# Terminal-Bench 2.1 (Vals) 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://modelchoice.dev/leaderboards/benchmarks/agentic-vals-terminal-bench21

Terminal-Bench 2.1, Vals AI run. Every model the catalog carries a published Terminal-Bench 2.1 (Vals) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Task success rate |
| Tasks | Difficult terminal tasks |
| Difficulty | Frontier agentic |
| Published by | [Vals AI Terminal-Bench 2.1, Vals AI run leaderboard](https://www.vals.ai/benchmarks/terminal-bench-2-1) |

Vals AI’s independent run of the Terminal-Bench 2.1 terminal-task suite with published easy, medium, and hard splits.

## Terminal-Bench 2.1 (Vals) ranking

70 models with a published Terminal-Bench 2.1 (Vals) 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 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 87.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 87.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 85.8 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 85.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 84.6 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 81.3 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 80.9 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude Fable 5](https://modelchoice.dev/models/claude-fable-5) | Anthropic | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 11 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 79.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 78.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 77.5 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 77.5 | Observed 2026-11-21 · source benchlm:models |
| 15 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 76.4 | Observed 2026-11-21 · source benchlm:models |
| 15 | [MiMo-V2.6-Flash](https://modelchoice.dev/models/mimo-v2-6-flash) | Xiaomi | 76.4 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 74.5 | Observed 2026-11-21 · source benchlm:models |
| 17 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 74.5 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 73.8 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Grok 4.7](https://modelchoice.dev/models/grok-4-7) | xAI | 73.4 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 73.0 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Muse Spark 1.3](https://modelchoice.dev/models/muse-spark-1-3) | Meta | 72.3 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 71.9 | Observed 2026-11-21 · source benchlm:models |
| 25 | [GLM-5.3](https://modelchoice.dev/models/glm-5-3) | Z.AI | 71.5 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 70.8 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Muse Spark 1.2](https://modelchoice.dev/models/muse-spark-1-2) | Meta | 69.7 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 69.3 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 68.5 | Observed 2026-11-21 · source benchlm:models |
| 30 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 67.8 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 67.8 | Observed 2026-11-21 · source benchlm:models |
| 30 | [MiMo-V2.6-Pro](https://modelchoice.dev/models/mimo-v2-6-pro) | Xiaomi | 67.8 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 67.4 | Observed 2026-11-21 · source benchlm:models |
| 34 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 67.0 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Kimi K2.7 Code](https://modelchoice.dev/models/kimi-k2-7-code) | Moonshot AI | 67.0 | Observed 2026-11-21 · source benchlm:models |
| 36 | [GLM-5.3-Flash](https://modelchoice.dev/models/glm-5-3-flash) | Z.AI | 62.9 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 61.0 | Observed 2026-11-21 · source benchlm:models |
| 38 | [MiMo-V2.5](https://modelchoice.dev/models/mimo-v2-5) | Xiaomi | 60.7 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Composer 2.5](https://modelchoice.dev/models/composer-2-5) | Cursor | 58.4 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Qwen3.8-27B](https://modelchoice.dev/models/qwen3-8-27b) | Alibaba | 58.4 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 57.7 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Claude Sonnet 4.6](https://modelchoice.dev/models/claude-sonnet-4-6) | Anthropic | 57.3 | Observed 2026-11-21 · source benchlm:models |
| 42 | [MiMo-V2.5-Pro](https://modelchoice.dev/models/mimo-v2-5-pro) | Xiaomi | 57.3 | Observed 2026-11-21 · source benchlm:models |
| 44 | [GLM-5.1](https://modelchoice.dev/models/glm-5-1) | Z.AI | 56.9 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Hy4 preview](https://modelchoice.dev/models/hy4-preview) | Tencent | 55.1 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Inkling-Small](https://modelchoice.dev/models/inkling-small) | Thinking Machines Lab | 55.1 | Observed 2026-11-21 · source benchlm:models |
| 47 | [DeepSeek V4 Pro](https://modelchoice.dev/models/deepseek-v4-pro) | DeepSeek | 54.7 | Observed 2026-11-21 · source benchlm:models |
| 47 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 54.7 | Last good 2026-11-18 · source benchlm:models |
| 47 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 54.7 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Gemini 3 Flash](https://modelchoice.dev/models/gemini-3-flash) | Google | 53.9 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 53.6 | Observed 2026-11-21 · source benchlm:models |
| 51 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 53.6 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 53.2 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 52.8 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Nemotron 3 Ultra](https://modelchoice.dev/models/nemotron-3-ultra-500b) | NVIDIA | 50.9 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Gemini 3.5 Flash-Lite](https://modelchoice.dev/models/gemini-3-5-flash-lite) | Google | 50.2 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Ling 3.0 Flash](https://modelchoice.dev/models/ling-3-0-flash) | InclusionAI | 50.2 | Observed 2026-11-21 · source benchlm:models |
| 58 | [MiniMax M2.7](https://modelchoice.dev/models/minimax-m2-7) | MiniMax | 48.7 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Inkling](https://modelchoice.dev/models/inkling) | Thinking Machines Lab | 47.6 | Observed 2026-11-21 · source benchlm:models |
| 60 | [Grok 4.20](https://modelchoice.dev/models/grok-4-20-beta) | xAI | 44.2 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Claude Haiku 4.5](https://modelchoice.dev/models/claude-haiku-4-5) | Anthropic | 43.8 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Grok 4.3](https://modelchoice.dev/models/grok-4-3) | xAI | 41.9 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Kimi K2.5 (Reasoning)](https://modelchoice.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 41.9 | Last good 2026-11-18 · source benchlm:models |
| 64 | [GPT-5.4 nano](https://modelchoice.dev/models/gpt-5-4-nano) | OpenAI | 41.6 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Mistral Medium 3.5 128B](https://modelchoice.dev/models/mistral-medium-3-5-128b) | Mistral | 39.0 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Mercury 2.5](https://modelchoice.dev/models/mercury-2-5) | Inception | 34.5 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Gemini 3.1 Flash-Lite](https://modelchoice.dev/models/gemini-3-1-flash-lite) | Google | 34.1 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Laguna M.1](https://modelchoice.dev/models/laguna-m-1) | Poolside | 34.1 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Laguna XS.2](https://modelchoice.dev/models/laguna-xs-2) | Poolside | 25.8 | Observed 2026-11-21 · source benchlm:models |
| 70 | [Command A+](https://modelchoice.dev/models/command-a-plus) | Cohere | 17.6 | Observed 2026-11-21 · 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.
