Clinical Benchmarks

HealthBench Professional

Physician-selected workplace tasks, from care consults to documentation and research, graded on physician-written rubrics.

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.

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%).
As printed
70.3%
Where
p. 138, paragraph above Figure 8.15.B, HealthBench Professional after length adjustment.
Setting
Anthropic public-API reproduction; max effort; no system prompt; Opus 4.8 grader; length-adjusted; raw 74.0%
Reported by
independent run
Document
[1] Claude Sonnet 5.5 System Card
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%).
As printed
69.2%
Where
p. 138, Section 8.15.2 and paragraph above Figure 8.15.B.
Setting
Anthropic; max effort; Opus 4.8 grader; safety classifiers enabled; length-adjusted; raw 77.1%
Reported by
vendor-reported
Document
[1] Claude Sonnet 5.5 System Card
3Claude Fable 5Anthropic · length-adjusted0.660Model's own labJun 2026[2]
HealthBench Professional 66.0 - 64.7 56.9 51.8 -
As printed
66.0
Where
p. 252, Table 8.1.A, row HealthBench Professional, column Mythos 5 (Fable 5 column '-'); Figure 8.18.2.A p. 298 bar label 66.0% on Claude Mythos 5
Setting
length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 70.3%). Measured as Claude Mythos 5; Anthropic itself prints 66.0 in the Fable 5 column of the Opus 5 card with footnote Mythos 5.
Reported by
vendor-reported
Document
[2] Claude Fable 5 and Claude Mythos 5 System Card
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%.
As printed
65.6%
Where
pp. 213–214, Section 8.15.2, paragraph and Figure 8.15.2.A.
Setting
Anthropic; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt; safety classifiers and refusal fallback to Opus 5; length-adjusted; raw 77.1%
Reported by
vendor-reported
Document
[3] Claude Opus 5.5 System Card
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.
As printed
65.5%
Where
p. 132, Figure 8.11.1.A, HealthBench Professional panel, GPT-6 Luna (OpenAI) diamond label (visually read printed label); Section 8.11.1 text on pp. 131-132
Setting
Run by Anthropic through OpenAI's public API; max effort; Opus 4.8 grader; length-adjusted; not OpenAI's published figure
Reported by
independent run
Document
[4] Claude Haiku 5.5 System Card
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%.
As printed
64.8%
Where
p. 133, Section 8.11.3; same value in p. 111, Table 8.1.A, row HealthBench Professional (Length-adjusted), column Haiku 5.5 (printed 64.8) and p. 132, Figure 8.11.1.A
Setting
Anthropic; max effort; Opus 4.8 grader; safety classifiers enabled; length-adjusted; raw 71.0%; five runs (October 1 and 2); thirteen repeat max runs on October 4 averaged 64.2%
Reported by
vendor-reported
Document
[4] Claude Haiku 5.5 System Card
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)
As printed
64.7
Where
Section 11.4.1, Table 29, HealthBench Professional length-adjusted, GPT-6 Astra column; September 22 correction.
Setting
length-adjusted, max reasoning effort (68.2 unadjusted, 3,185 mean response chars, as corrected by OpenAI on September 22; first printed as 69.5 and 4,097); GPT-6 Astra system card Table 6, column 'gpt-6 Astra'.
Reported by
vendor-reported
Document
[5] GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)
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)
As printed
64.2
Where
Section 5.1, Table 7, HealthBench Professional length-adjusted, GPT-6.1 Sol column
Setting
OpenAI; length-adjusted; 64.2 (67.2, 3038) (adjusted, raw, mean response characters); addendum Table 7 refers to the GPT-6 Astra card for method
Reported by
vendor-reported
Document
[6] Addendum to GPT-6 Astra System Card: GPT-6.1 Sol
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%
As printed
63.3%
Where
p. 199, Figure 8.17.2.A, Claude Fable 5 length-adjusted bar (visually read printed labels).
Setting
Measured as Claude Fable 5; Anthropic September card; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt; raw 68.9%
Reported by
vendor-reported
Document
[7] Claude Fable 5.1 and Claude Mythos 5.1 System Card
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)
As printed
62.7
Where
Section 5.1, Table 5, HealthBench Professional length-adjusted, GPT-6.1 Terra column
Setting
OpenAI; length-adjusted; 62.7 (64.2, 2531) (adjusted, raw, mean response characters); addendum Table 5 refers to the GPT-6 Astra card for method
Reported by
vendor-reported
Document
[8] Addendum to GPT-6 Astra System Card: GPT-6.1 Terra
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.
As printed
62.3
Where
p. 3, results table (image), HealthBench Pro row, Muse Wonder Full (max) column; methodology p. 4
Setting
Meta internal run; length-normalized weighted rubric score, GPT-5.4 grader, no tools, max reasoning effort (Muse Wonder Model Card p. 3 table, Muse Wonder Full (max) column)
Reported by
vendor-reported
Document
[9] Muse Wonder Model Card
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%.
As printed
62.1%
Where
p. 199, sec. 8.17.2 (same figure printed as 62.1% in Table 8.1.A, p. 167)
Setting
length-adjusted (method published in the HealthBench Professional paper); Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over five trials, no tools or customized system prompt; Fable 5.1 run with safety classifiers active and a refusal-fallback to Claude Opus 5 (raw 74.2%).
Reported by
vendor-reported
Document
[7] Claude Fable 5.1 and Claude Mythos 5.1 System Card
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)
As printed
60.8
Where
Section 11.4.1, Table 29, HealthBench Professional length-adjusted, GPT-6 Luna column; September 22 correction.
Setting
OpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)
Reported by
vendor-reported
Document
[5] GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)
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)
As printed
60.8
Where
Section 11.4.1, Table 29, HealthBench Professional length-adjusted, GPT-6 Sol column; September 22 correction.
Setting
OpenAI; length-adjusted; maximum reasoning effort; 60.8 (59.5, 1573) (adjusted, raw, mean response characters)
Reported by
vendor-reported
Document
[5] GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)
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)
As printed
60.5
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.6-SOL
Setting
length-adjusted, max reasoning effort (64.1 unadjusted, 3,228 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-SOL. API max-effort setting, not the August ChatGPT production setting measured in row 492.
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
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.
As printed
60.5
Where
p. 3, results table (image), HealthBench Pro row, Muse Wonder (max) column; methodology p. 4
Setting
Meta internal run; length-normalized weighted rubric score, GPT-5.4 grader, no tools, max reasoning effort (Muse Wonder Model Card p. 3 table, Muse Wonder (max) column)
Reported by
vendor-reported
Document
[9] Muse Wonder Model Card
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%.
As printed
59.8%
Where
p. 189, section 8.15.2 HealthBench Professional results; also Table 8.1.A p. 152 ('HealthBench Professional 59.8 ...')
Setting
length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 73.4%).
Reported by
vendor-reported
Document
[11] System Card: Claude Opus 5
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))
As printed
59.3
Where
p. 101, Figure 44 'General capability benchmark results' (image), row HealthBench Professional, column Muse Spark 1.1; protocol p. 104 (printed 103): HealthBench Pro comprises 525 evaluation data points graded by rubrics. We use GPT-5.4 with low reasoning effort as the grader and report the length-normalized rubric score as done in their paper.
Setting
length-normalized, GPT-5.4 low-reasoning grader, xhigh reasoning via Meta Model API (Muse Spark 1.1 Evaluation Report Figure 44)
Reported by
vendor-reported
Document
[12] Muse Spark 1.1 Evaluation Report
19Claude Sonnet 5Anthropic · length-adjusted0.578Model's own labJun 2026[13]
HealthBench Professional 57.8 44.2 51.8 -
As printed
57.8
Where
p. 115, Table 8.1.A, row HealthBench Professional, column Claude Sonnet 5; Figure 8.12.2.A p. 139
Setting
length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 62.4%).
Reported by
vendor-reported
Document
[13] System Card: Claude Sonnet 5
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)
As printed
57.7
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.6-TERRA
Setting
length-adjusted, max reasoning effort (62.4 unadjusted, 3,618 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-TERRA.
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
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%
As printed
57.4%
Where
p. 139, Figure 8.12.2.A, Claude Opus 4.8 bar (visually read printed labels).
Setting
Anthropic June evaluation; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt
Reported by
vendor-reported
Document
[13] System Card: Claude Sonnet 5
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%
As printed
56.7%
Where
Model Improvements comparison table, Clinical reasoning / HealthBench Professional row; Grok 4.7 column; September 21, 2026.
Setting
SpaceXAI evaluation; xHigh effort; HealthBench Professional
Reported by
vendor-reported
Document
[14] Introducing Grok 4.7
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%.
As printed
55.8%
Where
p. 228, section 8.14.1 HealthBench Professional; Figure 8.14.A p. 229
Setting
length-adjusted, adaptive thinking at max effort, Claude Sonnet 4.6 grader (the grader used by the Opus 4.8 card itself); the other Claude rows on this board use the Claude Opus 4.8 grader, under which Anthropic later prints 57.4 for this model.
Reported by
vendor-reported
Document
[15] System Card: Claude Opus 4.8
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)
As printed
55.7
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.6-LUNA
Setting
length-adjusted, max reasoning effort (59.8 unadjusted, 3,389 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-LUNA. API max-effort setting, not the August ChatGPT production setting measured in row 493.
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
25Gemini 4 ArgonGoogle · Artificial Analysis…0.551Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | Gemini 4 Argon (high) | 55.1%
As printed
55.1%
Where
Score section, Length-Adjusted Score chart, Gemini 4 Argon (high) bar label; raw score 64.2% on the Raw Score tab
Setting
Artificial Analysis independent run, high reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (64.2 raw, 5,133 mean response chars)
Reported by
independent run
Document
[16] HealthBench Professional Benchmark | Artificial Analysis
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))
As printed
54.1
Where
p. 101, Figure 44 (image), row HealthBench Professional, column Muse Spark; protocol p. 104 (printed 103)
Setting
length-normalized, GPT-5.4 low-reasoning grader; Muse Spark (1.0) column in the Muse Spark 1.1 Evaluation Report Figure 44
Reported by
vendor-reported
Document
[12] Muse Spark 1.1 Evaluation Report
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)
As printed
54.0
Where
p. 11, section 5.1 HealthBench, table "Reported as length-adjusted score (unadjusted, mean response length in characters)", column GPT-5.6 Sol (August)
Setting
ChatGPT production (Instant) deployment setting, length-adjusted, GPT-5.6 August Updates PDF column GPT-5.6 Sol (August) (56.6 unadjusted, 2,894 chars)
Reported by
vendor-reported
Document
[17] GPT-5.6 - August Updates (system card addendum)
28Kimi K3Moonshot AI · Artificial Analysis…0.532Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | Kimi K3 (max) | 53.2%
As printed
53.2%
Where
Score section, Length-Adjusted Score chart, Kimi K3 (max) bar label; raw score 56.9% on the Raw Score tab
Setting
Artificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (56.9 raw, 3,250 mean response chars)
Reported by
independent run
Document
[16] HealthBench Professional Benchmark | Artificial Analysis
29GLM 5.3Zhipu · Artificial Analysis…0.528Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | GLM-5.3 (max) | 52.8%
As printed
52.8%
Where
Score section, Length-Adjusted Score chart, GLM-5.3 (max) bar label; raw score 57.9% on the Raw Score tab
Setting
Artificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (57.9 raw, 3,748 mean response chars)
Reported by
independent run
Document
[16] HealthBench Professional Benchmark | Artificial Analysis
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%.
As printed
51.9%
Where
p. 228, section 8.14.1 HealthBench Professional; Figure 8.14.A p. 229
Setting
length-adjusted; adaptive thinking at max effort; Claude Sonnet 4.6 grader; 5 trials; comparison model in the Opus 4.8 card
Reported by
vendor-reported
Document
[15] System Card: Claude Opus 4.8
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)
As printed
51.8
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.5
Setting
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.5 (57.2 unadjusted, 3818 chars)
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
32Gemini 3.8 FlashGoogle · Artificial Analysis…0.517Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | Gemini 3.8 Flash (high) | 51.7%
As printed
51.7%
Where
Score section, Length-Adjusted Score chart, Gemini 3.8 Flash (high) bar label; raw score 59.0% on the Raw Score tab
Setting
Artificial Analysis independent run, high reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (59.0 raw, 4,494 mean response chars)
Reported by
independent run
Document
[16] HealthBench Professional Benchmark | Artificial Analysis
33DeepSeek V4.1 FlashDeepSeek · Artificial Analysis…0.507Independent runOct 2026[16]
HealthBench Professional: Length-Adjusted Score | DeepSeek V4.1 Flash (max) | 50.7%
As printed
50.7%
Where
Score section, Length-Adjusted Score chart, DeepSeek V4.1 Flash (max) bar label; raw score 52.9% on the Raw Score tab
Setting
Artificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (52.9 raw, 2,760 mean response chars)
Reported by
independent run
Document
[16] HealthBench Professional Benchmark | Artificial Analysis
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%
As printed
48.5%
Where
Model Improvements comparison table, Clinical reasoning / HealthBench Professional row; Grok 4.6 column; September 21, 2026.
Setting
SpaceXAI evaluation; High effort; HealthBench Professional
Reported by
vendor-reported
Document
[14] Introducing Grok 4.7
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)
As printed
48.1
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.4
Setting
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.4 (51.9 unadjusted, 3308 chars)
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
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)
As printed
46.2
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5
Setting
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5 (51.0 unadjusted, 3616 chars)
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
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)
As printed
45.9
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.2
Setting
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.2 (50.0 unadjusted, 3400 chars)
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
38Claude Sonnet 4.6Anthropic · length-adjusted0.442Model's own labJun 2026[13]
HealthBench Professional 57.8 44.2 51.8 -
As printed
44.2
Where
p. 115, Table 8.1.A, row HealthBench Professional, column Claude Sonnet 4.6
Setting
length-adjusted; Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt; comparison column in the Sonnet 5 card. Other Anthropic prints: 44.4% (Fable card Figure 8.18.2.A), 41.7% (Opus 4.8 card, Sonnet 4.6 grader)
Reported by
vendor-reported
Document
[13] System Card: Claude Sonnet 5
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)
As printed
44.1
Where
p. 11, section 5.1 HealthBench, table "Reported as length-adjusted score (unadjusted, mean response length in characters)", column GPT-5.6 Luna (August)
Setting
ChatGPT production (Instant) deployment setting, length-adjusted, GPT-5.6 August Updates PDF column GPT-5.6 Luna (August) (46.8 unadjusted, 2,920 chars)
Reported by
vendor-reported
Document
[17] GPT-5.6 - August Updates (system card addendum)
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)
As printed
39.6
Where
Section 5.1 HealthBench, Table 6 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.1
Setting
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.1 (48.0 unadjusted, 4863 chars)
Reported by
vendor-reported
Document
[10] GPT-5.6 System Card
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)
As printed
38.4
Where
Section 4.1 HealthBench, Table 5 (reported as length-adjusted score (unadjusted, mean response length in characters)), column GPT-5.5 INSTANT
Setting
length-adjusted (40.7 unadjusted, 2,775 mean response chars); GPT-5.5 Instant system card Table 5, column GPT-5.5 INSTANT.
Reported by
vendor-reported
Document
[18] GPT-5.5 Instant System Card
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
As printed
35
Where
p. 54, Table 12 'Post-trained model evaluation results on various public benchmarks', Health group, column HealthBench Prof.; protocol Appendix K.6 p. 106: HealthBench Professional introduces a length penalty for the primary metric, to correct for a well-observed correlation between lengthy responses and artificially increased LLM-grader scores. For all reported scores, we use the standard GPT-5.4 grader and rubrics provided by OpenAI.
Setting
length-adjusted (HealthBench Professional length penalty), standard GPT-5.4 grader and OpenAI rubrics, Microsoft AI run; printed at integer precision.
Reported by
vendor-reported
Document
[19] MAI-Thinking-1: Building a Hill-Climbing Machine
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 | –
As printed
32.2
Where
p. 111, Table 8.1.A, row HealthBench Professional (Length-adjusted), column Haiku 4.5
Setting
Anthropic; extended thinking (Haiku 4.5 has no effort setting); Opus 4.8 grader; safety classifiers enabled; length-adjusted; measured for the Haiku 5.5 card
Reported by
vendor-reported
Document
[4] Claude Haiku 5.5 System Card
References

19 documents support this board

  1. 1.Claude Sonnet 5.5 System Cardsystem card, Anthropic, 28 Sep 2026. Every result it supports
  2. 2.Claude Fable 5 and Claude Mythos 5 System Cardsystem card, Anthropic, 9 Jun 2026. Every result it supports
  3. 3.Claude Opus 5.5 System Cardsystem card, Anthropic, 22 Sep 2026. Every result it supports
  4. 4.Claude Haiku 5.5 System Cardsystem card, Anthropic, 7 Oct 2026. Every result it supports
  5. 5.GPT-6 Astra System Card - HealthBench (Deployment Safety Hub)system card, OpenAI, 3 Sep 2026. Every result it supports
  6. 6.Addendum to GPT-6 Astra System Card: GPT-6.1 Solsystem card, OpenAI, 29 Sep 2026. Every result it supports
  7. 7.Claude Fable 5.1 and Claude Mythos 5.1 System Cardsystem card, Anthropic, 1 Sep 2026. Every result it supports
  8. 8.Addendum to GPT-6 Astra System Card: GPT-6.1 Terrasystem card, OpenAI, 26 Oct 2026. Every result it supports
  9. 9.Muse Wonder Model Cardmodel card, Meta, 12 Oct 2026. Every result it supports
  10. 10.GPT-5.6 System Cardsystem card, OpenAI, 9 Jul 2026. Every result it supports
  11. 11.System Card: Claude Opus 5system card, Anthropic, 24 Jul 2026. Every result it supports
  12. 12.Muse Spark 1.1 Evaluation Reportmodel card, Meta, 9 Jul 2026. Every result it supports
  13. 13.System Card: Claude Sonnet 5system card, Anthropic, 30 Jun 2026. Every result it supports
  14. 14.Introducing Grok 4.7launch post, SpaceXAI, 21 Sep 2026. Every result it supports
  15. 15.System Card: Claude Opus 4.8system card, Anthropic, 28 May 2026. Every result it supports
  16. 16.HealthBench Professional Benchmark | Artificial Analysisindependent leaderboard, Artificial Analysis, 2 Nov 2026. Every result it supports
  17. 17.GPT-5.6 - August Updates (system card addendum)system card, OpenAI, 6 Aug 2026. Every result it supports
  18. 18.GPT-5.5 Instant System Cardsystem card, OpenAI, 5 May 2026. Every result it supports
  19. 19.MAI-Thinking-1: Building a Hill-Climbing Machinemodel card, Microsoft AI, 12 Aug 2026. Every result it supports