Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Knowledge benchmark
HealthBench Professional raw score. Every model the catalog carries a published HealthBench Professional (raw) value for, ranked by that value.
Raw score on physician-authored clinical consult, documentation, and research conversations. 10 models in the ModelScale catalog have a published value.
Each point is a model with a published HealthBench Professional (raw) value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
10 models with a published HealthBench Professional (raw) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Raw rubric score |
|---|---|---|---|
| 1 | Anthropic | 77.1 | |
| 1 | Anthropic | 77.1 | |
| 3 | Anthropic | 73.4 |
What the benchmark measures and how its value is published, from the source’s own record.
HealthBench Professional (raw) (HealthBench Professional raw score) is a knowledge benchmark published by HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats. Raw score on physician-authored clinical consult, documentation, and research conversations. Its evaluation set is described by the source as 525 physician-authored conversations. The source rates its difficulty as professional clinical tasks.
Each model's result is published by HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats as raw rubric score. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 10 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | OpenAI | 68.2 |
| 5 | OpenAI | 67.2 |
| 6 | OpenAI | 66.0 |
| 7 | OpenAI | 65.5 |
| 8 | OpenAI | 64.2 |
| 9 | OpenAI | 61.2 |
| 10 | OpenAI | 59.5 |
Evidence key: Observed
Rows are ordered by the value HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.