# Mystery Game Puzzles → MaxxBench

Calibration · https://benchgap.net/calibration/mysterygamepuzzles/current/to/maxxbench/current · data retrieved 2026-11-18

MaxxBench is estimated from Mystery Game Puzzles with a Hill curve fitted on 13 models measured on both: y = 0.4718 + (0.7734 − 0.4718)·x^6.00 / (0.54996^6.00 + x^6.00), R² = 0.65, cross-validated error 8.8 pp. It is used for 20 estimates.

| Estimated model | Mystery Game Puzzles | MaxxBench | Source |
|---|---|---|---|
| [o3](https://benchgap.net/model/o3.md) | 29.0% | 47.8% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.5 Flash](https://benchgap.net/model/qwen3-5-flash.md) | 20.0% | 47.3% | estimated ± 8.8 pp, medium confidence |
| [Qwen 3.6 Max (preview)](https://benchgap.net/model/qwen3-6-max-preview.md) | 19.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 18.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Claude Sonnet 4.5](https://benchgap.net/model/claude-sonnet-4-5.md) | 17.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 17.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.5 Plus](https://benchgap.net/model/qwen3-5-plus.md) | 17.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 17.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 16.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [GPT-5.1](https://benchgap.net/model/gpt-5-1.md) | 16.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.7 Flash](https://benchgap.net/model/qwen3-7-flash.md) | 15.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [GPT-4o mini](https://benchgap.net/model/gpt-4o-mini.md) | 12.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 12.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [GPT-4.1 mini](https://benchgap.net/model/gpt-4-1-mini.md) | 7.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 7.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [o3-mini](https://benchgap.net/model/o3-mini.md) | 7.0% | 47.2% | estimated ± 8.8 pp, medium confidence |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 5.0% | 47.2% | estimated ± 8.8 pp, low confidence |
| [o4-mini](https://benchgap.net/model/o4-mini.md) | 5.0% | 47.2% | estimated ± 8.8 pp, low confidence |
| [Qwen3 Max](https://benchgap.net/model/qwen3-max.md) | 5.0% | 47.2% | estimated ± 8.8 pp, low confidence |
| [GPT-OSS 120B](https://benchgap.net/model/gpt-oss-120b.md) | 0.0% | 47.2% | estimated ± 8.8 pp, low confidence |

## Fitted on

| Model | Mystery Game Puzzles | MaxxBench |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 52.0% | 63.5% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 59.0% | 63.5% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 71.0% | 76.4% |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 65.0% | 66.9% |
| [DeepSeek V4.1 Flash 1017](https://benchgap.net/model/deepseek-v4-1-flash.md) | 49.0% | 55.6% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 34.0% | 28.1% |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 47.0% | 53.4% |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 33.0% | 56.7% |
| [GLM-5.3-Flash](https://benchgap.net/model/glm-5-3-flash.md) | 8.0% | 55.1% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 21.0% | 46.1% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 58.0% | 69.1% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 84.0% | 71.9% |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 7.0% | 51.7% |
