# AA Coding Index → PostTrainBench

Calibration · https://benchgap.net/calibration/aa-coding-index/current/to/post-train-bench12/current · data retrieved 2026-11-18

PostTrainBench is estimated from AA Coding Index with a Hill curve fitted on 12 models measured on both: y = 0.0267 + (1.2000 − 0.0267)·x^6.00 / (0.91418^6.00 + x^6.00), R² = 0.47, cross-validated error 5.9 pp. It is used for 4 estimates.

| Estimated model | AA Coding Index | PostTrainBench | Source |
|---|---|---|---|
| [Qwen3.8 Max Preview](https://benchgap.net/model/qwen3-8-max-preview.md) | 71.8% | 25.0% | estimated ± 5.9 pp, low confidence |
| [Quasar 438B](https://benchgap.net/model/quasar-438b.md) | 61.2% | 12.4% | estimated ± 5.9 pp, low confidence |
| [Apodex 1.1](https://benchgap.net/model/apodex-1-1.md) | 60.8% | 12.0% | estimated ± 5.9 pp, low confidence |
| [Apodex 1.1 Mini](https://benchgap.net/model/apodex-1-1-mini.md) | 60.8% | 12.0% | estimated ± 5.9 pp, low confidence |

## Fitted on

| Model | AA Coding Index | PostTrainBench |
|---|---|---|
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 73.6% | 24.3% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 74.3% | 31.0% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 78.0% | 35.7% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 68.8% | 18.1% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 68.8% | 30.4% |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 74.8% | 34.5% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 71.1% | 17.8% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 74.9% | 23.9% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 77.4% | 31.0% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 76.9% | 41.9% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 72.5% | 22.6% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 76.2% | 31.5% |
