# Chess Puzzles 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-chess-puzzles

Chess Puzzles (Epoch AI). Every model the catalog carries a published Chess Puzzles value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Exact-match move answer from FEN text input |
| Tasks | 100 programmatically generated chess positions with a single best move |
| Difficulty | Novel chess positions, single best move |
| Published by | [Chess Puzzles (Epoch AI)](https://epoch.ai/benchmarks/chess-puzzles) |

Epoch AI's Chess Puzzles benchmark gives models 100 novel chess positions as FEN text and asks for the single best next move, as judged by Stockfish.

## Chess Puzzles ranking

86 models with a published Chess Puzzles 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 | Exact-match move answer from FEN text input | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 4 Neon](https://modelchoice.dev/models/gemini-4-neon) | Google | 83.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Fable 5.2](https://modelchoice.dev/models/claude-fable-5-2) | Anthropic | 79.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Gemini 4 Carbon](https://modelchoice.dev/models/gemini-4-carbon) | Google | 78.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6.2 Astra](https://modelchoice.dev/models/gpt-6-2-astra) | OpenAI | 78.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 74.0 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 68.0 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 67.0 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 66.0 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 63.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.5 Pro](https://modelchoice.dev/models/gpt-5-5-pro) | OpenAI | 62.0 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Gemini 4 Hydrogen](https://modelchoice.dev/models/gemini-4-hydrogen) | Google | 60.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 59.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 59.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.4 Pro](https://modelchoice.dev/models/gpt-5-4-pro) | OpenAI | 59.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 59.0 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 58.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 56.0 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Claude Haiku 5.5](https://modelchoice.dev/models/claude-haiku-5-5) | Anthropic | 55.0 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 52.0 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 51.0 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 48.0 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-5.2](https://modelchoice.dev/models/gpt-5-2) | OpenAI | 48.0 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 48.0 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Fable 5](https://modelchoice.dev/models/claude-fable-5) | Anthropic | 47.0 | Observed 2026-11-21 · source benchlm:models |
| 24 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 47.0 | Observed 2026-11-21 · source benchlm:models |
| 26 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 46.0 | Last good 2026-11-18 · source benchlm:models |
| 26 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 46.0 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 46.0 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 45.0 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 45.0 | Observed 2026-11-21 · source benchlm:models |
| 29 | [GPT-5.4 nano](https://modelchoice.dev/models/gpt-5-4-nano) | OpenAI | 45.0 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 45.0 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 43.0 | Observed 2026-11-21 · source benchlm:models |
| 33 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 43.0 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GPT-5.1](https://modelchoice.dev/models/gpt-5-1) | OpenAI | 42.0 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 41.0 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Grok 4.7](https://modelchoice.dev/models/grok-4-7) | xAI | 41.0 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemini 3 Flash](https://modelchoice.dev/models/gemini-3-flash) | Google | 40.0 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 40.0 | Observed 2026-11-21 · source benchlm:models |
| 40 | [GLM-5.3](https://modelchoice.dev/models/glm-5-3) | Z.AI | 37.0 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Muse Spark 1.3](https://modelchoice.dev/models/muse-spark-1-3) | Meta | 37.0 | Observed 2026-11-21 · source benchlm:models |
| 42 | [GPT-5](https://modelchoice.dev/models/gpt-5) | OpenAI | 36.0 | Observed 2026-11-21 · source benchlm:models |
| 42 | [GPT-5 (high)](https://modelchoice.dev/models/gpt-5-high) | OpenAI | 36.0 | Last good 2026-11-18 · source benchlm:models |
| 42 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 36.0 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 36.0 | Observed 2026-11-21 · source benchlm:models |
| 42 | [o3](https://modelchoice.dev/models/o3) | OpenAI | 36.0 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 35.0 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 34.0 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 33.0 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Mistral Large 4](https://modelchoice.dev/models/mistral-large-4) | Mistral | 33.0 | Observed 2026-11-21 · source benchlm:models |
| 51 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 32.0 | Observed 2026-11-21 · source benchlm:models |
| 51 | [GPT-5 (medium)](https://modelchoice.dev/models/gpt-5-medium) | OpenAI | 32.0 | Last good 2026-11-18 · source benchlm:models |
| 53 | [Grok 4.20](https://modelchoice.dev/models/grok-4-20-beta) | xAI | 29.0 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Muse Spark 1.2](https://modelchoice.dev/models/muse-spark-1-2) | Meta | 27.0 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 27.0 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Seed 2.1 Turbo](https://modelchoice.dev/models/seed-2-1-turbo) | ByteDance | 26.0 | Observed 2026-11-21 · source benchlm:models |
| 57 | [Claude Sonnet 4.6](https://modelchoice.dev/models/claude-sonnet-4-6) | Anthropic | 23.0 | Observed 2026-11-21 · source benchlm:models |
| 58 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 22.0 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 21.0 | Observed 2026-11-21 · source benchlm:models |
| 59 | [GLM-4.7](https://modelchoice.dev/models/glm-4-7) | Z.AI | 21.0 | Observed 2026-11-21 · source benchlm:models |
| 59 | [GLM-5.3-Flash](https://modelchoice.dev/models/glm-5-3-flash) | Z.AI | 21.0 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Inkling](https://modelchoice.dev/models/inkling) | Thinking Machines Lab | 21.0 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Seed 2.1 Pro](https://modelchoice.dev/models/seed-2-1-pro) | ByteDance | 21.0 | Observed 2026-11-21 · source benchlm:models |
| 64 | [GLM-5.1](https://modelchoice.dev/models/glm-5-1) | Z.AI | 20.0 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 20.0 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Grok 4.3](https://modelchoice.dev/models/grok-4-3) | xAI | 18.0 | Observed 2026-11-21 · source benchlm:models |
| 67 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 17.0 | Observed 2026-11-21 · source benchlm:models |
| 67 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 17.0 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Gemini 3.5 Flash-Lite](https://modelchoice.dev/models/gemini-3-5-flash-lite) | Google | 16.0 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 16.0 | Observed 2026-11-21 · source benchlm:models |
| 71 | [o3-mini](https://modelchoice.dev/models/o3-mini) | OpenAI | 15.0 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 14.0 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Kimi K2.7 Code](https://modelchoice.dev/models/kimi-k2-7-code) | Moonshot AI | 14.0 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Qwen3.5 Flash](https://modelchoice.dev/models/qwen3-5-flash) | Alibaba | 14.0 | Observed 2026-11-21 · source benchlm:models |
| 75 | [o4-mini](https://modelchoice.dev/models/o4-mini) | OpenAI | 13.0 | Observed 2026-11-21 · source benchlm:models |
| 75 | [o4-mini (high)](https://modelchoice.dev/models/o4-mini-high) | OpenAI | 13.0 | Last good 2026-11-18 · source benchlm:models |
| 77 | [GPT-4.1](https://modelchoice.dev/models/gpt-4-1) | OpenAI | 11.0 | Observed 2026-11-21 · source benchlm:models |
| 78 | [Claude Sonnet 4.5](https://modelchoice.dev/models/claude-sonnet-4-5) | Anthropic | 10.0 | Observed 2026-11-21 · source benchlm:models |
| 78 | [o1](https://modelchoice.dev/models/o1) | OpenAI | 10.0 | Observed 2026-11-21 · source benchlm:models |
| 80 | [GPT-4o](https://modelchoice.dev/models/gpt-4o) | OpenAI | 9.0 | Observed 2026-11-21 · source benchlm:models |
| 80 | [Qwen3.5 Plus](https://modelchoice.dev/models/qwen3-5-plus) | Alibaba | 9.0 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Claude Haiku 4.5](https://modelchoice.dev/models/claude-haiku-4-5) | Anthropic | 8.0 | Observed 2026-11-21 · source benchlm:models |
| 83 | [Claude 3 Opus](https://modelchoice.dev/models/claude-3-opus) | Anthropic | 4.0 | Observed 2026-11-21 · source benchlm:models |
| 84 | [GPT-4o mini](https://modelchoice.dev/models/gpt-4o-mini) | OpenAI | 3.0 | Observed 2026-11-21 · source benchlm:models |
| 85 | [GPT-4.1 mini](https://modelchoice.dev/models/gpt-4-1-mini) | OpenAI | 1.0 | Observed 2026-11-21 · source benchlm:models |
| 86 | [GPT-4.1 nano](https://modelchoice.dev/models/gpt-4-1-nano) | OpenAI | 0.0 | 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.
