# AA Terminal-Bench 4.0 leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-aa-terminal-bench4

Artificial Analysis Terminal-Bench v4.0. Every model the catalog carries a published AA Terminal-Bench 4.0 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Task success rate |
| Tasks | Terminal-based agent tasks |
| Difficulty | Agentic software engineering |
| Published by | [Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |

An independently evaluated Terminal-Bench v4.0 result from Artificial Analysis, one of the ten components of its Intelligence Index v4.3.

## AA Terminal-Bench 4.0 ranking

49 models with a published AA Terminal-Bench 4.0 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Task success rate | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 67.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 4 Carbon](https://modelscale.dev/models/gemini-4-carbon) | Google | 65.2 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6.2 Astra](https://modelscale.dev/models/gpt-6-2-astra) | OpenAI | 64.1 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 63.6 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 4 Neon](https://modelscale.dev/models/gemini-4-neon) | Google | 63.6 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.2 Sol](https://modelscale.dev/models/gpt-6-2-sol) | OpenAI | 60.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Fable 5.2](https://modelscale.dev/models/claude-fable-5-2) | Anthropic | 59.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 59.6 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 59.1 | Last good 2026-11-17 · source benchlm:models |
| 10 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 57.1 | Last good 2026-10-23 · source benchlm:models |
| 10 | [Muse Wonder Full](https://modelscale.dev/models/muse-wonder-full) | Meta | 57.1 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 56.1 | Last good 2026-11-17 · source benchlm:models |
| 13 | [GPT-6.1 Terra](https://modelscale.dev/models/gpt-6-1-terra) | OpenAI | 55.6 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Gemini 4 Hydrogen](https://modelscale.dev/models/gemini-4-hydrogen) | Google | 53.5 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 52.0 | Last good 2026-11-17 · source benchlm:models |
| 15 | [Muse Wonder](https://modelscale.dev/models/muse-wonder) | Meta | 52.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 49.0 | Last good 2026-09-30 · source benchlm:models |
| 18 | [Qwen4 Max](https://modelscale.dev/models/qwen4-max) | Alibaba | 48.5 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 43.9 | Last good 2026-10-08 · source benchlm:models |
| 20 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 42.4 | Last good 2026-09-18 · source benchlm:models |
| 21 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 41.9 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Muse Ember](https://modelscale.dev/models/muse-ember) | Meta | 40.9 | Observed 2026-11-21 · source benchlm:models |
| 23 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 39.9 | Last good 2026-09-30 · source benchlm:models |
| 24 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 35.4 | Last good 2026-09-18 · source benchlm:models |
| 25 | [MiMo-V2.6-Pro](https://modelscale.dev/models/mimo-v2-6-pro) | Xiaomi | 34.8 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 33.3 | Last good 2026-10-08 · source benchlm:models |
| 26 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | 33.3 | Last good 2026-10-23 · source benchlm:models |
| 28 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | 32.8 | Observed 2026-11-21 · source benchlm:models |
| 28 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 32.8 | Last good 2026-10-23 · source benchlm:models |
| 30 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 26.8 | Last good 2026-10-08 · source benchlm:models |
| 31 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 25.8 | Observed 2026-11-21 · source benchlm:models |
| 31 | [MiniMax M3.1 Flash](https://modelscale.dev/models/minimax-m3-1-flash) | MiniMax | 25.8 | Last good 2026-10-23 · source benchlm:models |
| 33 | [Mistral Large 4](https://modelscale.dev/models/mistral-large-4) | Mistral | 24.7 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 21.2 | Last good 2026-09-28 · source benchlm:models |
| 35 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 19.7 | Last good 2026-10-23 · source benchlm:models |
| 36 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 14.1 | Last good 2026-09-18 · source benchlm:models |
| 37 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 13.1 | Observed 2026-11-21 · source benchlm:models |
| 38 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 12.6 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 12.6 | Last good 2026-10-23 · source benchlm:models |
| 40 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 11.6 | Last good 2026-09-30 · source benchlm:models |
| 41 | [Muse Spark Open](https://modelscale.dev/models/muse-spark-open) | Meta | 8.1 | Last good 2026-10-23 · source benchlm:models |
| 42 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 5.6 | Observed 2026-11-21 · source benchlm:models |
| 43 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | 3.0 | Observed 2026-11-21 · source benchlm:models |
| 44 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 2.0 | Last good 2026-10-19 · source benchlm:models |
| 45 | [Gemini 3.5 Flash-Lite](https://modelscale.dev/models/gemini-3-5-flash-lite) | Google | 1.0 | Last good 2026-09-30 · source benchlm:models |
| 45 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 1.0 | Last good 2026-10-23 · source benchlm:models |
| 47 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 0.5 | Last good 2026-10-08 · source benchlm:models |
| 47 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 0.5 | Last good 2026-10-08 · source benchlm:models |
| 49 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | 0.0 | Last good 2026-10-06 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
