# Chess Puzzles → EBR-bench

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

EBR-bench is estimated from Chess Puzzles with a inverse Michaelis–Menten curve fitted on 28 models measured on both: y = 0.46996·(x − 0.0000) / (0.0000 + 1.1932 − x), R² = 0.82, cross-validated error 12.3 pp. It is used for 15 estimates.

| Estimated model | Chess Puzzles | EBR-bench | Source |
|---|---|---|---|
| [GPT-5.5 Pro](https://benchgap.net/model/gpt-5-5-pro.md) | 62.0% | 50.8% | estimated ± 12.3 pp, low confidence |
| [GPT-5.4 Pro](https://benchgap.net/model/gpt-5-4-pro.md) | 59.0% | 46.0% | estimated ± 12.3 pp, low confidence |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 34.0% | 18.7% | estimated ± 12.3 pp, low confidence |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 29.0% | 15.1% | estimated ± 12.3 pp, low confidence |
| [Muse Spark 1.2](https://benchgap.net/model/muse-spark-1-2.md) | 27.0% | 13.7% | estimated ± 12.3 pp, low confidence |
| [Seed 2.1 Turbo](https://benchgap.net/model/seed-2-1-turbo.md) | 26.0% | 13.1% | estimated ± 12.3 pp, low confidence |
| [GLM-4.7](https://benchgap.net/model/glm-4-7.md) | 21.0% | 10.0% | estimated ± 12.3 pp, low confidence |
| [Inkling](https://benchgap.net/model/inkling.md) | 21.0% | 10.0% | estimated ± 12.3 pp, low confidence |
| [Seed 2.1 Pro](https://benchgap.net/model/seed-2-1-pro.md) | 21.0% | 10.0% | estimated ± 12.3 pp, low confidence |
| [Kimi K2.7 Code](https://benchgap.net/model/kimi-k2-7-code.md) | 14.0% | 6.2% | estimated ± 12.3 pp, low confidence |
| [GPT-4.1](https://benchgap.net/model/gpt-4-1.md) | 11.0% | 4.8% | estimated ± 12.3 pp, low confidence |
| [o1](https://benchgap.net/model/o1.md) | 10.0% | 4.3% | estimated ± 12.3 pp, low confidence |
| [GPT-4o](https://benchgap.net/model/gpt-4o.md) | 9.0% | 3.8% | estimated ± 12.3 pp, low confidence |
| [Claude 3 Opus](https://benchgap.net/model/claude-3-opus.md) | 4.0% | 1.6% | estimated ± 12.3 pp, low confidence |
| [GPT-4.1 nano](https://benchgap.net/model/gpt-4-1-nano.md) | 0.0% | 0.0% | estimated ± 12.3 pp, low confidence |

## Fitted on

| Model | Chess Puzzles | EBR-bench |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 47.0% | 39.5% |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 48.0% | 57.1% |
| [Claude Fable 5.2](https://benchgap.net/model/claude-fable-5-2.md) | 79.0% | 90.5% |
| [Claude Haiku 5.5](https://benchgap.net/model/claude-haiku-5-5.md) | 55.0% | 43.8% |
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 14.0% | 14.3% |
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 21.0% | 12.7% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 41.0% | 19.0% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 52.0% | 28.6% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 43.0% | 45.7% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 67.0% | 71.4% |
| [Claude Sonnet 4.5](https://benchgap.net/model/claude-sonnet-4-5.md) | 10.0% | 2.4% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 51.0% | 14.3% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 45.0% | 4.8% |
| [Gemini 4 Argon](https://benchgap.net/model/gemini-4-argon.md) | 59.0% | 64.8% |
| [Gemini 4 Carbon](https://benchgap.net/model/gemini-4-carbon.md) | 78.0% | 87.6% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 22.0% | 9.5% |
| [GPT-5](https://benchgap.net/model/gpt-5.md) | 36.0% | 12.7% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 48.0% | 23.0% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 48.0% | 25.4% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 63.0% | 34.3% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 59.0% | 44.8% |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 68.0% | 54.3% |
| [GPT-6.2 Astra](https://benchgap.net/model/gpt-6-2-astra.md) | 78.0% | 92.4% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 74.0% | 76.2% |
| [GPT-6 Sol](https://benchgap.net/model/gpt-6-sol.md) | 56.0% | 53.3% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 33.0% | 30.5% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 20.0% | 2.4% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 27.0% | 9.5% |
