GPT-6 Luna
Released 22 Sep 2026$0.1 input, $0.5 output per million tokens1.05M contextproprietaryAlso written as openai/gpt-6-luna
5 results on 4 of 13 boards, latest measured Oct 2026. Compare with other models
Clinical Benchmarks Index39.7Rank 31 of 1493 of 10 boardsAverage × multiplier 56.1 × 0.707 = 39.7This site’s own calculation. Working How it is computed
Results
Each line sits on its own board's scale. Tall tick: the board leader.
Clinical reasoning and knowledge
- HealthBench ProfessionalListed 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 figure0.655Rank 5 of 35Leader GPT-6 Astra (Anthropic run) 0.703
- HealthBench ProfessionalOpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)0.608Rank 11 of 35Leader GPT-6 Astra (Anthropic run) 0.703
Documentation and coding
- MedScribe (Vals AI)model ID openai/gpt-6-luna; max_output_tokens=128000; reasoning_effort=max83.71Rank 40 of 105Leader Claude Opus 5.5 91.43
- MedCode (Vals AI)model ID openai/gpt-6-luna; reasoning_effort=max; max_output_tokens=12800044.69Rank 38 of 103Leader Claude Opus 5 63.57
EHR and workflow agents
- PhysicianBenchListed 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 figure33.6Rank 11 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
Index working
The Clinical Benchmarks Index is this site's own calculation: a weighted average of the board scores times a multiplier for the boards behind it. How it is computed
- HealthBench Professional0.60860.8×0.743OpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)
- MedScribe (Vals AI)83.7183.7×0.25, near its ceilingNear its ceiling: leader 91.4, weight 0.25model ID openai/gpt-6-luna; max_output_tokens=128000; reasoning_effort=max
- MedCode (Vals AI)44.6944.7×0.911model ID openai/gpt-6-luna; reasoning_effort=max; max_output_tokens=128000
- Weighted average of 3 boards
- 56.1
- Multiplier for 3 of 10 boards
- × 0.707
- Index
- 56.1 × 0.707 = 39.7
Score: the result on the board’s own 0 to 100 scale. Dot: this model; tick: the board’s leader. Weight: how much the board counts in the weighted average; bold where the board is near its ceiling and counts for less. 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 5 results
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 figureClaude 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. 131-132HealthBench 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 document11HealthBench 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 document40MedScribe (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=maxVals 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 document38MedCode (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=128000Vals 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 document11PhysicianBench 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 figureClaude 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 runsThis 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
Other OpenAI models: GPT-4.1, GPT-4.1 mini, GPT-4o, 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 Astra, GPT-6 Sol, GPT OSS 120B, GPT OSS 20B, o3, o4-mini