# HealthBench (raw) leaderboard

Knowledge benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/knowledge-health-bench

HealthBench raw score. Every model the catalog carries a published HealthBench (raw) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Raw rubric score |
| Tasks | 5,000 multi-turn patient conversations |
| Difficulty | Realistic healthcare conversations |
| Published by | [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://arxiv.org/abs/2505.08775) |

Raw score on realistic multi-turn healthcare conversations graded against expert-written rubrics.

## HealthBench (raw) ranking

8 models with a published HealthBench (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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 69.4 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 68.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 67.1 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 56.9 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 56.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 51.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 50.0 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 47.1 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
