# BioBasicsBench → HealthBench Professional

Calibration · https://benchgap.net/calibration/biobasicsbench/current/to/healthbenchprofessional/current · data retrieved 2026-11-21

HealthBench Professional is estimated from BioBasicsBench with a Michaelis–Menten curve fitted on 5 models measured on both: y = 0.8554·x / (0.20223 + x), R² = 0.70, cross-validated error 6.1 pp. It is used for 0 estimates.

## Fitted on

| Model | BioBasicsBench | HealthBench Professional |
|---|---|---|
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 33.2% | 48.1% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 45.6% | 60.5% |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 62.6% | 64.2% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 67.0% | 64.7% |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 37.6% | 60.8% |
