Clinical Benchmarks
Menu

GPT-6 Astra

Released 3 Sep 2026$10 input, $50 output per million tokens1.05M contextproprietaryAlso written as GPT-6 Astra (xhigh), GPT6 Astra, GPT-6-Astra, GPT Astra, GPT-6 Astra (max), Astra, gpt-6-astra

4 results on 3 of 13 boards, latest measured Sep 2026. Compare with other models

Clinical Benchmarks Index44.0Rank 21 of 1493 of 10 boardsAverage × multiplier 62.2 × 0.707 = 44.0This 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

  1. HealthBench Professional
    Anthropic public-API reproduction; max effort; no system prompt; Opus 4.8 grader; length-adjusted; raw 74.0%
    0.703
    Rank 1 of 35Leads this board
    Independent run
    Measured Sep 2026
  2. HealthBench Professional
    length-adjusted, max reasoning effort (69.5 unadjusted, 4,097 mean response chars); GPT-6 Astra system card Table 6, column 'gpt-6 Astra'.
    0.647
    Rank 7 of 35Leader GPT-6 Astra (Anthropic run) 0.703
    Vendor-reported
    Measured Sep 2026

Documentation and coding

  1. MedScribe (Vals AI)
    87.91
    Rank 14 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedCode (Vals AI)
    48.49
    Rank 26 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026

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 Professional0.70370.3×0.743Anthropic public-API reproduction; max effort; no system prompt; Opus 4.8 grader; length-adjusted; raw 74.0%
  • MedScribe (Vals AI)87.9187.9×0.25, near its ceilingNear its ceiling: leader 91.4, weight 0.25
  • MedCode (Vals AI)48.4948.5×0.911
Weighted average of 3 boards
62.2
Multiplier for 3 of 10 boards
× 0.707
Index
62.2 × 0.707 = 44.0

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 4 results
  1. 1HealthBench Professional Anthropic public-API… 0.703
    Printed as 70.3%Independent run, measured Sep 2026Configuration: Anthropic public-API reproduction; max effort; no system prompt; Opus 4.8 grader; length-adjusted; raw 74.0%
    Claude Sonnet 5.5 System Card system card, Anthropic, 28 Sep 2026. p. 138, paragraph above Figure 8.15.B, HealthBench Professional after length adjustment.
    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%).
    Every result from this document
  2. 7HealthBench Professional length-adjusted 0.647
    Printed as 64.7Vendor-reported, measured Sep 2026Configuration: length-adjusted, max reasoning effort (69.5 unadjusted, 4,097 mean response chars); GPT-6 Astra system card Table 6, column 'gpt-6 Astra'.
    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 Astra 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. 14MedScribe (Vals AI) 87.91
    Printed as 87.91%Official leaderboard, measured Sep 2026
    Vals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 14 of 105 (GPT-6 Astra), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["openai/gpt-6-astra"].
    14 | GPT-6 Astra | 87.91%±1.94 | $10/$50 | 2m34s
    Every result from this document
  4. 26MedCode (Vals AI) 48.49
    Printed as 48.49%Official leaderboard, measured Sep 2026
    Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 26 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["openai/gpt-6-astra"].
    26 | GPT-6 Astra | 48.49%±2.13 | $10/$50 | 102.86s
    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 Luna, GPT-6 Sol, GPT OSS 120B, GPT OSS 20B, o3, o4-mini