# BabaIsBench 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://modelchoice.dev/leaderboards/benchmarks/external-baba-is-bench

BabaIsBench (Baba Is You intro levels, pass@1). Every model the catalog carries a published BabaIsBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Agent plays through a text interface in the Harbor framework |
| Tasks | 8 intro levels of Baba Is You, three attempts per level (Stage 0); 15 further levels run once (Stage 1) |
| Difficulty | Rule-rewriting puzzles that need planning over many moves |
| Published by | [Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (Quesma)](https://quesma.com/blog/baba-is-bench/) |

Quesma's BabaIsBench has LLM agents play the puzzle game Baba Is You through a text interface, where a level is won by pushing word tiles around to rewrite its rules. The score here is the first-attempt pass rate on the eight intro levels.

## BabaIsBench ranking

30 models with a published BabaIsBench 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 | Agent plays through a text interface in the Harbor framework | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5](https://modelchoice.dev/models/claude-fable-5) | Anthropic | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 96 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 96 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GLM-5.3](https://modelchoice.dev/models/glm-5-3) | Z.AI | 96 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 96 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 96 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 92 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 88 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 88 | Observed 2026-11-21 · source benchlm:models |
| 15 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 88 | Observed 2026-11-21 · source benchlm:models |
| 18 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 75 | Observed 2026-11-21 · source benchlm:models |
| 18 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 75 | Last good 2026-11-18 · source benchlm:models |
| 18 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 75 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 67 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GLM-5.3-Flash](https://modelchoice.dev/models/glm-5-3-flash) | Z.AI | 67 | Observed 2026-11-21 · source benchlm:models |
| 23 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 63 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 58 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Hy3](https://modelchoice.dev/models/hy3) | Tencent | 54 | Observed 2026-11-21 · source benchlm:models |
| 26 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 46 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Muse Spark 1.3](https://modelchoice.dev/models/muse-spark-1-3) | Meta | 46 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 29 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 25 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Qwen3.8-27B](https://modelchoice.dev/models/qwen3-8-27b) | Alibaba | 21 | 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.
