Clinical Benchmarks
Menu

Claude Fable 5.1

Released 1 Sep 2026$10 input, $50 output per million tokens1.0M contextproprietaryAlso written as Claude Fable 5.1/Mythos 5.1, Fable 5.1

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

Clinical Benchmarks Index50.3Rank 12 of 1494 of 10 boardsAverage × multiplier 61.6 × 0.816 = 50.3This 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
    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%).
    0.621
    Rank 10 of 35Leader GPT-6 Astra (Anthropic run) 0.703
    Vendor-reported
    Measured Sep 2026

Documentation and coding

  1. MedScribe (Vals AI)
    91.29
    Rank 2 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedCode (Vals AI)
    53.51
    Rank 7 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026

EHR and workflow agents

  1. PhysicianBench
    Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; safety classifiers enabled
    61.0
    Rank 3 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
    Vendor-reported
    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 Professional0.62162.1×0.743length-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%).
  • MedScribe (Vals AI)91.2991.3×0.25, near its ceilingNear its ceiling: leader 91.4, weight 0.25
  • MedCode (Vals AI)53.5153.5×0.911
  • PhysicianBench61.061.0×0.79Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; safety classifiers enabled
Weighted average of 4 boards
61.6
Multiplier for 4 of 10 boards
× 0.816
Index
61.6 × 0.816 = 50.3

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. 10HealthBench Professional length-adjusted 0.621
    Printed as 62.1%Vendor-reported, measured Sep 2026Configuration: 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%).
    Claude Fable 5.1 and Claude Mythos 5.1 System Card system card, Anthropic, 1 Sep 2026. p. 199, sec. 8.17.2 (same figure printed as 62.1% in Table 8.1.A, p. 167)
    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%.
    Every result from this document
  2. 2MedScribe (Vals AI) 91.29
    Printed as 91.29%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 2 of 105 (Claude Fable 5.1), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-fable-5-1"].
    2 | Claude Fable 5.1 | 91.29%±1.95 | $10/$50 | 3m08s
    Every result from this document
  3. 7MedCode (Vals AI) 53.51
    Printed as 53.51%Official leaderboard, measured Sep 2026
    Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 7 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-fable-5-1"].
    7 | Claude Fable 5.1 | 53.51%±2.17 | $10/$50 | 3m35s
    Every result from this document
  4. 3PhysicianBench Anthropic harness 61.0
    Printed as 61.0%Vendor-reported, measured Sep 2026Configuration: Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; safety classifiers enabled
    Claude Sonnet 5.5 System Card system card, Anthropic, 28 Sep 2026. pp. 138–139, Section 8.15.3; PhysicianBench pass@1, Claude Fable 5.1 (max).
    PhysicianBench is a public benchmark of 100 physician tasks carried out in an EHR. At max effort, Claude Sonnet 5.5 passes 63.2% of attempts, well above Claude Sonnet 5 (37.4%), level with Claude Fable 5.1 (61.0%), about 6 points above Claude Opus 5 (57.6%) and about 5 points below Claude Opus 5.5 (68.4%).
    Every result from this document

Other Anthropic models: Claude 3.7 Sonnet, Claude Fable 5, Claude Haiku 4.5, Claude Haiku 5.5, Claude Opus 4.1, Claude Opus 4.5, Claude Opus 4.6, Claude Opus 4.7, Claude Opus 4.8, Claude Opus 5, Claude Opus 5.5, Claude Sonnet 4, Claude Sonnet 4.5, Claude Sonnet 4.6, Claude Sonnet 5, Claude Sonnet 5.5