# SimpleQA → GPQA

Calibration · https://benchgap.net/calibration/1423 · data retrieved 2026-10-29

GPQA is estimated from SimpleQA with a Michaelis–Menten curve fitted on 14 models measured on both: y = 0.8069·x / (0.04361 + x), R² = 0.48, cross-validated error 9.1 pp. It is used for 0 estimates.

## Fitted on

| Model | SimpleQA | GPQA |
|---|---|---|
| [DeepSeek-R1](https://benchgap.net/model/deepseek-r1.md) | 30.1% | 71.5% |
| [DeepSeek-R1-0528](https://benchgap.net/model/deepseek-r1-0528.md) | 27.8% | 81.0% |
| [DeepSeek V3](https://benchgap.net/model/deepseek-v3.md) | 24.9% | 59.1% |
| [Gemini 1.5 Flash](https://benchgap.net/model/gemini-1-5-flash.md) | 8.6% | 50.0% |
| [Gemini 2.0 Flash](https://benchgap.net/model/gemini-2-0-flash.md) | 29.9% | 65.2% |
| [Gemini 2.0 Flash-Lite](https://benchgap.net/model/gemini-2-0-flash-lite.md) | 16.5% | 50.5% |
| [Gemini 2.5 Flash-Lite](https://benchgap.net/model/gemini-2-5-flash-lite.md) | 10.7% | 64.6% |
| [GPT-4.5](https://benchgap.net/model/gpt-4-5.md) | 62.5% | 69.5% |
| [Grok 3 [Beta]](https://benchgap.net/model/grok-3-beta.md) | 43.6% | 75.4% |
| [Kimi K2](https://benchgap.net/model/kimi-k2.md) | 31.0% | 75.1% |
| [Mistral Small 3.1](https://benchgap.net/model/mistral-small-3-1.md) | 10.4% | 46.0% |
| [o1-mini](https://benchgap.net/model/o1-mini.md) | 7.6% | 60.0% |
| [o4-mini](https://benchgap.net/model/o4-mini.md) | 20.2% | 77.6% |
| [Qwen3 235B 2507](https://benchgap.net/model/qwen3-235b-2507.md) | 54.3% | 77.5% |