Task results
Best moves in an undisclosed game (Mystery Game Puzzles)
Puzzles in a puzzle-oriented variant of a well-known game, where the model picks the best next move.
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1–2 | GPT-6 Astra | OpenAI | Rating 82.4 ±8.0 | $10 | $50 | 1.05M | OpenAI Released 2026-09 Price $10 / $50 Length 1.05M | ||||
| 1–3 | GPT-6.1 Sol | OpenAI | Rating 78.0 ±8.7 | $2 | $10 | 1.05M | OpenAI Released 2026-09 Price $2 / $10 Length 1.05M | ||||
| 2–8 | Claude Opus 5.5 | Anthropic | Rating 68.1 ±9.8 | $4 | $20 | 1M | Anthropic Released 2026-09 Price $4 / $20 Length 1M | ||||
| 3–11 | Claude Sonnet 5.5 | Anthropic | Rating 61.4 ±10.4 | $2 | $10 | 1M | Anthropic Released 2026-09 Price $2 / $10 Length 1M | ||||
| 3–12 | Gemini 4 Argon | Rating 60.3 ±10.4 | $2 | $10 | 1.05M | Google Released 2026-09 Price $2 / $10 Length 1.05M | |||||
| 3–14 | Claude Opus 5 | Anthropic | Rating 54.8 ±10.7 | $5 | $25 | 1M | Anthropic Released 2026-07 Price $5 / $25 Length 1M | ||||
| 3–14 | Claude Fable 5.1 | Anthropic | Rating 53.7 ±10.7 | $10 | $50 | 1M | Anthropic Released 2026-09 Price $10 / $50 Length 1M | ||||
| 3–14 | GPT-5.6 Sol | OpenAI | Rating 53.7 ±10.7 | $4 | $20 | 1.05M | OpenAI Released 2026-07 Price $4 / $20 Length 1.05M | ||||
| 4–16 | GPT-5.5 | OpenAI | Rating 51.5 ±10.8 | $5 | $30 | 1.05M | OpenAI Released 2026-04 Price $5 / $30 Length 1.05M | ||||
| 4–16 | GPT-6 Sol | OpenAI | Rating 51.5 ±10.8 | $2 | $10 | 1.05M | OpenAI Released 2026-09 Price $2 / $10 Length 1.05M | ||||
| 4–16 | Claude Fable 5 | Anthropic | Rating 47.1 ±10.8 | $10 | $50 | 1M | Anthropic Released 2026-06 Price $10 / $50 Length 1M | ||||
| 5–17 | Muse Wonder | Meta | Rating 46.0 ±10.8 | $4 | $20 | 1.05M | Meta Released 2026-10 Price $4 / $20 Length 1.05M | ||||
| 6–20 | DeepSeek-V4.1 Flash (2026-10) | DeepSeek | Rating 43.8 ±10.8 | $0.15 | $0.6 | 1M | DeepSeek Released 2026-10 Price $0.15 / $0.6 Length 1M | ||||
| 6–25 | Gemini 3.8 Flash | Rating 41.6 ±10.8 | $0.75 | $3.75 | 1.05M | Google Released 2026-09 Price $0.75 / $3.75 Length 1.05M | |||||
| 9–30 | DeepSeek-V4.1 Flash | DeepSeek | Rating 37.2 ±10.7 | — | — | 1M | DeepSeek Released 2026-09 Price — Length 1M | ||||
| 9–30 | DeepSeek-V4 Pro (2026-08) | DeepSeek | Rating 37.2 ±10.7 | $0.66 | $1.98 | 1M | DeepSeek Released 2026-08 Price $0.66 / $1.98 Length 1M | ||||
| 12–35 | Qwen3.8 Max | Alibaba | Rating 31.7 ±10.5 | $2 | $6 | 1M | Alibaba Released 2026-08 Price $2 / $6 Length 1M | ||||
| 13–37 | Gemini 3.7 Flash | Rating 30.6 ±10.5 | $0.75 | $3.75 | 1.05M | Google Released 2026-08 Price $0.75 / $3.75 Length 1.05M | |||||
| 13–37 | GPT-5.4 | OpenAI | Rating 30.6 ±10.5 | $2.5 | $15 | 1.05M | OpenAI Released 2026-03 Price $2.5 / $15 Length 1.05M | ||||
| 13–37 | Claude Opus 4.8 | Anthropic | Rating 29.5 ±10.4 | $5 | $25 | 1M | Anthropic Released 2026-05 Price $5 / $25 Length 1M | ||||
| 14–39 | Claude Sonnet 5 | Anthropic | Rating 28.4 ±10.4 | $2 | $10 | 1M | Anthropic Released 2026-06 Price $2 / $10 Length 1M | ||||
| 14–39 | GPT-5.6 Terra | OpenAI | Rating 28.4 ±10.4 | $2 | $12 | 1.05M | OpenAI Released 2026-07 Price $2 / $12 Length 1.05M | ||||
| 14–41 | DeepSeek-V4 Flash (2026-07) | DeepSeek | Rating 27.3 ±10.3 | — | — | 1M | DeepSeek Released 2026-07 Price — Length 1M | ||||
| 14–41 | Gemini 3.1 Pro (preview) | Rating 27.3 ±10.3 | $2 | $12 | 1.05M | Google Released 2026-02 Price $2 / $12 Length 1.05M | |||||
| 14–41 | Grok 4.6 | xAI | Rating 27.3 ±10.3 | $2 | $6 | 500K | xAI Released 2026-08 Price $2 / $6 Length 500K | ||||
| 15–43 | GLM-5.3 | Z.ai | Rating 26.2 ±10.2 | $1.4 | $4.4 | 1M | Z.ai Released 2026-08 Price $1.4 / $4.4 Length 1M | ||||
| 15–45 | Gemini 3.5 Flash | Rating 25.1 ±10.1 | $1.5 | $9 | 1.05M | Google Released 2026-05 Price $1.5 / $9 Length 1.05M | |||||
| 15–45 | Qwen3.7 Max | Alibaba | Rating 25.1 ±10.1 | $2.5 | $7.5 | 1M | Alibaba Released 2026-05 Price $2.5 / $7.5 Length 1M | ||||
| 15–49 | Claude Haiku 5.5 | Anthropic | Rating 22.9 ±9.9 | $0.1 | $0.5 | 1M | Anthropic Released 2026-10 Price $0.1 / $0.5 Length 1M | ||||
| 15–49 | Gemini 3.6 Flash | Rating 22.9 ±9.9 | $0.75 | $3.75 | 1.05M | Google Released 2026-07 Price $0.75 / $3.75 Length 1.05M | |||||
| 17–52 | Grok 4.7 | xAI | Rating 21.8 ±9.8 | $2 | $6 | 500K | xAI Released 2026-09 Price $2 / $6 Length 500K | ||||
| 17–52 | o3 | OpenAI | Rating 21.8 ±9.8 | $2 | $8 | 200K | OpenAI Released 2025-04 Price $2 / $8 Length 200K | ||||
| 17–58 | Claude Opus 4.7 | Anthropic | Rating 20.7 ±9.7 | $5 | $25 | 1M | Anthropic Released 2026-04 Price $5 / $25 Length 1M | ||||
| 17–60 | Gemini 3 Flash (preview) | Rating 18.5 ±9.5 | $0.5 | $3 | 1M | Google Released 2025-12 Price $0.5 / $3 Length 1M | |||||
| 17–60 | Kimi K3 | Moonshot | Rating 18.5 ±9.5 | $3 | $15 | 1.05M | Moonshot Released 2026-07 Price $3 / $15 Length 1.05M | ||||
| 18–60 | Claude Opus 4.6 | Anthropic | Rating 17.4 ±9.4 | $5 | $25 | 1M | Anthropic Released 2026-02 Price $5 / $25 Length 1M | ||||
| 18–60 | Muse Spark 1.3 | Meta | Rating 17.4 ±9.6 | $1.25 | $4.25 | 1.05M | Meta Released 2026-09 Price $1.25 / $4.25 Length 1.05M | ||||
| 21–60 | GPT-5.2 | OpenAI | Rating 15.2 ±9.1 | $1.75 | $14 | 400K | OpenAI Released 2025-12 Price $1.75 / $14 Length 400K | ||||
| 21–60 | GPT-5 | OpenAI | Rating 15.2 ±9.1 | $1.25 | $10 | 400K | OpenAI Released 2025-08 Price $1.25 / $10 Length 400K | ||||
| 23–63 | Claude Opus 4.5 | Anthropic | Rating 14.1 ±9.0 | $5 | $25 | 200K | Anthropic Released 2025-11 Price $5 / $25 Length 200K | ||||
| 23–63 | Qwen3.6 35B A3B | Alibaba | Rating 14.1 ±9.0 | $0.375 | $2.25 | 262.1K | Alibaba Released 2026-04 Price $0.375 / $2.25 Length 262.1K | ||||
| 26–64 | Claude Opus 4.1 | Anthropic | Rating 13.0 ±8.8 | — | — | 200K | Anthropic Released 2025-08 Price — Length 200K | ||||
| 26–64 | GPT-5.6 Luna | OpenAI | Rating 13.0 ±8.8 | $0.2 | $1.2 | 1.05M | OpenAI Released 2026-07 Price $0.2 / $1.2 Length 1.05M | ||||
| 27–64 | NVIDIA Nemotron 3 Ultra | NVIDIA | Rating 11.9 ±8.7 | — | — | 131.1K | NVIDIA Released 2026-06 Price — Length 131.1K | ||||
| 27–64 | Qwen3.5 Flash | Alibaba | Rating 11.9 ±8.7 | $0.1 | $0.4 | 1M | Alibaba Released 2026-02 Price $0.1 / $0.4 Length 1M | ||||
| 29–65 | Gemini 3.5 Flash-Lite | Rating 10.8 ±8.5 | $0.3 | $2.5 | 1.05M | Google Released 2026-07 Price $0.3 / $2.5 Length 1.05M | |||||
| 29–65 | GLM-5.2 | Z.ai | Rating 10.8 ±8.5 | $1.4 | $4.4 | 1M | Z.ai Released 2026-06 Price $1.4 / $4.4 Length 1M | ||||
| 29–65 | GPT-5.1 | OpenAI | Rating 10.8 ±8.5 | $1.25 | $10 | 400K | OpenAI Released 2025-11 Price $1.25 / $10 Length 400K | ||||
| 29–65 | Qwen3.6 Max (preview) | Alibaba | Rating 10.8 ±8.5 | $1.3 | $7.8 | 240K | Alibaba Released 2026-04 Price $1.3 / $7.8 Length 240K | ||||
| 31–68 | Kimi K2.6 | Moonshot | Rating 9.7 ±8.3 | $0.95 | $4 | 262.1K | Moonshot Released 2026-04 Price $0.95 / $4 Length 262.1K | ||||
| 31–68 | Qwen3.5 397B A17B | Alibaba | Rating 9.7 ±8.3 | $0.6 | $3.6 | 262.1K | Alibaba Released 2026-02 Price $0.6 / $3.6 Length 262.1K | ||||
| 31–68 | Qwen3.6 Flash | Alibaba | Rating 9.7 ±8.3 | $0.25 | $1.5 | 1M | Alibaba Released 2026-04 Price $0.25 / $1.5 Length 1M | ||||
| 33–70 | Claude Sonnet 4.5 | Anthropic | Rating 8.6 ±8.2 | $3 | $15 | 200K | Anthropic Released 2025-09 Price $3 / $15 Length 200K | ||||
| 33–70 | DeepSeek-V4 Pro | DeepSeek | Rating 8.6 ±8.2 | $0.66 | $1.98 | 1M | DeepSeek Released 2026-04 Price $0.66 / $1.98 Length 1M | ||||
| 33–70 | Mistral Large 4 | Mistral | Rating 8.6 ±8.2 | $1.36 | $4.18 | 524.3K | Mistral Released 2026-10 Price $1.36 / $4.18 Length 524.3K | ||||
| 33–70 | Qwen3.5 122B A10B | Alibaba | Rating 8.6 ±8.2 | $0.4 | $3.2 | 262.1K | Alibaba Released 2026-02 Price $0.4 / $3.2 Length 262.1K | ||||
| 33–70 | Qwen3.5 Plus | Alibaba | Rating 8.6 ±8.2 | $0.4 | $2.4 | 1M | Alibaba Released 2026-02 Price $0.4 / $2.4 Length 1M | ||||
| 33–70 | Qwen3.7 Plus | Alibaba | Rating 8.6 ±8.2 | $0.4 | $1.6 | 1M | Alibaba Released 2026-06 Price $0.4 / $1.6 Length 1M | ||||
| 34–70 | Claude Sonnet 4.6 | Anthropic | Rating 7.5 ±8.0 | $3 | $15 | 1M | Anthropic Released 2026-02 Price $3 / $15 Length 1M | ||||
| 34–74 | Qwen3.7 Flash | Alibaba | Rating 6.4 ±7.7 | $0.03 | $0.13 | 991K | Alibaba Released 2026-07 Price $0.03 / $0.13 Length 991K | ||||
| 40–77 | GPT-4 (2023-06) | OpenAI | Rating 3.1 ±7.1 | — | — | — | OpenAI Released 2023-06 Price — Length — | ||||
| 40–77 | GPT-4o mini | OpenAI | Rating 3.1 ±7.1 | — | — | 128K | OpenAI Released 2024-07 Price — Length 128K | ||||
| 40–77 | Qwen3.6 Plus | Alibaba | Rating 3.1 ±7.1 | $0.5 | $3 | 1M | Alibaba Released 2026-03 Price $0.5 / $3 Length 1M | ||||
| 42–77 | GPT-5.4 mini | OpenAI | Rating 2.0 ±6.8 | $0.75 | $4.5 | 400K | OpenAI Released 2026-03 Price $0.75 / $4.5 Length 400K | ||||
| 46–77 | GPT-5 mini | OpenAI | Rating 0.9 ±6.5 | $0.25 | $2 | 400K | OpenAI Released 2025-08 Price $0.25 / $2 Length 400K | ||||
| 50–78 | GPT-5.4 nano | OpenAI | Rating 0.0 ±6.2 | $0.2 | $1.25 | 400K | OpenAI Released 2026-03 Price $0.2 / $1.25 Length 400K | ||||
| 50–78 | GPT-5 nano | OpenAI | Rating 0.0 ±6.2 | $0.05 | $0.4 | 400K | OpenAI Released 2025-08 Price $0.05 / $0.4 Length 400K | ||||
| 50–78 | Qwen3 235B A22B (thinking) | Alibaba | Rating 0.0 ±6.2 | — | — | 262.1K | Alibaba Released 2025-07 Price — Length 262.1K | ||||
| 53–79 | GLM-5.3 Flash | Z.ai | Rating 0.0 ±5.9 | $0.15 | $0.5 | 1M | Z.ai Released 2026-08 Price $0.15 / $0.5 Length 1M | ||||
| 53–79 | MiniMax-M3 | MiniMax | Rating 0.0 ±5.9 | $0.3 | $1.2 | 1.05M | MiniMax Released 2026-06 Price $0.3 / $1.2 Length 1.05M | ||||
| 60–79 | GPT-4.1 mini | OpenAI | Rating 0.0 ±5.5 | — | — | 1.05M | OpenAI Released 2025-04 Price — Length 1.05M | ||||
| 60–79 | GPT-6 Luna | OpenAI | Rating 0.0 ±5.5 | $0.1 | $0.5 | 1.05M | OpenAI Released 2026-09 Price $0.1 / $0.5 Length 1.05M | ||||
| 60–79 | o3-mini | OpenAI | Rating 0.0 ±5.5 | $1.1 | $4.4 | 200K | OpenAI Released 2025-01 Price $1.1 / $4.4 Length 200K | ||||
| 60–79 | Qwen3.6 27B | Alibaba | Rating 0.0 ±5.5 | $0.6 | $3.6 | 262.1K | Alibaba Released 2026-04 Price $0.6 / $3.6 Length 262.1K | ||||
| 61–79 | Inkling Small | Thinking Machines | Rating 0.0 ±5.2 | $0.58 | $1.44 | 524.3K | Thinking Machines Released 2026-07 Price $0.58 / $1.44 Length 524.3K | ||||
| 61–79 | o4-mini | OpenAI | Rating 0.0 ±4.7 | $1.1 | $4.4 | 200K | OpenAI Released 2025-04 Price $1.1 / $4.4 Length 200K | ||||
| 61–79 | Qwen3 Max (instruct) | Alibaba | Rating 0.0 ±4.7 | — | — | 258K | Alibaba Released 2025-09 Price — Length 258K | ||||
| 66–79 | GPT-3.5 Turbo (2024-01) | OpenAI | Rating 0.0 ±3.7 | — | — | 16.4K | OpenAI Released 2024-01 Price — Length 16.4K | ||||
| 69–79 | GPT-OSS 120B | OpenAI | Rating 0.0 ±3.0 | — | — | 128K | OpenAI Released 2025-08 Price — Length 128K |
Best accuracy over time
2023-06-13Release date2026-10-17
How to read this page
- To prevent game-specific preparation, the game's name, the prompt and example positions are not published. 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