# MMMU-Pro w/ Python → AA-MMMU-Pro

Calibration · https://benchgap.net/calibration/mmmupropython/current/to/aa-mmmu-pro/current · data retrieved 2026-11-21

AA-MMMU-Pro is estimated from MMMU-Pro w/ Python with a Hill curve fitted on 10 models measured on both: y = 0.1825 + (0.9318 − 0.1825)·x^6.00 / (0.63760^6.00 + x^6.00), R² = 0.93, cross-validated error 2.0 pp. It is used for 0 estimates.

## Fitted on

| Model | MMMU-Pro w/ Python | AA-MMMU-Pro |
|---|---|---|
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 82.1% | 78.4% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 78.0% | 73.3% |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 69.5% | 65.4% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 83.2% | 79.9% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 79.5% | 78.6% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 84.6% | 83.4% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 82.0% | 80.7% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 80.1% | 79.4% |
| [Kimi K3.1 Pro](https://benchgap.net/model/kimi-3-1-pro.md) | 90.0% | 83.9% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 83.4% | 80.5% |
