Calibration
MMMU-Pro w/ Python → AA-MMMU-Pro
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 | 82.1% | 78.4% |
| GPT-5.4 mini | 78.0% | 73.3% |
| GPT-5.4 nano | 69.5% | 65.4% |
| GPT-5.5 | 83.2% | 79.9% |
| GPT-5.6 Luna | 79.5% | 78.6% |
| GPT-5.6 Sol | 84.6% | 83.4% |
| GPT-5.6 Terra | 82.0% | 80.7% |
| Kimi K2.6 | 80.1% | 79.4% |
| Kimi K3.1 Pro | 90.0% | 83.9% |
| Kimi K3 | 83.4% | 80.5% |