HealthBench
When someone asks an AI about their own health, do the answers meet a physician's standard?
More about this benchmark
Realistic multi-turn health conversations graded on physician-written rubrics for accuracy, completeness, and communication.
5,000 realistic multi-turn health conversations graded against physician-written rubrics (48,562 criteria) covering accuracy, completeness, context awareness, communication, and instruction following. OpenAI now also reports a length-adjusted variant that penalizes verbosity.
- Each item
- Conversation with an example-specific rubric
- The model gets
- A health conversation ending at the next response to be evaluated.
- It returns
- An open-ended assistant response.
- Setting
- Original 5,000-conversation benchmark; physician criteria graded by a model.
- Released
- May 2025
- Models on the official board
- 8
- Paper version
- Original HealthBench; May 2025 paper v1
Reading these numbers
Cross-source rows are not directly comparable: Anthropic reports a raw score under its own protocol, OpenAI leads with length-adjusted numbers at maximum reasoning effort and reports production Instant settings separately, and Baichuan ran its competitors itself. The benchmark's official grader is GPT-4.1. OpenAI has said the parent set is approaching a noise ceiling for frontier models and points to HealthBench Professional for continued measurement.
Scores come from a mix of vendor documents and official results.
- Results
- 33 from 26 models
- Latest
- Oct 2026
- Published by
- OpenAI
- Index weight
- 0.798, core
- Sources
- 17
Counts toward the Health Evals Index as a core benchmark, at weight 0.798: realistic health conversations with people, graded on physician rubrics.
Where every published HealthBench score sits
33 scores, one column each, highest first, on the benchmark's own scale. Higher is better.
- Claude Opus 5.5
- Claude Opus 5
- Claude Sonnet 5.5
- Baichuan-M3
- GPT-5.2-High
- Claude Fable 5
- Claude Haiku 5.5
- Claude Opus 5.5
- Claude Fable 5
- Claude Fable 5.1
- Claude Opus 4.8
- Claude Sonnet 5
- GPT-6.1 Sol
- GPT-6 Astra
- Claude Opus 5 (length-adjusted)
- GPT-5
- GPT OSS 120B
- GPT-5.6 Sol
- GPT-5.6 Terra
- GPT-5.2
- GPT-5.5
- GPT-6 Luna (Anthropic run)
- GPT-5.6 Luna
- GPT-6.1 Terra
- GPT-5.6 Sol (August)
Each column is the model's lab colour. The table below says who ran each score.
Every published score, ranked within this benchmark only
33 scores. Higher is better. Where the source gave a range, the whisker shows it. Open any row to read the sentence the score came from.
1Claude Opus 5.5Anthropic · raw/unadjusted68.1Model's makerSep 2026[1]
On HealthBench, Claude Opus 5.5 achieved a raw score of 68.1%, ahead of Claude Fable 5.1 at 66.7%, Claude Sonnet 5 at 59.2%, and Claude Opus 5 at 67.1%. After length adjustment, which penalizes verbose model responses, Claude Opus 5.5 achieved a score of 60.6%.
2Claude Opus 5Anthropic · raw/unadjusted67.1Model's makerJul 2026[2]
Claude Opus 5 achieved a raw score of 67.1%, which is the highest among all Claude models, ahead of Claude Mythos 5 at 62.5%, Claude Opus 4.8 at 58.8%, and Claude Sonnet 5 at 59.2%. After length adjustment, which penalizes verbose model responses, Claude Opus 5 achieved a score of 57.8%.
3Claude Sonnet 5.5Anthropic · max effort65.4Model's makerSep 2026[3]
Sonnet 5.5 | HealthBench | max 65.4%
4Baichuan-M3Baichuan · self-run in Baichuan-M3…65.1Model's makerFeb 2026[4]
On the comprehensive HealthBench Total, Baichuan-M3 achieves a score of 65.1, surpassing the runner-up GPT-5.2-High (63.3) by a clear margin.
5GPT-5.2-HighOpenAI · raw score as run by…63.3IndependentFeb 2026[4]
GPT-5.2-High 63.3 2.37% 2.78%
6Claude Fable 5Anthropic · length-adjusted62.7Model's makerJun 2026[5]
HealthBench 62.7 - 61.1 59.3 56.5 -
7Claude Haiku 5.5Anthropic · max effort61.6Model's makerOct 2026[6]
On HealthBench (one run per level below max), Haiku 5.5 scored 59.9% at low, 60.2% at medium, 60.3% at high, 61.1% at xhigh and 61.6% at max, a rise of 1.8 points against 6.9 on HealthBench Professional
8Claude Opus 5.5Anthropic · adaptive max effort60.6Model's makerSep 2026[1]
8.15.1 HealthBench results After length adjustment, which penalizes verbose model responses, Claude Opus 5.5 achieved a score of 60.6%.
9Claude Fable 5Anthropic · length-adjusted60.4Model's makerSep 2026[7]
HealthBench | Length-adjusted score | Claude Fable 5 | 60.4%
10Claude Fable 5.1Anthropic · length-adjusted60Model's makerSep 2026[7]
On HealthBench, Claude Fable 5.1 achieved a raw score of 66.7%, ahead of Claude Fable 5 at 61.2% and Claude Sonnet 5 at 59.2%, and behind Claude Opus 5 at 67.1%. After length adjustment, which penalizes verbose model responses, Fable 5.1 achieved a score of 60%.
11Claude Opus 4.8Anthropic · length-adjusted59.3Model's makerJun 2026[5]
HealthBench 62.7 - 61.1 59.3 56.5 -
12Claude Sonnet 5Anthropic · length-adjusted58.7Model's makerJun 2026[8]
[Figure 8.12.1.A] HealthBench length-adjusted scores. All Claude models used adaptive thinking at max effort. (bar label: Claude Sonnet 5 58.7%)
13GPT-6.1 SolOpenAI · length-adjusted58.5Model's makerSep 2026[9]
EVALUATION | GPT-5.5 | GPT-5.6 SOL | GPT-5.6 TERRA | GPT-5.6 LUNA | GPT-6 ASTRA | GPT-6 SOL | GPT-6 LUNA | GPT-6.1 SOL HealthBench length-adjusted | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930) | 58.3 (56.9, 1760) | 53.2 (47.1, 977) | 54.5 (50.0, 1255) | 58.5 (56.7, 1701)
14GPT-6 AstraOpenAI · length-adjusted58.3Model's makerSep 2026[10]
Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench length-adjusted | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930) | 58.3 (56.9, 1760) | 53.2 (47.1, 977) | 54.5 (50.0, 1255)
15Claude Opus 5 (length-adjusted)Anthropic · length-adjusted57.8Model's makerJul 2026[2]
8.15.1 HealthBench results After length adjustment, which penalizes verbose model responses, Claude Opus 5 achieved a score of 57.8%.
16GPT-5OpenAI · length-adjusted57.7Model's makerJun 2026[11]
evaluation | gpt-5 | gpt-5.1 | gpt-5.2 | gpt-5.4 | gpt-5.5 | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna HealthBench length-adjusted | 57.7 (63.1, 2904) | 50.9 (64.2, 4222) | 56.8 (60.7, 2645) | 54.0 (55.7, 2275) | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930)
17GPT OSS 120BOpenAI · reasoning level high57.6Model's makerAug 2025[12]
HealthBench 53.0 55.9 57.6 40.4 41.8 42.5
18GPT-5.6 SolOpenAI · length-adjusted57.0Model's makerJun 2026[11]
HealthBench length-adjusted 57.7 (63.1, 2904) 50.9 (64.2, 4222) 56.8 (60.7, 2645) 54.0 (55.7, 2275) 56.5 (58.4, 2313) 57.0 (55.6, 1764) 57.0 (58.7, 2285) 55.8 (55.4, 1930)
18GPT-5.6 TerraOpenAI · length-adjusted57.0Model's makerJun 2026[11]
HealthBench length-adjusted 57.7 (63.1, 2904) 50.9 (64.2, 4222) 56.8 (60.7, 2645) 54.0 (55.7, 2275) 56.5 (58.4, 2313) 57.0 (55.6, 1764) 57.0 (58.7, 2285) 55.8 (55.4, 1930)
20GPT-5.2OpenAI · length-adjusted56.8Model's makerJun 2026[11]
evaluation | gpt-5 | gpt-5.1 | gpt-5.2 | gpt-5.4 | gpt-5.5 | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna HealthBench length-adjusted | 57.7 (63.1, 2904) | 50.9 (64.2, 4222) | 56.8 (60.7, 2645) | 54.0 (55.7, 2275) | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930)
21GPT-5.5OpenAI · length-adjusted56.5Model's makerApr 2026[13]
HealthBench length-adjusted 57.7 (63.1, 2904) 50.9 (64.2, 4222) 56.8 (60.7, 2645) 54.0 (55.7, 2275) 56.5 (58.4, 2313)
22GPT-6 Luna (Anthropic run)OpenAI · Run by Anthropic through…56.3IndependentOct 2026[6]
HealthBench panel: 56.3% (GPT-6 Luna (OpenAI)); caption: GPT-6 Luna's scores come from our own runs through OpenAI's public API and are not OpenAI's published figures.
23GPT-5.6 LunaOpenAI · length-adjusted55.8Model's makerJun 2026[11]
HealthBench length-adjusted 57.7 (63.1, 2904) 50.9 (64.2, 4222) 56.8 (60.7, 2645) 54.0 (55.7, 2275) 56.5 (58.4, 2313) 57.0 (55.6, 1764) 57.0 (58.7, 2285) 55.8 (55.4, 1930)
24GPT-6.1 TerraOpenAI · length-adjusted55.1Model's makerOct 2026[14]
EVALUATION GPT-5.5 GPT-5.6-SOL GPT-5.6-TERRA GPT-5.6-LUNA GPT-6 ASTRA GPT-6-SOL GPT-6-LUNA GPT-6.1-SOL GPT-6.1-TERRA HealthBench length-adjusted 56.5 (58.4, 2313) 57.0 (55.6, 1764) 57.0 (58.7, 2285) 55.8 (55.4, 1930) 58.3 (56.9, 1760) 53.2 (47.1, 977) 54.5 (50.0, 1255) 58.5 (56.7, 1701) 55.1 (51.1, 1331)
25GPT-5.6 Sol (August)OpenAI · ChatGPT production/Instant…55.0Model's makerAug 2026[15]
HealthBench 49.6 (47.9, 1,724) 51.4 (50.9, 1,922) 55.0 (52.1, 1,514) 53.3 (50.7, 1,567)
26GPT-6 LunaOpenAI · length-adjusted54.5Model's makerSep 2026[10]
Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench length-adjusted | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930) | 58.3 (56.9, 1760) | 53.2 (47.1, 977) | 54.5 (50.0, 1255)
27GPT-5.3 ChatOpenAI · raw score54.1Model's makerMar 2026[16]
HealthBench 55.4% 54.1%
28GPT-5.4OpenAI · length-adjusted54.0Model's makerJun 2026[11]
evaluation | gpt-5 | gpt-5.1 | gpt-5.2 | gpt-5.4 | gpt-5.5 | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna HealthBench length-adjusted | 57.7 (63.1, 2904) | 50.9 (64.2, 4222) | 56.8 (60.7, 2645) | 54.0 (55.7, 2275) | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930)
29GPT-5.6 Luna (August)OpenAI · ChatGPT production53.3Model's makerAug 2026[15]
HealthBench 49.6 (47.9, 1,724) 51.4 (50.9, 1,922) 55.0 (52.1, 1,514) 53.3 (50.7, 1,567)
30GPT-6 SolOpenAI · length-adjusted53.2Model's makerSep 2026[10]
Evaluation | GPT-5.5 | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | GPT-6 Astra | GPT-6 Sol | GPT-6 Luna HealthBench length-adjusted | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930) | 58.3 (56.9, 1760) | 53.2 (47.1, 977) | 54.5 (50.0, 1255)
31GPT-5.5 InstantOpenAI · length-adjusted51.4Model's makerMay 2026[17]
HealthBench 49.6 (50.8, 2,208) 50.6 (51.5, 2,145) 49.6 (47.9, 1,724) 51.4 (50.9, 1,922)
32GPT-5.1OpenAI · length-adjusted50.9Model's makerJun 2026[11]
evaluation | gpt-5 | gpt-5.1 | gpt-5.2 | gpt-5.4 | gpt-5.5 | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna HealthBench length-adjusted | 57.7 (63.1, 2904) | 50.9 (64.2, 4222) | 56.8 (60.7, 2645) | 54.0 (55.7, 2275) | 56.5 (58.4, 2313) | 57.0 (55.6, 1764) | 57.0 (58.7, 2285) | 55.8 (55.4, 1930)
33GPT OSS 20BOpenAI · reasoning level high42.5Model's makerAug 2025[12]
HealthBench 53.0 55.9 57.6 40.4 41.8 42.5
The 17 documents behind these scores
- 1.Claude Opus 5.5 System Cardsystem card, Anthropic, 22 Sep 2026. Quotes from this document
- 2.System Card: Claude Opus 5system card, Anthropic, 24 Jul 2026. Quotes from this document
- 3.Claude Sonnet 5.5 System Cardsystem card, Anthropic, 28 Sep 2026. Quotes from this document
- 4.Baichuan-M3 Technical Reportpaper, Baichuan, 6 Feb 2026. Quotes from this document
- 5.Claude Fable 5 and Claude Mythos 5 System Cardsystem card, Anthropic, 9 Jun 2026. Quotes from this document
- 6.Claude Haiku 5.5 System Cardsystem card, Anthropic, 7 Oct 2026. Quotes from this document
- 7.Claude Fable 5.1 and Claude Mythos 5.1 System Cardsystem card, Anthropic, 1 Sep 2026. Quotes from this document
- 8.System Card: Claude Sonnet 5system card, Anthropic, 30 Jun 2026. Quotes from this document
- 9.Addendum to GPT-6 Astra System Card: GPT-6.1 Solsystem card, OpenAI, 29 Sep 2026. Quotes from this document
- 10.GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)system card, OpenAI, 3 Sep 2026. Quotes from this document
- 11.GPT-5.6 System Cardsystem card, OpenAI, 9 Jul 2026. Quotes from this document
- 12.gpt-oss-120b & gpt-oss-20b Model Cardmodel card, OpenAI, 5 Aug 2025. Quotes from this document
- 13.GPT-5.5 System Cardsystem card, OpenAI, 23 Apr 2026. Quotes from this document
- 14.Addendum to GPT-6 Astra System Card: GPT-6.1 Terrasystem card, OpenAI, 26 Oct 2026. Quotes from this document
- 15.GPT-5.6 - August Updates (system card addendum)system card, OpenAI, 6 Aug 2026. Quotes from this document
- 16.GPT-5.3 Instant System Cardsystem card, OpenAI, 2 Mar 2026. Quotes from this document
- 17.GPT-5.5 Instant System Cardsystem card, OpenAI, 5 May 2026. Quotes from this document