Agentic & Tool Use benchmark

# Terminal-Bench leaderboard

> Terminal-Bench results for 41 AI models, led by GPT-5.5 at 84.7%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/terminal-bench
- Last updated: 2026-10-10
- Title: Terminal-Bench Leaderboard (October 2026): Scores by Model

As of October 2026, GPT-5.5 has the highest published Terminal-Bench score on Noometry at 84.7%, out of 41 models with results.

Last verified October 10, 2026

## About Terminal-Bench

Hard tasks completed in a real terminal: compiling code, configuring systems, training models and debugging environments.

- **Category:** [Agentic & Tool Use](https://noometry.com/best/agentic)
- **Introduced:** 2025
- **Format:** Agent in a shell
- **Unit:** Percent (random guessing ≈ 0%)
- **Official site:** [www.tbench.ai](https://www.tbench.ai)

## Top 15 models

Top models on Terminal-Bench

1.  GPT-5.5 84.7%
2.  GPT-5.4 81.8%
3.  Claude Opus 4.7 80.2%
4.  Gemini 3.1 Pro Preview 80.2%
5.  Claude Opus 4.6 79.8%
6.  GPT-5.3 Codex 78.4%
7.  Gemini 3 Pro 69.4%
8.  GPT-5.2 Codex 66.5%
9.  GPT-5.2 64.9%
10.  Gemini 3 Flash Preview 64.3%
11.  Claude Opus 4.5 63.1%
12.  GPT-5.1-Codex-mini 61.6%
13.  GPT-5.1-Codex 60.4%
14.  Grok 4.20 (Non-Reasoning) 57.3%
15.  Claude Sonnet 4.6 53.4%
16.  405060708090

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## All results

Terminal-Bench results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [GPT-5.5](https://noometry.com/models/gpt-5-5) | [OpenAI](https://noometry.com/providers/openai) | 84.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [GPT-5.4](https://noometry.com/models/gpt-5-4) | [OpenAI](https://noometry.com/providers/openai) | 81.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7) | [Anthropic](https://noometry.com/providers/anthropic) | 80.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 80.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 79.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [GPT-5.3 Codex](https://noometry.com/models/gpt-5-3-codex) | [OpenAI](https://noometry.com/providers/openai) | 78.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 69.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [GPT-5.2 Codex](https://noometry.com/models/gpt-5-2-codex) | [OpenAI](https://noometry.com/providers/openai) | 66.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [GPT-5.2](https://noometry.com/models/gpt-5-2) | [OpenAI](https://noometry.com/providers/openai) | 64.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 10 | [Gemini 3 Flash Preview](https://noometry.com/models/gemini-3-flash-preview) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 64.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 11 | [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 63.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 12 | [GPT-5.1-Codex-mini](https://noometry.com/models/gpt-5-1-codex-mini) | [OpenAI](https://noometry.com/providers/openai) | 61.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 13 | [GPT-5.1-Codex](https://noometry.com/models/gpt-5-1-codex) | [OpenAI](https://noometry.com/providers/openai) | 60.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 14 | [Grok 4.20 (Non-Reasoning)](https://noometry.com/models/grok-4-20) | [xAI](https://noometry.com/providers/xai) | 57.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 15 | [Claude Sonnet 4.6](https://noometry.com/models/claude-sonnet-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 53.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 16 | [GLM-5](https://noometry.com/models/glm-5) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 52.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 17 | [GPT-5](https://noometry.com/models/gpt-5) | [OpenAI](https://noometry.com/providers/openai) | 49.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 18 | [GPT-5.1](https://noometry.com/models/gpt-5-1) | [OpenAI](https://noometry.com/providers/openai) | 47.6% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 19 | [Claude Sonnet 4.5](https://noometry.com/models/claude-sonnet-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 46.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 20 | [MiniMax-M2.7](https://noometry.com/models/minimax-m2-7) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 45.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 21 | [GPT-5-Codex](https://noometry.com/models/gpt-5-codex) | [OpenAI](https://noometry.com/providers/openai) | 44.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 22 | [Kimi K2.5](https://noometry.com/models/kimi-k2-5) | [Moonshot AI](https://noometry.com/providers/moonshot) | 43.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 23 | [MiniMax-M2.5](https://noometry.com/models/minimax-m2-5) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 42.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 24 | [DeepSeek-V3.2-Exp](https://noometry.com/models/deepseek-v3-2-exp) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 39.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 25 | [Claude Opus 4.1](https://noometry.com/models/claude-opus-4-1) | [Anthropic](https://noometry.com/providers/anthropic) | 38% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 26 | [MiniMax-M2.1](https://noometry.com/models/minimax-m2-1) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 36.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 27 | [Kimi K2 (Jul 2025)](https://noometry.com/models/kimi-k2) | [Moonshot AI](https://noometry.com/providers/moonshot) | 35.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 28 | [Claude Haiku 4.5](https://noometry.com/models/claude-haiku-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 35.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 29 | [GPT-5 Mini](https://noometry.com/models/gpt-5-mini) | [OpenAI](https://noometry.com/providers/openai) | 34.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 30 | [GLM-4.7](https://noometry.com/models/glm-4-7) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 33.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 31 | [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 32.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 32 | [MiniMax-M2](https://noometry.com/models/minimax-m2) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 30% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 33 | [Grok 4](https://noometry.com/models/grok-4) | [xAI](https://noometry.com/providers/xai) | 27.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 34 | [Qwen3-Coder 480B-A35B Instruct](https://noometry.com/models/qwen3-coder-480b-a35b-instruct) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 27.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 35 | [GLM-4.6](https://noometry.com/models/glm-4-6) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 24.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 36 | [Qwen3.6 35B-A3B](https://noometry.com/models/qwen3-6-35b-a3b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 23% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 37 | [GPT-5 Nano](https://noometry.com/models/gpt-5-nano) | [OpenAI](https://noometry.com/providers/openai) | 21.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 38 | [gpt-oss-120b](https://noometry.com/models/gpt-oss-120b) | [OpenAI](https://noometry.com/providers/openai) | 18.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 39 | [Gemini 2.5 Flash](https://noometry.com/models/gemini-2-5-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 17.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 40 | [Qwen3.5-9B](https://noometry.com/models/qwen3-5-9b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 9.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 41 | [gpt-oss-20b](https://noometry.com/models/gpt-oss-20b) | [OpenAI](https://noometry.com/providers/openai) | 3.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [GPT-5.5 vs GPT-5.4](https://noometry.com/compare/gpt-5-4-vs-gpt-5-5)
-   [GPT-5.5 vs Claude Opus 4.7](https://noometry.com/compare/claude-opus-4-7-vs-gpt-5-5)
-   [GPT-5.5 vs Gemini 3.1 Pro Preview](https://noometry.com/compare/gemini-3-1-pro-preview-vs-gpt-5-5)
-   [GPT-5.5 vs Claude Opus 4.6](https://noometry.com/compare/claude-opus-4-6-vs-gpt-5-5)
-   [GPT-5.4 vs Claude Opus 4.7](https://noometry.com/compare/claude-opus-4-7-vs-gpt-5-4)
-   [GPT-5.4 vs Gemini 3.1 Pro Preview](https://noometry.com/compare/gemini-3-1-pro-preview-vs-gpt-5-4)

## Other agentic & tool use benchmarks

-   [APEX-Agents](https://noometry.com/benchmarks/apex-agents)
-   [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl)
-   [OSWorld 2.0](https://noometry.com/benchmarks/osworld-2)
-   [GDPval](https://noometry.com/benchmarks/gdpval)
-   [Remote Labor Index](https://noometry.com/benchmarks/remote-labor-index)
-   [TheAgentCompany](https://noometry.com/benchmarks/the-agent-company)
-   [τ²-bench Airline](https://noometry.com/benchmarks/tau2-airline)
-   [τ²-bench Banking](https://noometry.com/benchmarks/tau2-banking)
-   [τ²-bench Retail](https://noometry.com/benchmarks/tau2-retail)
-   [τ²-bench Telecom](https://noometry.com/benchmarks/tau2-telecom)
-   [Cybench](https://noometry.com/benchmarks/cybench)
-   [DeepResearch Bench](https://noometry.com/benchmarks/deepresearch-bench)

## Frequently asked questions

### What does Terminal-Bench measure?

Hard tasks completed in a real terminal: compiling code, configuring systems, training models and debugging environments.

### Which model has the highest Terminal-Bench score?

As of October 2026, GPT-5.5 has the highest published Terminal-Bench score on Noometry at 84.7%, out of 41 models with results.

### What is the best open-weight model on Terminal-Bench?

GLM-5 has the highest Terminal-Bench accuracy among open-weight models at 52.4%, ranking 16 of 41 overall.

### Cite this page

Noometry. (2026). Terminal-Bench leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/terminal-bench

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/terminal-bench.md).