HealthBench Professional
Physician-selected workplace tasks, from care consults to documentation and research, graded on physician-written rubrics.
Dedicated boardPaperReferences
More about this boardLess
525 tasks that physicians picked out of 15,079 real workplace AI conversations, spanning care consults, clinical documentation, and medical research, each judged on a rubric physicians wrote for it.
Grader GPT-5.4 at low reasoning effort with a length adjustment. Physician-written responses score 0.437 on the same rubrics.
Published by OpenAI, released 22 Apr 2026. 525 physician-authored tasks. 0 to 1, higher is better.
- Length-adjusted rubric score × 100. April 2026 paper, overall benchmark; GPT-5.4 at highest reasoning; eight samples per task. Unit: points.
- Labs on the board
- 3
- Scale
- 0 to 1
- Tasks
- 525
- Grader
- GPT-5.4, low reasoning effort
- Use cases
- 3
- Countries
- 50
- Languages
- 52
- Physicians involved
- 190
- Pricing note
- GPT-5.6 models charge higher rates above 272K input tokens. MAI-Thinking-1 is in public preview on Microsoft Foundry without final list pricing.
- Specialties
- 26
- Paper version
- April 2026 paper v1; length-adjusted primary score
- Candidate conversations screened
- 15,079
- Physician-written responses score
- 0.437
- Publisher
- OpenAI
- Rows
- 43
- Models
- 37 on the board
- Released
- 22 Apr 2026
- Measured to
- Oct 2026
- Unit
- 525 tasks
- Documents cited
- 19
Every result on HealthBench Professional, on the board's own scale
43 results, one column each, highest first. 0 to 1, higher is better.
- GPT-6 Astra (Anthropic run)
- Claude Sonnet 5.5
- Claude Fable 5
- Claude Opus 5.5
- GPT-6 Luna (Anthropic run)
- Claude Haiku 5.5
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5 (September card)
- GPT-6.1 Terra
- Muse Wonder Full
- Claude Fable 5.1
- GPT-6 Luna
- GPT-6 Sol
- GPT-5.6 Sol
- Muse Wonder
- Claude Opus 5
- Muse Spark 1.1
- Claude Sonnet 5
- GPT-5.6 Terra
- Claude Opus 4.8 (Opus 4.8 grader)
- Grok 4.7
- Claude Opus 4.8
- GPT-5.6 Luna
- Gemini 4 Argon
Column colour is the model's lab. The table below says who ran each result.
Every published result, ranked on this board alone
43 rows. Higher is better. Bars run from 0 to 1; whiskers show a published interval. Select a row for its quote, page and document.
1GPT-6 Astra (Anthropic run)OpenAI · Anthropic public-API…0.703Independent runSep 2026[1]
On HealthBench Professional at max effort, length adjustment changes the ranking. After: GPT-6 Astra (70.3%) > Claude Sonnet 5.5 (69.2%) > Claude Opus 5.5 (65.6%) > Claude Fable 5.1 (62.1%).
2Claude Sonnet 5.5Anthropic · max effort0.692Model's own labSep 2026[1]
On HealthBench Professional at max effort, length adjustment changes the ranking. After: GPT-6 Astra (70.3%) > Claude Sonnet 5.5 (69.2%) > Claude Opus 5.5 (65.6%) > Claude Fable 5.1 (62.1%).
3Claude Fable 5Anthropic · length-adjusted0.660Model's own labJun 2026[2]
HealthBench Professional 66.0 - 64.7 56.9 51.8 -
4Claude Opus 5.5Anthropic · adaptive max effort0.656Model's own labSep 2026[3]
8.15.2 HealthBench Professional results length adjustment, which penalizes verbose model responses, Claude Opus 5.5 achieved a score of 65.6%.
5GPT-6 Luna (Anthropic run)OpenAI · Run by Anthropic through…0.655Independent runOct 2026[4]
HealthBench Professional panel: 65.5% (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.
6Claude Haiku 5.5Anthropic · max effort0.648Model's own labOct 2026[4]
Max effort scored highest, at 64.8% (71.0% raw); thirteen repeat runs at max on October 4, the day of the lower levels, averaged 64.2%.
7GPT-6 AstraOpenAI · length-adjusted0.647Model's own labSep 2026[5]
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 Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119)
8GPT-6.1 SolOpenAI · length-adjusted0.642Model's own labSep 2026[6]
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 Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119) | 64.2 (67.2, 3038)
9Claude Fable 5 (September card)Anthropic · Anthropic September card0.633Model's own labSep 2026[7]
HealthBench Professional | Length-adjusted score | Claude Fable 5 | 63.3%
10GPT-6.1 TerraOpenAI · length-adjusted0.627Model's own labOct 2026[8]
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 Professional length-adjusted 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389) 64.7 (68.2, 3185) 60.8 (59.5, 1573) 60.8 (61.2, 2119) 64.2 (67.2, 3038) 62.7 (64.2, 2531)
11Muse Wonder FullMeta · Meta internal run0.623Model's own labOct 2026[9]
HealthBench Pro (Open-ended health queries) | Muse Wonder Full (max) 62.3 | Muse Wonder (max) 60.5 | Claude Fable 5.1 (max) 62.1 | GPT-6 Astra (max) 65.3 | Claude Opus 5.5 (max) 65.6 Methodology (p. 4): HealthBench Pro evaluates responses to 525 professional-grade health questions. Models answer without tools, and a GPT-5.4 grader scores each response against physician-written rubrics. We run the official tasks and grading in a common internal framework. The primary metric is the length-normalized weighted rubric score.
12Claude Fable 5.1Anthropic · length-adjusted0.621Model's own labSep 2026[7]
On HealthBench Professional, Claude Fable 5.1 achieved a raw score of 74.2%, ahead of Claude Opus 5 at 73.4%, Fable 5 at 68.9%, and Claude Sonnet 5 at 62.4%. After length adjustment, which penalizes verbose model responses, Fable 5.1 achieved a score of 62.1%.
13GPT-6 LunaOpenAI · length-adjusted0.608Model's own labSep 2026[5]
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 Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119)
13GPT-6 SolOpenAI · length-adjusted0.608Model's own labSep 2026[5]
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 Professional length-adjusted | 51.8 (57.2, 3818) | 60.5 (64.1, 3228) | 57.7 (62.4, 3618) | 55.7 (59.8, 3389) | 64.7 (68.2, 3185) | 60.8 (59.5, 1573) | 60.8 (61.2, 2119)
15GPT-5.6 SolOpenAI · length-adjusted0.605Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
15Muse WonderMeta · Meta internal run0.605Model's own labOct 2026[9]
HealthBench Pro (Open-ended health queries) | Muse Wonder Full (max) 62.3 | Muse Wonder (max) 60.5 | Claude Fable 5.1 (max) 62.1 | GPT-6 Astra (max) 65.3 | Claude Opus 5.5 (max) 65.6 Methodology (p. 4): HealthBench Pro evaluates responses to 525 professional-grade health questions. Models answer without tools, and a GPT-5.4 grader scores each response against physician-written rubrics. We run the official tasks and grading in a common internal framework. The primary metric is the length-normalized weighted rubric score.
17Claude Opus 5Anthropic · length-adjusted0.598Model's own labJul 2026[11]
Claude Opus 5 achieved a raw score of 73.4%, which is the highest amongst all Claude models, ahead of Claude Mythos 5 at 70.3%, Claude Opus 4.8 at 60.3%, and Claude Sonnet 5 at 62.4%. After length adjustment, which penalizes verbose model responses, Claude Opus 5 achieved a score of 59.8%.
18Muse Spark 1.1Meta · length-normalized0.593Model's own labJul 2026[12]
Health | HealthBench Professional | 59.3 | 54.1 | 41.6 | 55.8 | 51.8 (Figure 44 image table row; columns Muse Spark 1.1, Muse Spark, Gemini 3.1 Pro (high), Opus 4.8 (max), GPT 5.5 (xhigh))
19Claude Sonnet 5Anthropic · length-adjusted0.578Model's own labJun 2026[13]
HealthBench Professional 57.8 44.2 51.8 -
20GPT-5.6 TerraOpenAI · length-adjusted0.577Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
21Claude Opus 4.8 (Opus 4.8 grader)Anthropic · Anthropic June evaluation0.574Model's own labJun 2026[13]
HealthBench Professional | Length-adjusted score (%) | Claude Opus 4.8 | 57.4%
22Grok 4.7SpaceX AI · SpaceXAI evaluation0.567Model's own labSep 2026[14]
Grok 4.7 xHigh Grok 4.6 High GPT-5.6 Sol Max Fable 5.1 Max Clinical reasoningHealthBench Professional 56.7% 48.5% 60.5% 62.1%
23Claude Opus 4.8Anthropic · length-adjusted0.558Model's own labMay 2026[15]
Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%.
24GPT-5.6 LunaOpenAI · length-adjusted0.557Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
25Gemini 4 ArgonGoogle · Artificial Analysis…0.551Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | Gemini 4 Argon (high) | 55.1%
26Muse SparkMeta · length-normalized0.541Model's own labJul 2026[12]
Health | HealthBench Professional | 59.3 | 54.1 | 41.6 | 55.8 | 51.8 (Figure 44 image table row; columns Muse Spark 1.1, Muse Spark, Gemini 3.1 Pro (high), Opus 4.8 (max), GPT 5.5 (xhigh))
27GPT-5.6 Sol (August)OpenAI · ChatGPT production0.540Model's own labAug 2026[17]
HealthBench Professional 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) 54.0 (56.6, 2,894) 44.1 (46.8, 2,920)
28Kimi K3Moonshot AI · Artificial Analysis…0.532Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | Kimi K3 (max) | 53.2%
29GLM 5.3Zhipu · Artificial Analysis…0.528Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | GLM-5.3 (max) | 52.8%
30Claude Opus 4.7Anthropic · length-adjusted0.519Model's own labMay 2026[15]
Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%.
31GPT-5.5OpenAI · length-adjusted0.518Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
32Gemini 3.8 FlashGoogle · Artificial Analysis…0.517Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | Gemini 3.8 Flash (high) | 51.7%
33DeepSeek V4.1 FlashDeepSeek · Artificial Analysis…0.507Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | DeepSeek V4.1 Flash (max) | 50.7%
34Grok 4.6SpaceX AI · SpaceXAI evaluation0.485Model's own labSep 2026[14]
Grok 4.7 xHigh Grok 4.6 High GPT-5.6 Sol Max Fable 5.1 Max Clinical reasoningHealthBench Professional 56.7% 48.5% 60.5% 62.1%
35GPT-5.4OpenAI · length-adjusted0.481Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
36GPT-5OpenAI · length-adjusted0.462Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
37GPT-5.2OpenAI · length-adjusted0.459Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
38Claude Sonnet 4.6Anthropic · length-adjusted0.442Model's own labJun 2026[13]
HealthBench Professional 57.8 44.2 51.8 -
39GPT-5.6 Luna (August)OpenAI · ChatGPT production0.441Model's own labAug 2026[17]
HealthBench Professional 32.9 (33.8, 2,285) 38.4 (40.7, 2,775) 54.0 (56.6, 2,894) 44.1 (46.8, 2,920)
40GPT-5.1OpenAI · length-adjusted0.396Model's own labJun 2026[10]
HealthBench Professional length-adjusted 46.2 (51.0, 3616) 39.6 (48.0, 4863) 45.9 (50.0, 3400) 48.1 (51.9, 3308) 51.8 (57.2, 3818) 60.5 (64.1, 3228) 57.7 (62.4, 3618) 55.7 (59.8, 3389)
41GPT-5.5 InstantOpenAI · length-adjusted0.384Model's own labMay 2026[18]
HealthBench Professional 37.6 (40.4, 2,973) 35.7 (38.3, 2,872) 32.9 (33.8, 2,285) 38.4 (40.7, 2,775)
42MAI-Thinking-1Microsoft · length-adjusted0.350Model's own labAug 2026[19]
Model AIR-Bench CyberSec Instruct CyberSec Auto Long Fact Truthful QA HealthBench Prof. MedXpert QA MAI-Thinking-1 88 63 63 98 88 35 43 Sonnet 4.6 88 62 56 98 88 38 49
43Claude Haiku 4.5Anthropic · extended thinking0.322Model's own labOct 2026[4]
Evaluation | Haiku 5.5 | Haiku 4.5 | Sonnet 5.5 | GPT-6 Luna HealthBench Professional (Length-adjusted) | 64.8 | 32.2 | 69.2 | –
19 documents support this board
- 1.Claude Sonnet 5.5 System Cardsystem card, Anthropic, 28 Sep 2026. Every result it supports
- 2.Claude Fable 5 and Claude Mythos 5 System Cardsystem card, Anthropic, 9 Jun 2026. Every result it supports
- 3.Claude Opus 5.5 System Cardsystem card, Anthropic, 22 Sep 2026. Every result it supports
- 4.Claude Haiku 5.5 System Cardsystem card, Anthropic, 7 Oct 2026. Every result it supports
- 5.GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)system card, OpenAI, 3 Sep 2026. Every result it supports
- 6.Addendum to GPT-6 Astra System Card: GPT-6.1 Solsystem card, OpenAI, 29 Sep 2026. Every result it supports
- 7.Claude Fable 5.1 and Claude Mythos 5.1 System Cardsystem card, Anthropic, 1 Sep 2026. Every result it supports
- 8.Addendum to GPT-6 Astra System Card: GPT-6.1 Terrasystem card, OpenAI, 26 Oct 2026. Every result it supports
- 9.Muse Wonder Model Cardmodel card, Meta, 12 Oct 2026. Every result it supports
- 10.GPT-5.6 System Cardsystem card, OpenAI, 9 Jul 2026. Every result it supports
- 11.System Card: Claude Opus 5system card, Anthropic, 24 Jul 2026. Every result it supports
- 12.Muse Spark 1.1 Evaluation Reportmodel card, Meta, 9 Jul 2026. Every result it supports
- 13.System Card: Claude Sonnet 5system card, Anthropic, 30 Jun 2026. Every result it supports
- 14.Introducing Grok 4.7launch post, SpaceXAI, 21 Sep 2026. Every result it supports
- 15.System Card: Claude Opus 4.8system card, Anthropic, 28 May 2026. Every result it supports
- 16.HealthBench Professional Benchmark | Artificial Analysisindependent leaderboard, Artificial Analysis, 2 Nov 2026. Every result it supports
- 17.GPT-5.6 - August Updates (system card addendum)system card, OpenAI, 6 Aug 2026. Every result it supports
- 18.GPT-5.5 Instant System Cardsystem card, OpenAI, 5 May 2026. Every result it supports
- 19.MAI-Thinking-1: Building a Hill-Climbing Machinemodel card, Microsoft AI, 12 Aug 2026. Every result it supports