# SimpleQA → MMLU

Calibration · https://benchgap.net/calibration/1424 · data retrieved 2026-10-29

MMLU is estimated from SimpleQA with a Michaelis–Menten curve fitted on 6 models measured on both: y = 0.9250·x / (0.00914 + x), R² = 0.64, cross-validated error 4.1 pp. It is used for 1 estimate.

| Estimated model | SimpleQA | MMLU | Source |
|---|---|---|---|
| [Gemini 2.0 Flash-Lite](https://benchgap.net/model/gemini-2-0-flash-lite.md) | 16.5% | 87.6% | estimated ± 4.1 pp, medium confidence |

## Fitted on

| Model | SimpleQA | MMLU |
|---|---|---|
| [DeepSeek-R1](https://benchgap.net/model/deepseek-r1.md) | 30.1% | 90.8% |
| [GPT-4.5](https://benchgap.net/model/gpt-4-5.md) | 62.5% | 90.8% |
| [Kimi K2](https://benchgap.net/model/kimi-k2.md) | 31.0% | 89.5% |
| [Mistral Small 3.1](https://benchgap.net/model/mistral-small-3-1.md) | 10.4% | 80.6% |
| [o1-mini](https://benchgap.net/model/o1-mini.md) | 7.6% | 85.2% |
| [o4-mini](https://benchgap.net/model/o4-mini.md) | 20.2% | 90.0% |