# DAYJOB Healthcare → EBR-bench

Calibration · https://benchgap.net/calibration/dayjob-healthcare/current/to/ebrbench/current · data retrieved 2026-11-21

EBR-bench is estimated from DAYJOB Healthcare with a Hill curve fitted on 11 models measured on both: y = 0.2408 + (1.1662 − 0.2408)·x^0.64 / (0.15878^0.64 + x^0.64), R² = 0.75, cross-validated error 14.8 pp. It is used for 0 estimates.

## Fitted on

| Model | DAYJOB Healthcare | EBR-bench |
|---|---|---|
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 0.8% | 28.6% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 9.2% | 45.7% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 25.2% | 71.4% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 0.0% | 14.3% |
| [Gemini 4 Argon](https://benchgap.net/model/gemini-4-argon.md) | 11.6% | 64.8% |
| [Gemini 4 Carbon](https://benchgap.net/model/gemini-4-carbon.md) | 15.6% | 87.6% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 0.0% | 34.3% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 1.2% | 44.8% |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 10.8% | 54.3% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 11.2% | 76.2% |
| [GPT-6 Sol](https://benchgap.net/model/gpt-6-sol.md) | 2.8% | 53.3% |
