcement | LLM Stats |
| LongCat-Flash-Lite | 0.3375 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| GLM-4.7 | 0.333 | Not recorded | Not recorded | 2025-12-22 · model_announcement | LLM Stats |
| Nova 2 Lite | 0.325 | Not recorded | Not recorded | 2025-12-02 · model_announcement | LLM Stats |
| DeepSeek-V3.1 | 0.313 | Not recorded | Not recorded | 2025-01-10 · model_announcement | LLM Stats |
| MiMo-V2-Flash | 0.305 | Not recorded | Not recorded | 2025-12-16 · model_announcement | LLM Stats |
| GLM-4.5-Air | 0.3 | Not recorded | Not recorded | 2025-07-28 · model_announcement | LLM Stats |
| Kimi K2 Instruct | 0.3 | Not recorded | Not recorded | 2025-07-11 · model_announcement | LLM Stats |
| Nemotron 3 Super (120B A12B) | 0.2578 | Not recorded | Not recorded | 2026-03-11 · model_announcement | LLM Stats |
| Kimi K2-Instruct-0905 | 0.25 | Not recorded | Not recorded | 2025-09-05 · model_announcement | LLM Stats |
| Nemotron 3 Nano (30B A3B) | 0.085 | Not recorded | Not recorded | 2025-12-15 · model_announcement | LLM Stats |
| DeepSeek-R1-0528 | 0.057 | Not recorded | Not recorded | 2025-05-28 · model_announcement | LLM Stats |