# StealthMark leaderboard

external 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/external-stealth-mark

StealthMark Intelligence Benchmarks (overall score). Every model the catalog carries a published StealthMark value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Private instructions, blind judging, rendered references and playable game levels |
| Tasks | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon |
| Difficulty | Chained physical reasoning, planning without tools and precise visual construction |
| Published by | [StealthMark: The AI Benchmark Explained (Stealth Models)](https://stealthmodels.com/stealthmark) |

StealthMark, from Stealth Models, scores a model out of 100 on eight original tasks: four on physical reasoning and multi-step planning, and four on producing a precise picture from a brief. The exact instructions are kept private so models can't be tuned to them.

## StealthMark ranking

43 models with a published StealthMark 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 | Private instructions, blind judging, rendered references and playable game levels | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 74.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 72.6 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 70.2 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 67.8 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 67.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 62.9 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 62.4 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-6.1 Terra](https://modelscale.dev/models/gpt-6-1-terra) | OpenAI | 60.4 | Observed 2026-11-21 · source benchlm:models |
| 9 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 59.1 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Muse Wonder](https://modelscale.dev/models/muse-wonder) | Meta | 57.0 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 56.7 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 53.7 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 52.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 52.0 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 51.5 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 50.6 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | 49.5 | Observed 2026-11-21 · source benchlm:models |
| 18 | [MiMo-V2.6-Flash](https://modelscale.dev/models/mimo-v2-6-flash) | Xiaomi | 49.3 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 47.9 | Observed 2026-11-21 · source benchlm:models |
| 19 | [MiMo-V2.6-Pro](https://modelscale.dev/models/mimo-v2-6-pro) | Xiaomi | 47.9 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 47.2 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 45.8 | Observed 2026-11-21 · source benchlm:models |
| 23 | [MiniMax M3.1 Flash](https://modelscale.dev/models/minimax-m3-1-flash) | MiniMax | 45.4 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Muse Spark Open](https://modelscale.dev/models/muse-spark-open) | Meta | 44.1 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Hy4 preview](https://modelscale.dev/models/hy4-preview) | Tencent | 43.9 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Mistral Large 4](https://modelscale.dev/models/mistral-large-4) | Mistral | 43.3 | Observed 2026-11-21 · source benchlm:models |
| 27 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 42.8 | Observed 2026-11-21 · source benchlm:models |
| 27 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 42.8 | Last good 2026-11-18 · source benchlm:models |
| 29 | [Ling 3.1 Flash](https://modelscale.dev/models/ling-3-1-flash) | InclusionAI | 42.4 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 39.5 | Observed 2026-11-21 · source benchlm:models |
| 31 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 39.1 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | 39.0 | Observed 2026-11-21 · source benchlm:models |
| 33 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 38.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 37.8 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 36.5 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 32.4 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | 31.9 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemma 4 31B](https://modelscale.dev/models/gemma-4-31b) | Google | 29.5 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 27.5 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Gemma 4 26B A4B](https://modelscale.dev/models/gemma-4-26b-a4b) | Google | 21.2 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 20.8 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 16.7 | Observed 2026-11-21 · source benchlm:models |
| 43 | [MAI-Thinking-1](https://modelscale.dev/models/mai-thinking-1) | Microsoft | 14.1 | 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.
