HealthBench Professional

Anthropic logoClaude Fable 5 on HealthBench Professional

Rank 3 of 43, updated November 2, 2026.

Claude Fable 5 scores 0.660 on HealthBench Professional, rank 3 of 43 models on the board. Anthropic's top-tier model, positioned above the Opus line for the hardest reasoning work. HealthBench Professional scores models on 525 tasks drawn from real clinician conversations, graded criterion by criterion against physician-written rubrics on a 0 to 1 scale.

3
rank of 43
0.660
length-adjusted score
0.703
score before the length adjustment
0.043
gap to the leader, GPT-6 Astra (Anthropic run)
1.0M
context window, tokens
$10.00 / $50.00
input / output price per 1M tokens

Where it sits on the board

The models ranked around Claude Fable 5, by length-adjusted score. Differences are against Claude Fable 5.

RankModelLength-adjustedBefore the adjustmentDifference
1OpenAI logoGPT-6 Astra (Anthropic run)0.7030.740+0.043
2Anthropic logoClaude Sonnet 5.50.6920.771+0.032
3Anthropic logoClaude Fable 50.6600.703–
4Anthropic logoClaude Opus 5.50.6560.771-0.004
5OpenAI logoGPT-6 Luna (Anthropic run)0.655–-0.005
6Anthropic logoClaude Haiku 5.50.6480.710-0.012
7OpenAI logoGPT-6 Astra0.6470.682-0.013

Result and API facts

Rank3 of 43
Length-adjusted score0.660
Score before the length adjustment0.703
LabAnthropic
Context window1.0M tokens
API price per 1M tokens$10.00 in / $50.00 out
Licenseproprietary
SourceClaude Fable 5 and Claude Mythos 5 System Card (system card)
Released2026-06-09

Source of this score

Read from Claude Fable 5 and Claude Mythos 5 System Card (system card, Anthropic, 2026-06-09). Vendor-reported. Confidence: verified. Configuration: 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..

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 52 corroborating documentsfull entry on the sources page
HealthBench Professional 66.0 - 64.7 56.9 51.8 -

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.043. Directly above sits Claude Sonnet 5.5 at 0.692. Directly below sits Claude Opus 5.5 at 0.656. The scores on this page are compiled from published documents rather than from one controlled run, so a small gap between 2 models can reflect a difference in grader version, reasoning effort, or deployment setting as well as a difference in capability.

What does Claude Fable 5 score on HealthBench Professional?

Claude Fable 5 scores 0.660 on HealthBench Professional, which places it at rank 3 of 43 models on the board as of November 2, 2026. The number was read from Claude Fable 5 and Claude Mythos 5 System Card, listed on the sources page.

How much does Claude Fable 5 cost to run?

Claude Fable 5 is priced at $10.00 per million input tokens and $50.00 per million output tokens through Anthropic's API.

Pairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.

  • Claude Fable 5 vs GPT-6 Astra (Anthropic run)
    0.660 vs 0.703, GPT-6 Astra (Anthropic run) by 0.043
  • Claude Fable 5 vs Claude Sonnet 5.5
    0.660 vs 0.692, Claude Sonnet 5.5 by 0.032
  • Claude Fable 5 vs Claude Opus 5.5
    0.660 vs 0.656, Claude Fable 5 by 0.004
  • Claude Fable 5 vs GPT-6 Luna (Anthropic run)
    0.660 vs 0.655, Claude Fable 5 by 0.005
  • Claude Fable 5 vs Claude Haiku 5.5
    0.660 vs 0.648, Claude Fable 5 by 0.012
  • Claude Fable 5 vs GPT-6 Astra
    0.660 vs 0.647, Claude Fable 5 by 0.013
  • Claude Fable 5 vs GPT-6.1 Sol
    0.660 vs 0.642, Claude Fable 5 by 0.018
  • Claude Fable 5 vs Claude Fable 5 (September card)
    0.660 vs 0.633, Claude Fable 5 by 0.027
  • Claude Fable 5 vs GPT-6.1 Terra
    0.660 vs 0.627, Claude Fable 5 by 0.033
  • Claude Fable 5 vs Muse Wonder Full
    0.660 vs 0.623, Claude Fable 5 by 0.037
  • Claude Fable 5 vs Claude Fable 5.1
    0.660 vs 0.621, Claude Fable 5 by 0.039
  • Claude Fable 5 vs GPT-6 Luna
    0.660 vs 0.608, Claude Fable 5 by 0.052
  • Claude Fable 5 vs GPT-6 Sol
    0.660 vs 0.608, Claude Fable 5 by 0.052
  • 0.660 vs 0.605, Claude Fable 5 by 0.055
  • Claude Fable 5 vs Muse Wonder
    0.660 vs 0.605, Claude Fable 5 by 0.055
  • 0.660 vs 0.598, Claude Fable 5 by 0.062
  • Claude Fable 5 vs Muse Spark 1.1
    0.660 vs 0.593, Claude Fable 5 by 0.067
  • Claude Fable 5 vs Claude Sonnet 5
    0.660 vs 0.578, Claude Fable 5 by 0.082
  • Claude Fable 5 vs GPT-5.6 Terra
    0.660 vs 0.577, Claude Fable 5 by 0.083
  • Claude Fable 5 vs Claude Opus 4.8 (Opus 4.8 grader)
    0.660 vs 0.574, Claude Fable 5 by 0.086
  • Claude Fable 5 vs Grok 4.7
    0.660 vs 0.567, Claude Fable 5 by 0.093
  • Claude Fable 5 vs Claude Opus 4.8
    0.660 vs 0.558, Claude Fable 5 by 0.102
  • Claude Fable 5 vs GPT-5.6 Luna
    0.660 vs 0.557, Claude Fable 5 by 0.103
  • Claude Fable 5 vs Gemini 4 Argon
    0.660 vs 0.551, Claude Fable 5 by 0.109
  • Claude Fable 5 vs Muse Spark
    0.660 vs 0.541, Claude Fable 5 by 0.119
  • Claude Fable 5 vs GPT-5.6 Sol (August)
    0.660 vs 0.540, Claude Fable 5 by 0.120
  • Claude Fable 5 vs Kimi K3
    0.660 vs 0.532, Claude Fable 5 by 0.128
  • Claude Fable 5 vs GLM 5.3
    0.660 vs 0.528, Claude Fable 5 by 0.132
  • Claude Fable 5 vs Claude Opus 4.7
    0.660 vs 0.519, Claude Fable 5 by 0.141
  • Claude Fable 5 vs GPT-5.5
    0.660 vs 0.518, Claude Fable 5 by 0.142
  • Claude Fable 5 vs Gemini 3.8 Flash
    0.660 vs 0.517, Claude Fable 5 by 0.143
  • Claude Fable 5 vs DeepSeek V4.1 Flash
    0.660 vs 0.507, Claude Fable 5 by 0.153
  • Claude Fable 5 vs Grok 4.6
    0.660 vs 0.485, Claude Fable 5 by 0.175
  • Claude Fable 5 vs GPT-5.4
    0.660 vs 0.481, Claude Fable 5 by 0.179
  • Claude Fable 5 vs GPT-5
    0.660 vs 0.462, Claude Fable 5 by 0.198
  • Claude Fable 5 vs GPT-5.2
    0.660 vs 0.459, Claude Fable 5 by 0.201
  • Claude Fable 5 vs Claude Sonnet 4.6
    0.660 vs 0.442, Claude Fable 5 by 0.218
  • Claude Fable 5 vs GPT-5.6 Luna (August)
    0.660 vs 0.441, Claude Fable 5 by 0.219
  • Claude Fable 5 vs GPT-5.1
    0.660 vs 0.396, Claude Fable 5 by 0.264
  • Claude Fable 5 vs GPT-5.5 Instant
    0.660 vs 0.384, Claude Fable 5 by 0.276
  • Claude Fable 5 vs MAI-Thinking-1
    0.660 vs 0.350, Claude Fable 5 by 0.310
  • Claude Fable 5 vs Claude Haiku 4.5
    0.660 vs 0.322, Claude Fable 5 by 0.338

Where the scores come from and how they are read is on the methodology page. The full ranking is on the leaderboard.