Clinical Benchmarks

GPT-6 Luna

Released 22 Sep 2026$0.1 input, $0.5 output per million tokens1.05M contextproprietaryAlso written as openai/gpt-6-luna

8 results on 7 of 14 boards, latest measured Nov 2026. Compare with other models

Clinical Benchmarks Index50.6Rank 16 of 1286 of 12 boardsThis site’s own calculation. Show the working How it is computed

On the Clinical Benchmarks Index

The top 15 on the index, then GPT-6 Luna at rank 16. Select a column to open that model.

Board by board

GPT-6 Luna against the top 10 on each board it has a result on, on that board's own scale. Its own column is in colour.

HealthBench Professionalrank 5 of 43

  1. 0.703GPT-6 Astra (Anthropic run)
  2. 0.692Claude Sonnet 5.5
  3. 0.660Claude Fable 5
  4. 0.656Claude Opus 5.5
  5. 0.655GPT-6 Luna (Anthropic run)
  6. 0.648Claude Haiku 5.5
  7. 0.642GPT-6.1 Sol
  8. 0.627GPT-6.1 Terra
  9. 0.623Muse Wonder Full
  10. 0.621Claude Fable 5.1

37 modelsFull board

Bedside Benchrank 9 of 15

  1. 94.6Claude Opus 5
  2. 94.3Muse Spark Open
  3. 93.4GPT-6 Astra
  4. 92.7Gemini 4 Argon
  5. 91.1GPT-5.6 Sol
  6. 89.7Kimi K3
  7. 89.1Ember-1
  8. 88.1GPT-6 Sol
  9. 87.2GPT-6 Luna
  10. 86.9GLM 5.3

15 modelsFull board

MedScribe (Vals AI)rank 41 of 106

  1. 91.43Claude Opus 5.5
  2. 91.29Claude Fable 5.1
  3. 91.10Claude Sonnet 5.5
  4. 90.98Claude Opus 5
  5. 90.06Muse Spark 1.2
  6. 89.38Grok 4.7
  7. 88.94GLM 5.3 Flash
  8. 88.89Muse Spark 1.1
  9. 88.81GLM 5.3
  10. 83.71GPT-6 Luna

95 modelsFull board

MedCode (Vals AI)rank 39 of 104

  1. 63.57Claude Opus 5
  2. 59.06Gemini 3.1 Pro Preview (02/26)
  3. 58.80Gemini 4 Argon
  4. 56.07Claude Fable 5
  5. 55.92Gemini 3 Flash (12/25)
  6. 55.83Gemini 3.5 Flash
  7. 54.86Claude Opus 4.7
  8. 53.51Claude Fable 5.1
  9. 53.39Gemini 3.7 Flash
  10. 44.69GPT-6 Luna

95 modelsFull board

MLCR-AArank 11 of 27

  1. 41.7Claude Sonnet 5.5 (Max, Default Fallback)
  2. 41.7GPT-6 Astra (Max)
  3. 38.3GPT-6.1 Sol (Max)
  4. 38.3Kimi K3.1 Pro
  5. 35.0Claude Haiku 5.5 (Max)
  6. 33.9GPT-6 Sol (Max)
  7. 31.7GPT-5.5 Instant (June 2026)
  8. 30.6GPT-6.1 Terra (Max)
  9. 27.8Claude Opus 5.5
  10. 26.1GPT-6 Luna (Max)

27 modelsFull board

PhysicianBenchrank 11 of 28

  1. 68.4Claude Opus 5.5 (max)
  2. 63.2Claude Sonnet 5.5 (max)
  3. 61.0Claude Fable 5.1 (max)
  4. 57.6Claude Opus 5 (max)
  5. 46.3GPT-5.5
  6. 43.0Claude Haiku 5.5 (max)
  7. 37.4Claude Sonnet 5 (max)
  8. 33.6GPT-6 Luna (Anthropic run)
  9. 31.7Claude Opus 4.6
  10. 29.3Claude Opus 4.7

20 modelsFull board

RCM-Benchrank 16 of 20

  1. 92.68Claude Opus 5
  2. 91.49Gemini 4 Argon
  3. 91.24Claude Sonnet 5
  4. 91.21GPT-5.6 Sol
  5. 91.05Claude Sonnet 5.5
  6. 90.23Gemini 3.8 Flash
  7. 90.14Claude Opus 5.5
  8. 89.82Claude Sonnet 4.6
  9. 88.99DeepSeek V4.1 Flash
  10. 85.81GPT-6 Luna

20 modelsFull board

Every result, with its source

Each line sits on its own board's scale. Tall tick: the board leader.

Clinical reasoning and knowledge

  1. HealthBench Professional
    Listed as GPT-6 Luna (Anthropic run)
    Run by Anthropic through OpenAI's public API; max effort; Opus 4.8 grader; length-adjusted; not OpenAI's published figure
    0.655
    Rank 5 of 43Leader GPT-6 Astra (Anthropic run) 0.703
    Independent run
    Measured Oct 2026
  2. HealthBench Professional
    OpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)
    0.608
    Rank 13 of 43Leader GPT-6 Astra (Anthropic run) 0.703
    Vendor-reported
    Measured Sep 2026
  3. Bedside Bench
    Score (avg@3)
    87.2
    Rank 9 of 15 here, 16 models on the boardLeader Claude Opus 5 94.6
    Official leaderboard
    Measured Oct 2026

Documentation and coding

  1. MedScribe (Vals AI)
    model ID openai/gpt-6-luna; max_output_tokens=128000; reasoning_effort=max
    83.71
    Rank 41 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedCode (Vals AI)
    model ID openai/gpt-6-luna; reasoning_effort=max; max_output_tokens=128000
    44.69
    Rank 39 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  3. MLCR-AA
    overall pass rate, Max
    26.1
    Rank 11 of 27Leader Claude Sonnet 5.5 (Max, Default Fallback) 41.7
    Independent run
    Measured Nov 2026

EHR and workflow agents

  1. PhysicianBench
    Listed as GPT-6 Luna (Anthropic run)
    Run by Anthropic through OpenAI's public API; Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; not OpenAI's published figure
    33.6
    Rank 11 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
    Independent run
    Measured Oct 2026
  2. RCM-Bench
    Score (avg@3), medium reasoning
    85.81
    Rank 16 of 20Leader Claude Opus 5 92.68
    Official leaderboard
    Measured Oct 2026

Index working

Show the working: each board’s result, how hard the board runs and the field average

The Clinical Benchmarks Index is this site's own calculation from 12 boards. How it is computed

  • HealthBench Professional0.60860.8+5.0 easy board55.80.743 weightOpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)
  • MedScribe (Vals AI)83.7183.7+33.8 easy board49.90.15 weight, near its ceilingNear its ceiling: leader 91.4, weight 0.15model ID openai/gpt-6-luna; max_output_tokens=128000; reasoning_effort=max
  • MedCode (Vals AI)44.6944.7−3.3 hard board48.00.319 weightmodel ID openai/gpt-6-luna; reasoning_effort=max; max_output_tokens=128000
  • Bedside Bench87.287.2+39.2 easy board48.00.25 weight, near its ceilingNear its ceiling: leader 94.6, weight 0.25Score (avg@3)
  • RCM-Bench85.8185.8+36.5 easy board49.30.088 weight, near its ceilingNear its ceiling: leader 92.7, weight 0.088Score (avg@3), medium reasoning
  • MLCR-AA26.126.1−26.5 hard board52.60.6 weightoverall pass rate, Max
Adjusted average of 6 boards, by weight
52.2
Field average, counts for 20% with 6 of 12 boards
44.2
Index
= 50.6

Score: the result on the board’s own 0 to 100 scale (dot; tick: the board’s leader). Board runs: how far the board’s scores sit above or below the same models’ scores on the other boards. Adjusted: the score minus that offset. The index is the adjusted average with the field average mixed in, more of it the fewer boards a model has. Each result links to its quote and page; the line under it is the setting it was measured with.

Sources

The quote, page and document for each of the 8 results
  1. 5HealthBench Professional Run by Anthropic through… 0.655
    Printed as 65.5%Independent run, measured Oct 2026Configuration: Run by Anthropic through OpenAI's public API; max effort; Opus 4.8 grader; length-adjusted; not OpenAI's published figure
    Claude Haiku 5.5 System Card system card, Anthropic, 7 Oct 2026. 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
    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.
    Every result from this document
  2. 13HealthBench Professional length-adjusted 0.608
    Printed as 60.8Vendor-reported, measured Sep 2026Configuration: OpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)
    GPT-6 Astra System Card - HealthBench (Deployment Safety Hub) system card, OpenAI, 3 Sep 2026. Section 11.4.1, Table 29, HealthBench Professional length-adjusted, GPT-6 Luna column; September 22 correction.
    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)
    Every result from this document
  3. 41MedScribe (Vals AI) gpt-6-luna 83.71
    Printed as 83.71%Official leaderboard, measured Sep 2026Configuration: model ID openai/gpt-6-luna; max_output_tokens=128000; reasoning_effort=max
    Vals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 40 of 105 (GPT-6 Luna), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-6-luna"].
    40 | GPT-6 Luna | 83.71%±1.95 | $0.1/$0.5 | 2m50s
    Every result from this document
  4. 39MedCode (Vals AI) gpt-6-luna 44.69
    Printed as 44.69%Official leaderboard, measured Sep 2026Configuration: model ID openai/gpt-6-luna; reasoning_effort=max; max_output_tokens=128000
    Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 38 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-6-luna"].
    38 | GPT-6 Luna | 44.69%±2.30 | $0.1/$0.5 | 108.77s
    Every result from this document
  5. 11PhysicianBench Run by Anthropic through… 33.6
    Printed as 33.6%Independent run, measured Oct 2026Configuration: Run by Anthropic through OpenAI's public API; Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; not OpenAI's published figure
    Claude Haiku 5.5 System Card system card, Anthropic, 7 Oct 2026. p. 133, Section 8.11.2; p. 132, Figure 8.11.2.A GPT-6 Luna bar; p. 131-132, Section 8.11.1 says GPT-6 Luna scores come from Anthropic's own runs
    This was 9.4 points above GPT-6 Luna at 33.6% (95% confidence interval 2.6 to 16.2 points, paired by task)
    Every result from this document
  6. 9Bedside Bench Score 87.2
    Printed as 87.2Official leaderboard, measured Oct 2026Configuration: Score (avg@3)
    Bedside Bench on the Fireworks Specialized Intelligence Index official leaderboard, Fireworks AI, 22 Oct 2026. https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/bedside-bench (feed: benchmarks[id=healthcare/bedside-bench].results)
    GPT-6 Luna 87.2 (Score (avg@3)), rank 10
    Every result from this document
  7. 16RCM-Bench Score 85.81
    Printed as 85.81Official leaderboard, measured Oct 2026Configuration: Score (avg@3), medium reasoning
    RCM-Bench-1 on the Fireworks Specialized Intelligence Index official leaderboard, Fireworks AI, 22 Oct 2026. https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
    GPT-6 Luna 85.8081 (Score (avg@3)), rank 16
    Every result from this document
  8. 11MLCR-AA overall pass rate 26.1
    Printed as 26.1%Independent run, measured Nov 2026Configuration: overall pass rate, Max
    MLCR-AA (Medical Long Context Reasoning), Artificial Analysis official leaderboard, Artificial Analysis, 5 Nov 2026. artificialanalysis.ai/evaluations/mlcr-aa, Score chart (mlcrAaOverallPassRate)
    GPT-6 Luna (Max): 26.1% (Score: share of responses judged complete with no claim contradicting the record)
    Every result from this document

Other OpenAI models: GPT-5, GPT-5.1, GPT-5.2, GPT-5.3-Codex, GPT-5.4, GPT-5.4 mini, GPT-5.4 nano, GPT-5.5, GPT-5.5 Instant, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5 mini, GPT-5 nano, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Sol, o3, o4-mini