Task results
Choosing the best chess move (Chess Puzzles)
Positions newly generated with a chess engine, where the model picks the best move for the side to play.
How to read this table
- Higher rows are rated higher. A range like “1–2” means the gap is within the margin of error.
- The score is the share of a shared set of problems the model solved (%).
- ± is how far the score moves when re-measured, so small gaps do not mean much.
- Prices are a guide per million tokens, reading then writing.
- Length is how much text the model can read at once (tokens).
± range of the top model
| Rank | Model | Developer | Accuracy (%) | Evaluated | Input $ /1M | Output $ /1M | Context | Supports | Weights | Released | Price and specs |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1–6 | GPT-6 Astra Pro | OpenAI | Rating 74.7 ±8.9 | — | — | — | OpenAI Released 2026-09 Price — Length — | ||||
| 1–8 | GPT-6 Astra | OpenAI | Rating 72.6 ±9.1 | $10 | $50 | 1.05M | OpenAI Released 2026-09 Price $10 / $50 Length 1.05M | ||||
| 1–16 | GPT-5.6 Sol Pro | OpenAI | Rating 66.3 ±9.7 | — | — | — | OpenAI Released 2026-07 Price — Length — | ||||
| 1–16 | GPT-6.1 Sol | OpenAI | Rating 66.3 ±9.7 | $2 | $10 | 1.05M | OpenAI Released 2026-09 Price $2 / $10 Length 1.05M | ||||
| 1–16 | Claude Opus 5.5 | Anthropic | Rating 65.3 ±9.7 | $4 | $20 | 1M | Anthropic Released 2026-09 Price $4 / $20 Length 1M | ||||
| 1–16 | Gemini 3.7 Flash | Rating 64.2 ±9.8 | $0.75 | $3.75 | 1.05M | Google Released 2026-08 Price $0.75 / $3.75 Length 1.05M | |||||
| 2–18 | GPT-5.5 | OpenAI | Rating 61.1 ±10.0 | $5 | $30 | 1.05M | OpenAI Released 2026-04 Price $5 / $30 Length 1.05M | ||||
| 2–18 | GPT-5.5 Pro | OpenAI | Rating 60.0 ±10.1 | $30 | $180 | 1.05M | OpenAI Released 2026-04 Price $30 / $180 Length 1.05M | ||||
| 3–25 | GPT-5.2 Pro | OpenAI | Rating 57.9 ±10.2 | $21 | $168 | 400K | OpenAI Released 2025-12 Price $21 / $168 Length 400K | ||||
| 3–28 | Claude Sonnet 5.5 | Anthropic | Rating 56.9 ±10.2 | $2 | $10 | 1M | Anthropic Released 2026-09 Price $2 / $10 Length 1M | ||||
| 3–28 | Gemini 4 Argon | Rating 56.9 ±10.2 | $2 | $10 | 1.05M | Google Released 2026-09 Price $2 / $10 Length 1.05M | |||||
| 3–28 | GPT-5.4 Pro | OpenAI | Rating 56.9 ±10.2 | $30 | $180 | 1.05M | OpenAI Released 2026-03 Price $30 / $180 Length 1.05M | ||||
| 3–28 | GPT-5.6 Sol | OpenAI | Rating 56.9 ±10.2 | $4 | $20 | 1.05M | OpenAI Released 2026-07 Price $4 / $20 Length 1.05M | ||||
| 3–31 | Gemini 3.8 Flash | Rating 55.8 ±10.2 | $0.75 | $3.75 | 1.05M | Google Released 2026-09 Price $0.75 / $3.75 Length 1.05M | |||||
| 3–33 | GPT-6 Sol | OpenAI | Rating 53.7 ±10.3 | $2 | $10 | 1.05M | OpenAI Released 2026-09 Price $2 / $10 Length 1.05M | ||||
| 3–35 | Claude Haiku 5.5 | Anthropic | Rating 52.7 ±10.3 | $0.1 | $0.5 | 1M | Anthropic Released 2026-10 Price $0.1 / $0.5 Length 1M | ||||
| 7–38 | Claude Opus 4.8 | Anthropic | Rating 49.5 ±10.4 | $5 | $25 | 1M | Anthropic Released 2026-05 Price $5 / $25 Length 1M | ||||
| 7–38 | Gemini 3.1 Pro (preview) | Rating 48.4 ±10.4 | $2 | $12 | 1.05M | Google Released 2026-02 Price $2 / $12 Length 1.05M | |||||
| 9–46 | Claude Fable 5.1 | Anthropic | Rating 45.3 ±10.4 | $10 | $50 | 1M | Anthropic Released 2026-09 Price $10 / $50 Length 1M | ||||
| 9–46 | DeepSeek-V4.1 Flash | DeepSeek | Rating 45.3 ±10.4 | — | — | 1M | DeepSeek Released 2026-09 Price — Length 1M | ||||
| 9–46 | GPT-5.2 | OpenAI | Rating 45.3 ±10.4 | $1.75 | $14 | 400K | OpenAI Released 2025-12 Price $1.75 / $14 Length 400K | ||||
| 9–46 | GPT-5.4 | OpenAI | Rating 45.3 ±10.4 | $2.5 | $15 | 1.05M | OpenAI Released 2026-03 Price $2.5 / $15 Length 1.05M | ||||
| 9–46 | GPT-5 Pro | OpenAI | Rating 45.3 ±10.4 | $15 | $120 | 400K | OpenAI Released 2025-10 Price $15 / $120 Length 400K | ||||
| 9–47 | Claude Fable 5 | Anthropic | Rating 44.2 ±10.3 | $10 | $50 | 1M | Anthropic Released 2026-06 Price $10 / $50 Length 1M | ||||
| 9–47 | GPT-5.6 Terra | OpenAI | Rating 44.2 ±10.3 | $2 | $12 | 1.05M | OpenAI Released 2026-07 Price $2 / $12 Length 1.05M | ||||
| 10–49 | DeepSeek-V4.1 Flash (2026-10) | DeepSeek | Rating 43.2 ±10.3 | $0.15 | $0.6 | 1M | DeepSeek Released 2026-10 Price $0.15 / $0.6 Length 1M | ||||
| 10–49 | DeepSeek-V4 Pro (2026-08) | DeepSeek | Rating 43.2 ±10.3 | $0.66 | $1.98 | 1M | DeepSeek Released 2026-08 Price $0.66 / $1.98 Length 1M | ||||
| 10–49 | Qwen3.8 Max | Alibaba | Rating 43.2 ±10.3 | $2 | $6 | 1M | Alibaba Released 2026-08 Price $2 / $6 Length 1M | ||||
| 14–50 | Claude Sonnet 5 | Anthropic | Rating 42.1 ±10.3 | $2 | $10 | 1M | Anthropic Released 2026-06 Price $2 / $10 Length 1M | ||||
| 14–50 | Gemini 3.5 Flash | Rating 42.1 ±10.3 | $1.5 | $9 | 1.05M | Google Released 2026-05 Price $1.5 / $9 Length 1.05M | |||||
| 14–50 | GPT-5.4 nano | OpenAI | Rating 42.1 ±10.3 | $0.2 | $1.25 | 400K | OpenAI Released 2026-03 Price $0.2 / $1.25 Length 400K | ||||
| 15–50 | Claude Opus 5 | Anthropic | Rating 40.0 ±10.3 | $5 | $25 | 1M | Anthropic Released 2026-07 Price $5 / $25 Length 1M | ||||
| 15–50 | GPT-5.6 Luna | OpenAI | Rating 40.0 ±10.3 | $0.2 | $1.2 | 1.05M | OpenAI Released 2026-07 Price $0.2 / $1.2 Length 1.05M | ||||
| 16–51 | Gemini 3.6 Flash | Rating 39.0 ±10.2 | $0.75 | $3.75 | 1.05M | Google Released 2026-07 Price $0.75 / $3.75 Length 1.05M | |||||
| 16–51 | GPT-5.1 | OpenAI | Rating 39.0 ±10.2 | $1.25 | $10 | 400K | OpenAI Released 2025-11 Price $1.25 / $10 Length 400K | ||||
| 17–51 | Claude Opus 4.7 | Anthropic | Rating 37.9 ±10.2 | $5 | $25 | 1M | Anthropic Released 2026-04 Price $5 / $25 Length 1M | ||||
| 17–51 | Grok 4.7 | xAI | Rating 37.9 ±10.2 | $2 | $6 | 500K | xAI Released 2026-09 Price $2 / $6 Length 500K | ||||
| 17–52 | Gemini 3 Flash (preview) | Rating 35.8 ±10.1 | $0.5 | $3 | 1M | Google Released 2025-12 Price $0.5 / $3 Length 1M | |||||
| 19–53 | GLM-5.3 | Z.ai | Rating 33.7 ±10.0 | $1.4 | $4.4 | 1M | Z.ai Released 2026-08 Price $1.4 / $4.4 Length 1M | ||||
| 19–53 | Kimi K3 | Moonshot | Rating 33.7 ±10.0 | $3 | $15 | 1.05M | Moonshot Released 2026-07 Price $3 / $15 Length 1.05M | ||||
| 19–53 | Muse Spark 1.3 | Meta | Rating 33.7 ±10.0 | $1.25 | $4.25 | 1.05M | Meta Released 2026-09 Price $1.25 / $4.25 Length 1.05M | ||||
| 19–53 | o3 | OpenAI | Rating 33.7 ±10.0 | $2 | $8 | 200K | OpenAI Released 2025-04 Price $2 / $8 Length 200K | ||||
| 19–53 | Qwen3.8 Max (2026-09) | Alibaba | Rating 33.7 ±10.0 | — | — | 1M | Alibaba Released 2026-09 Price — Length 1M | ||||
| 19–54 | GPT-5 | OpenAI | Rating 32.7 ±9.9 | $1.25 | $10 | 400K | OpenAI Released 2025-08 Price $1.25 / $10 Length 400K | ||||
| 19–54 | GPT-6 Luna | OpenAI | Rating 32.7 ±9.9 | $0.1 | $0.5 | 1.05M | OpenAI Released 2026-09 Price $0.1 / $0.5 Length 1.05M | ||||
| 19–56 | Grok 4.5 | xAI | Rating 31.6 ±9.9 | $2 | $6 | 500K | xAI Released 2026-07 Price $2 / $6 Length 500K | ||||
| 24–59 | Muse Spark 1.1 | Meta | Rating 30.6 ±9.8 | $1.25 | $4.25 | 1M | Meta Released 2026-07 Price $1.25 / $4.25 Length 1M | ||||
| 26–64 | Grok 4.6 | xAI | Rating 29.5 ±9.7 | $2 | $6 | 500K | xAI Released 2026-08 Price $2 / $6 Length 500K | ||||
| 26–64 | Mistral Large 4 | Mistral | Rating 29.5 ±9.7 | $1.36 | $4.18 | 524.3K | Mistral Released 2026-10 Price $1.36 / $4.18 Length 524.3K | ||||
| 29–66 | DeepSeek-V4 Flash (2026-07) | DeepSeek | Rating 28.5 ±9.7 | — | — | 1M | DeepSeek Released 2026-07 Price — Length 1M | ||||
| 34–68 | Grok 4.20 Reasoning | xAI | Rating 25.3 ±9.4 | $1.25 | $2.5 | 2M | xAI Released 2026-02 Price $1.25 / $2.5 Length 2M | ||||
| 38–68 | Muse Spark 1.2 | Meta | Rating 23.2 ±9.2 | $1.25 | $4.25 | 1.05M | Meta Released 2026-08 Price $1.25 / $4.25 Length 1.05M | ||||
| 39–69 | Qwen3.7 Max | Alibaba | Rating 22.1 ±9.1 | $2.5 | $7.5 | 1M | Alibaba Released 2026-05 Price $2.5 / $7.5 Length 1M | ||||
| 44–73 | GPT-5 mini | OpenAI | Rating 20.0 ±8.9 | $0.25 | $2 | 400K | OpenAI Released 2025-08 Price $0.25 / $2 Length 400K | ||||
| 46–74 | Claude Sonnet 4.6 | Anthropic | Rating 19.0 ±8.7 | $3 | $15 | 1M | Anthropic Released 2026-02 Price $3 / $15 Length 1M | ||||
| 46–74 | GPT-5.4 mini | OpenAI | Rating 19.0 ±8.7 | $0.75 | $4.5 | 400K | OpenAI Released 2026-03 Price $0.75 / $4.5 Length 400K | ||||
| 47–75 | GLM-5.2 | Z.ai | Rating 17.9 ±8.6 | $1.4 | $4.4 | 1M | Z.ai Released 2026-06 Price $1.4 / $4.4 Length 1M | ||||
| 47–75 | GPT-5 nano | OpenAI | Rating 17.9 ±8.6 | $0.05 | $0.4 | 400K | OpenAI Released 2025-08 Price $0.05 / $0.4 Length 400K | ||||
| 47–75 | o4-mini | OpenAI | Rating 17.9 ±8.6 | $1.1 | $4.4 | 200K | OpenAI Released 2025-04 Price $1.1 / $4.4 Length 200K | ||||
| 48–75 | Claude Opus 4.6 | Anthropic | Rating 16.9 ±8.4 | $5 | $25 | 1M | Anthropic Released 2026-02 Price $5 / $25 Length 1M | ||||
| 48–75 | Gemini 3.5 Flash-Lite | Rating 16.9 ±8.4 | $0.3 | $2.5 | 1.05M | Google Released 2026-07 Price $0.3 / $2.5 Length 1.05M | |||||
| 48–75 | GLM-4.7 | Z.ai | Rating 16.9 ±8.4 | $0.6 | $2.2 | 204.8K | Z.ai Released 2025-12 Price $0.6 / $2.2 Length 204.8K | ||||
| 48–75 | GLM-5.3 Flash | Z.ai | Rating 16.9 ±8.4 | $0.15 | $0.5 | 1M | Z.ai Released 2026-08 Price $0.15 / $0.5 Length 1M | ||||
| 48–75 | Inkling | Thinking Machines | Rating 16.9 ±8.4 | $1.87 | $4.68 | 262.1K | Thinking Machines Released 2026-07 Price $1.87 / $4.68 Length 262.1K | ||||
| 50–75 | GLM-5.1 | Z.ai | Rating 15.8 ±8.3 | $1.4 | $4.4 | 200K | Z.ai Released 2026-04 Price $1.4 / $4.4 Length 200K | ||||
| 50–75 | Kimi K2.6 | Moonshot | Rating 15.8 ±8.3 | $0.95 | $4 | 262.1K | Moonshot Released 2026-04 Price $0.95 / $4 Length 262.1K | ||||
| 51–77 | DeepSeek-V4 Pro | DeepSeek | Rating 14.8 ±8.1 | $0.66 | $1.98 | 1M | DeepSeek Released 2026-04 Price $0.66 / $1.98 Length 1M | ||||
| 51–77 | Grok 4.3 | xAI | Rating 13.7 ±8.0 | $1.25 | $2.5 | 1M | xAI Released 2026-04 Price $1.25 / $2.5 Length 1M | ||||
| 53–79 | o3-mini | OpenAI | Rating 10.6 ±7.4 | $1.1 | $4.4 | 200K | OpenAI Released 2025-01 Price $1.1 / $4.4 Length 200K | ||||
| 54–80 | Claude Opus 4.5 | Anthropic | Rating 9.5 ±7.2 | $5 | $25 | 200K | Anthropic Released 2025-11 Price $5 / $25 Length 200K | ||||
| 54–80 | Kimi K2.7 Code | Moonshot | Rating 9.5 ±7.2 | $0.95 | $4 | 262.1K | Moonshot Released 2026-06 Price $0.95 / $4 Length 262.1K | ||||
| 54–80 | Qwen3.5 Flash | Alibaba | Rating 9.5 ±7.2 | $0.1 | $0.4 | 1M | Alibaba Released 2026-02 Price $0.1 / $0.4 Length 1M | ||||
| 54–80 | Qwen3.6 Plus | Alibaba | Rating 9.5 ±7.2 | $0.5 | $3 | 1M | Alibaba Released 2026-03 Price $0.5 / $3 Length 1M | ||||
| 55–80 | MiniMax-M3 | MiniMax | Rating 8.5 ±7.0 | $0.3 | $1.2 | 1.05M | MiniMax Released 2026-06 Price $0.3 / $1.2 Length 1.05M | ||||
| 57–80 | Qwen3.6 Flash | Alibaba | Rating 7.4 ±6.7 | $0.25 | $1.5 | 1M | Alibaba Released 2026-04 Price $0.25 / $1.5 Length 1M | ||||
| 67–80 | Claude Sonnet 4.5 | Anthropic | Rating 5.3 ±6.2 | $3 | $15 | 200K | Anthropic Released 2025-09 Price $3 / $15 Length 200K | ||||
| 67–80 | o1 | OpenAI | Rating 5.3 ±6.2 | $15 | $60 | 128K | OpenAI Released 2024-12 Price $15 / $60 Length 128K | ||||
| 69–83 | Claude Haiku 4.5 | Anthropic | Rating 3.2 ±5.6 | $1 | $5 | 200K | Anthropic Released 2025-10 Price $1 / $5 Length 200K | ||||
| 69–83 | Qwen3.5 Plus | Alibaba | Rating 3.2 ±5.6 | $0.4 | $2.4 | 1M | Alibaba Released 2026-02 Price $0.4 / $2.4 Length 1M | ||||
| 70–84 | GPT-4o (2024-08) | OpenAI | Rating 1.1 ±4.9 | $2.5 | $10 | 128K | OpenAI Released 2024-08 Price $2.5 / $10 Length 128K | ||||
| 78–85 | Claude 3 Opus | Anthropic | Rating 0.0 ±3.5 | — | — | — | Anthropic Released 2024-02 Price — Length — | ||||
| 78–85 | GPT-4.1 | OpenAI | Rating 0.0 ±3.5 | $2 | $8 | 1.05M | OpenAI Released 2025-04 Price $2 / $8 Length 1.05M | ||||
| 78–85 | GPT-4o mini | OpenAI | Rating 0.0 ±3.5 | — | — | 128K | OpenAI Released 2024-07 Price — Length 128K | ||||
| 80–85 | GPT-4.1 mini | OpenAI | Rating 0.0 ±2.1 | — | — | 1.05M | OpenAI Released 2025-04 Price — Length 1.05M | ||||
| 81–85 | GPT-4.1 nano | OpenAI | Rating 0.0 ±0.0 | $0.1 | $0.4 | 1.05M | OpenAI Released 2025-04 Price $0.1 / $0.4 Length 1.05M |
Best accuracy over time
2024-02-29Release date2026-10-17
How to read this page
- Each position has a single best move as judged by Stockfish, and a matching move is correct. The value is accuracy.
- The accuracy is the share of problems solved, with the part you could get by guessing removed.
- In the Supports column the icons are, from left: can use tools / can read images / can answer in a fixed format (JSON); faded means not supported or unknown.
- Open-weights models have their contents (the weights) published, so you can also run them on your own computer or server. Models without the open-weights mark are normally used through the developer's own services (apps or API); for some models the weights status is unknown.
- Names such as ChatGPT next to a model are the consumer services its developer offers. Check on the service itself whether that model is available there.
Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-10-24, data sources