# Terminal-Bench

> Terminal-Bench results for 33 AI models we list, with each result's setting, date and source.

- Canonical: https://www.anchorterminal.com/benchmarks/terminal-bench/
- Markdown: https://www.anchorterminal.com/benchmarks/terminal-bench/index.md (~4,400 tokens)
- Slim: https://www.anchorterminal.com/benchmarks/terminal-bench/index.min.md (~4,280 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/benchmarks/terminal-bench/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-21

An agent harness running a model in a sandboxed shell, five trials or more on every task, until the task's tests pass. A row is one harness and model pair at one reasoning effort; the model is what's ranked.

- Score: % of trials passed, higher is better
- Run by: Stanford and the Laude Institute (the Terminal-Bench maintainers)
- Status: Current, newest result 20 November 2026
- Updated: as models are released
- Data: https://github.com/harbor-framework/terminal-bench/tree/main/leaderboard/submissions (Apache-2.0, https://github.com/harbor-framework/terminal-bench/blob/main/LICENSE), read 2026-11-20
- Method: https://www.tbench.ai/

## Results: 4.0

26 models we list, each at its best setting, best first.

| # | Model | Score | Range | Who ran it | Setting | Date | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 64.8% | 61.7% to 68.0% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 | https://www.tbench.ai/ |
| 2 | [Claude Sonnet 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 61.8% | 58.9% to 64.8% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 | https://www.tbench.ai/ |
| 3 | [Kimi K3.1 Pro](https://www.anchorterminal.com/tools/kimi-k3-1-pro.md) | 60.9% | 56.8% to 65.0% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-30 | https://www.tbench.ai/ |
| 4 | [GPT-6.1 Sol](https://www.anchorterminal.com/tools/openai-api.md) | 58.2% | 55.1% to 61.3% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 | https://www.tbench.ai/ |
| 5 | [Claude Fable 5.1](https://www.anchorterminal.com/tools/anthropic-api.md) | 57.9% | 54.1% to 61.6% | Independent | effort max, harness Claude Code, harness version 2.1.257, trials 330 | 2026-09-02 | https://www.tbench.ai/ |
| 6 | [Gemini 4 Argon](https://www.anchorterminal.com/tools/gemini-4-argon.md) | 54.9% | 51.9% to 57.8% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-13 | https://www.tbench.ai/ |
| 7 | [GPT-6.1 Terra](https://www.anchorterminal.com/tools/openai-api.md) | 51.8% | 49.0% to 54.6% | Independent | effort max, harness Codex, harness version 0.164.0, trials 330 | 2026-10-28 | https://www.tbench.ai/ |
| 8 | [GPT-6 Sol](https://www.anchorterminal.com/tools/azure-openai.md) | 49.4% | 46.2% to 52.6% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 | https://www.tbench.ai/ |
| 9 | [Muse Wonder](https://www.anchorterminal.com/tools/meta-model-api.md) | 47.0% | 43.2% to 50.8% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, trials 330 | 2026-11-05 | https://www.tbench.ai/ |
| 10 | [GLM-5.3](https://www.anchorterminal.com/tools/glm-5-3.md) | 41.8% | 38.6% to 45.0% | Independent | effort max, harness Claude Code, harness version 2.1.207, trials 330 | 2026-08-26 | https://www.tbench.ai/ |
| 11 | [Claude Haiku 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 40.0% | 36.3% to 43.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-06 | https://www.tbench.ai/ |
| 11 | [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | 40.0% | 36.3% to 43.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-31 | https://www.tbench.ai/ |
| 13 | [Tencent Hy4](https://www.anchorterminal.com/tools/hy4.md) | 39.1% | 35.6% to 42.6% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 | https://www.tbench.ai/ |
| 14 | [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | 36.7% | 33.0% to 40.3% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-02 | https://www.tbench.ai/ |
| 15 | [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | 27.9% | 24.0% to 31.8% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-04 | https://www.tbench.ai/ |
| 16 | [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | 22.4% | 18.6% to 26.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 | https://www.tbench.ai/ |
| 17 | [Gemini 3.8 Flash](https://www.anchorterminal.com/tools/vertex-ai.md) | 19.1% | 15.7% to 22.4% | Independent | effort high, harness mini-SWE-agent, harness version 2.4.6, trials 330 | 2026-09-01 | https://www.tbench.ai/ |
| 18 | [GPT-6 Luna](https://www.anchorterminal.com/tools/azure-openai.md) | 16.4% | 13.6% to 19.1% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 | https://www.tbench.ai/ |
| 19 | [Muse Spark 1.3](https://www.anchorterminal.com/tools/meta-model-api.md) | 14.6% | 11.6% to 17.5% | Independent | effort xhigh, harness Muse Code, harness version 1.4.1, trials 330 | 2026-09-30 | https://www.tbench.ai/ |
| 20 | [MiniMax M3](https://www.anchorterminal.com/tools/minimax-api.md) | 7.3% | 4.6% to 10.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-10 | https://www.tbench.ai/ |
| 21 | [DeepSeek V4 Pro](https://www.anchorterminal.com/tools/deepseek-api.md) | 6.7% | 4.2% to 9.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 | https://www.tbench.ai/ |
| 22 | [Beam 1.0](https://www.anchorterminal.com/tools/reflection-beam.md) | 6.4% | 4.7% to 8.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 | https://www.tbench.ai/ |
| 23 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 2.7% | 1.1% to 4.4% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-14 | https://www.tbench.ai/ |
| 24 | [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | 0.9% | 0.0% to 1.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 | https://www.tbench.ai/ |
| 25 | [Nemotron 3.5 Super VL](https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md) | 0.3% | -0.3% to 0.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 | https://www.tbench.ai/ |
| 26 | [Inkling](https://www.anchorterminal.com/tools/inkling.md) | 0.0% | 0.0% to 0.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 | https://www.tbench.ai/ |

Every setting, 27 rows:

| Model | As named | Score | Who ran it | Setting | Date |
| --- | --- | --- | --- | --- | --- |
| Claude Opus 5.5 | anthropic/claude-opus-5-5 | 64.8% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 |
| Claude Sonnet 5.5 | anthropic/claude-sonnet-5-5 | 61.8% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 |
| Kimi K3.1 Pro | Kimi K3.1 Pro | 60.9% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-30 |
| GPT-6.1 Sol | GPT-6.1 Sol | 58.2% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 |
| Claude Fable 5.1 | anthropic/claude-fable-5-1 | 57.9% | Independent | effort max, harness Claude Code, harness version 2.1.257, trials 330 | 2026-09-02 |
| Gemini 4 Argon | Gemini 4 Argon | 54.9% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-13 |
| GPT-6.1 Terra | GPT-6.1 Terra | 51.8% | Independent | effort max, harness Codex, harness version 0.164.0, trials 330 | 2026-10-28 |
| GPT-6 Sol | GPT-6 Sol | 49.4% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 |
| Muse Wonder | Muse Wonder | 47.0% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, trials 330 | 2026-11-05 |
| GLM-5.3 | GLM-5.3 | 41.8% | Independent | effort max, harness Claude Code, harness version 2.1.207, trials 330 | 2026-08-26 |
| Claude Haiku 5.5 | anthropic/claude-haiku-5-5 | 40.0% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-06 |
| DeepSeek V4.1 Flash | DeepSeek V4.1 Flash 1017 | 40.0% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-31 |
| Tencent Hy4 | Hy4 | 39.1% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 |
| GLM-5.3-Flash | GLM-5.3-Flash | 36.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-02 |
| GLM-5.3-Flash | GLM-5.3-Flash | 35.8% | Independent | effort none, harness Claude Code, harness version 2.1.285, trials 330 | 2026-10-06 |
| Mistral Large 4 | Mistral Large 4 | 27.9% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-04 |
| Kimi K3 | Kimi K3 | 22.4% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 |
| Gemini 3.8 Flash | Gemini 3.8 Flash | 19.1% | Independent | effort high, harness mini-SWE-agent, harness version 2.4.6, trials 330 | 2026-09-01 |
| GPT-6 Luna | GPT-6 Luna | 16.4% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 |
| Muse Spark 1.3 | Muse Spark 1.3 | 14.6% | Independent | effort xhigh, harness Muse Code, harness version 1.4.1, trials 330 | 2026-09-30 |
| MiniMax M3 | MiniMax M3 | 7.3% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-10 |
| DeepSeek V4 Pro | DeepSeek V4 Pro 0813 | 6.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 |
| Beam 1.0 | Beam 1.0 | 6.4% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 |
| Gemini 3.1 Pro (preview) | gemini/gemini-3.1-pro-preview | 2.7% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-14 |
| Inkling-Small | Inkling Small | 0.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 |
| Nemotron 3.5 Super VL | Nemotron 3.5 Super VL | 0.3% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 |
| Inkling | Inkling | 0.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 |

## Results: 4.1

24 models we list, each at its best setting, best first.

| # | Model | Score | Range | Who ran it | Setting | Date | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://www.anchorterminal.com/tools/claude-fable-5-2.md) | 65.8% | 62.9% to 68.6% | Independent | effort max, harness Claude Code, harness version 2.1.321, trials 330 | 2026-11-10 | https://www.tbench.ai/ |
| 2 | [Gemini 4 Carbon](https://www.anchorterminal.com/tools/gemini-4-carbon.md) | 64.5% | 61.3% to 67.8% | Independent | effort high, harness Antigravity CLI, harness version 1.5.7, trials 330 | 2026-11-14 | https://www.tbench.ai/ |
| 3 | [GPT-6.2 Astra](https://www.anchorterminal.com/tools/gpt-6-2-astra.md) | 62.1% | 59.8% to 64.4% | Independent | effort max, harness Codex, harness version 0.169.0, trials 330 | 2026-11-17 | https://www.tbench.ai/ |
| 4 | [GPT-6.2 Sol](https://www.anchorterminal.com/tools/openai-api.md) | 61.5% | 58.8% to 64.3% | Independent | effort max, harness Codex, harness version 0.169.0, trials 330 | 2026-11-17 | https://www.tbench.ai/ |
| 5 | [Gemini 4 Neon](https://www.anchorterminal.com/tools/gemini-4-neon.md) | 61.2% | 58.4% to 64.1% | Independent | effort xhigh, harness Antigravity CLI, harness version 1.5.12, trials 330 | 2026-11-20 | https://www.tbench.ai/ |
| 6 | [Kimi K3.1 Pro](https://www.anchorterminal.com/tools/kimi-k3-1-pro.md) | 59.7% | 55.5% to 63.9% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 7 | [Gemini 4 Hydrogen](https://www.anchorterminal.com/tools/gemini-4-hydrogen.md) | 56.4% | 53.4% to 59.3% | Independent | effort high, harness Antigravity CLI, harness version 1.5.7, trials 330 | 2026-11-13 | https://www.tbench.ai/ |
| 8 | [Gemini 4 Argon](https://www.anchorterminal.com/tools/gemini-4-argon.md) | 55.5% | 52.6% to 58.3% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, regrade yes, trials 330 | 2026-11-13 | https://www.tbench.ai/ |
| 9 | [GPT-6.1 Terra](https://www.anchorterminal.com/tools/openai-api.md) | 53.3% | 50.2% to 56.4% | Independent | effort max, harness Codex, harness version 0.164.0, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 10 | [Muse Wonder](https://www.anchorterminal.com/tools/meta-model-api.md) | 47.0% | 43.2% to 50.8% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, regrade yes, trials 330 | 2026-11-13 | https://www.tbench.ai/ |
| 11 | [Claude Haiku 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 40.0% | 36.4% to 43.6% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 12 | [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | 38.5% | 34.7% to 42.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 13 | [Tencent Hy4](https://www.anchorterminal.com/tools/hy4.md) | 37.9% | 34.4% to 41.4% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 14 | [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | 37.0% | 33.3% to 40.6% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 15 | [Muse Ember](https://www.anchorterminal.com/tools/muse-ember.md) | 30.6% | 26.8% to 34.4% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, trials 330 | 2026-11-10 | https://www.tbench.ai/ |
| 16 | [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | 27.6% | 23.7% to 31.4% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 17 | [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | 23.0% | 19.3% to 26.8% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 18 | [MiniMax M3](https://www.anchorterminal.com/tools/minimax-api.md) | 7.6% | 4.8% to 10.3% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 19 | [DeepSeek V4 Pro](https://www.anchorterminal.com/tools/deepseek-api.md) | 6.7% | 4.2% to 9.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 20 | [Beam 1.0](https://www.anchorterminal.com/tools/reflection-beam.md) | 6.4% | 4.7% to 8.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 21 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 2.7% | 1.1% to 4.4% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, regrade yes, trials 330 | 2026-11-15 | https://www.tbench.ai/ |
| 22 | [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | 0.9% | 0.0% to 1.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 23 | [Nemotron 3.5 Super VL](https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md) | 0.3% | -0.3% to 0.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |
| 24 | [Inkling](https://www.anchorterminal.com/tools/inkling.md) | 0.0% | 0.0% to 0.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |

A rank is among the models we list with a result, not a place on the whole leaderboard, and a model offered by several hosts is shown once, on its own listing. These results don't move our grades.

Data: Terminal-Bench, Stanford and the Laude Institute, Apache 2.0, Apache-2.0. All benchmarks: https://www.anchorterminal.com/benchmarks/index.md

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
