# FrontierCode 1.1 Main → AA Coding Index

Calibration · https://benchgap.net/calibration/frontiercode/current/to/aa-coding-index/current · data retrieved 2026-11-18

AA Coding Index is estimated from FrontierCode 1.1 Main with a Michaelis–Menten curve fitted on 9 models measured on both: y = 1.1662·x / (0.25924 + x), R² = 0.86, cross-validated error 4.4 pp. It is used for 1 estimate.

| Estimated model | FrontierCode 1.1 Main | AA Coding Index | Source |
|---|---|---|---|
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 26.9% | 59.4% | estimated ± 4.4 pp, medium confidence |

## Fitted on

| Model | FrontierCode 1.1 Main | AA Coding Index |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 53.5% | 76.5% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 38.5% | 73.6% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 46.5% | 74.3% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 53.4% | 78.0% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 42.7% | 71.6% |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 43.6% | 76.1% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 27.0% | 56.1% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 43.0% | 74.9% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 53.3% | 76.9% |
