HealthBench Professional

Meta logoMuse Wonder Full on HealthBench Professional

Rank 11 of 43, updated November 2, 2026.

Muse Wonder Full scores 0.623 on HealthBench Professional, rank 11 of 43 models on the board. 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.

11
rank of 43
0.623
length-adjusted score
–
score before the length adjustment, not printed in the source
0.080
gap to the leader, GPT-6 Astra (Anthropic run)
1M
context window, tokens
–
no published list pricing

Where it sits on the board

The models ranked around Muse Wonder Full, by length-adjusted score. Differences are against Muse Wonder Full.

RankModelLength-adjustedBefore the adjustmentDifference
8OpenAI logoGPT-6.1 Sol0.6420.672+0.019
9Anthropic logoClaude Fable 5 (September card)0.6330.689+0.010
10OpenAI logoGPT-6.1 Terra0.6270.642+0.004
11Meta logoMuse Wonder Full0.623––
12Anthropic logoClaude Fable 5.10.6210.742-0.002
13OpenAI logoGPT-6 Luna0.6080.612-0.015
14OpenAI logoGPT-6 Sol0.6080.595-0.015

Result and API facts

Rank11 of 43
Length-adjusted score0.623
Score before the length adjustmentnot printed in the source
LabMeta
Context window1M tokens
API price per 1M tokensno published list pricing
Licenseproprietary
SourceMuse Wonder Model Card (model card)
Released2026-10-12

Source of this score

Read from Muse Wonder Model Card (model card, Meta, 2026-10-12). Vendor-reported. Confidence: verified. Configuration: Meta internal run; length-normalized weighted rubric score, GPT-5.4 grader, no tools, max reasoning effort (Muse Wonder Model Card p. 3 table, Muse Wonder Full (max) column).

p. 3, results table (image), HealthBench Pro row, Muse Wonder Full (max) column; methodology p. 4full entry on the sources page
HealthBench Pro (Open-ended health queries) | Muse Wonder Full (max) 62.3 | Muse Wonder (max) 60.5 | Claude Fable 5.1 (max) 62.1 | GPT-6 Astra (max) 65.3 | Claude Opus 5.5 (max) 65.6 Methodology (p. 4): HealthBench Pro evaluates responses to 525 professional-grade health questions. Models answer without tools, and a GPT-5.4 grader scores each response against physician-written rubrics. We run the official tasks and grading in a common internal framework. The primary metric is the length-normalized weighted rubric score.

Position in the field

The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.080. Directly above sits GPT-6.1 Terra at 0.627. Directly below sits Claude Fable 5.1 at 0.621. 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 Muse Wonder Full score on HealthBench Professional?

Muse Wonder Full scores 0.623 on HealthBench Professional, which places it at rank 11 of 43 models on the board as of November 2, 2026. The number was read from Muse Wonder Model Card, listed on the sources page.

How much does Muse Wonder Full cost to run?

Meta has not published API pricing for Muse Wonder Full.

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

  • Muse Wonder Full vs GPT-6 Astra (Anthropic run)
    0.623 vs 0.703, GPT-6 Astra (Anthropic run) by 0.080
  • Muse Wonder Full vs Claude Sonnet 5.5
    0.623 vs 0.692, Claude Sonnet 5.5 by 0.069
  • Muse Wonder Full vs Claude Fable 5
    0.623 vs 0.660, Claude Fable 5 by 0.037
  • Muse Wonder Full vs Claude Opus 5.5
    0.623 vs 0.656, Claude Opus 5.5 by 0.033
  • Muse Wonder Full vs GPT-6 Luna (Anthropic run)
    0.623 vs 0.655, GPT-6 Luna (Anthropic run) by 0.032
  • Muse Wonder Full vs Claude Haiku 5.5
    0.623 vs 0.648, Claude Haiku 5.5 by 0.025
  • Muse Wonder Full vs GPT-6 Astra
    0.623 vs 0.647, GPT-6 Astra by 0.024
  • Muse Wonder Full vs GPT-6.1 Sol
    0.623 vs 0.642, GPT-6.1 Sol by 0.019
  • Muse Wonder Full vs Claude Fable 5 (September card)
    0.623 vs 0.633, Claude Fable 5 (September card) by 0.010
  • Muse Wonder Full vs GPT-6.1 Terra
    0.623 vs 0.627, GPT-6.1 Terra by 0.004
  • Muse Wonder Full vs Claude Fable 5.1
    0.623 vs 0.621, Muse Wonder Full by 0.002
  • Muse Wonder Full vs GPT-6 Luna
    0.623 vs 0.608, Muse Wonder Full by 0.015
  • Muse Wonder Full vs GPT-6 Sol
    0.623 vs 0.608, Muse Wonder Full by 0.015
  • Muse Wonder Full vs GPT-5.6 Sol
    0.623 vs 0.605, Muse Wonder Full by 0.018
  • Muse Wonder Full vs Muse Wonder
    0.623 vs 0.605, Muse Wonder Full by 0.018
  • Muse Wonder Full vs Claude Opus 5
    0.623 vs 0.598, Muse Wonder Full by 0.025
  • Muse Wonder Full vs Muse Spark 1.1
    0.623 vs 0.593, Muse Wonder Full by 0.030
  • Muse Wonder Full vs Claude Sonnet 5
    0.623 vs 0.578, Muse Wonder Full by 0.045
  • Muse Wonder Full vs GPT-5.6 Terra
    0.623 vs 0.577, Muse Wonder Full by 0.046
  • Muse Wonder Full vs Claude Opus 4.8 (Opus 4.8 grader)
    0.623 vs 0.574, Muse Wonder Full by 0.049
  • Muse Wonder Full vs Grok 4.7
    0.623 vs 0.567, Muse Wonder Full by 0.056
  • Muse Wonder Full vs Claude Opus 4.8
    0.623 vs 0.558, Muse Wonder Full by 0.065
  • Muse Wonder Full vs GPT-5.6 Luna
    0.623 vs 0.557, Muse Wonder Full by 0.066
  • Muse Wonder Full vs Gemini 4 Argon
    0.623 vs 0.551, Muse Wonder Full by 0.072
  • Muse Wonder Full vs Muse Spark
    0.623 vs 0.541, Muse Wonder Full by 0.082
  • Muse Wonder Full vs GPT-5.6 Sol (August)
    0.623 vs 0.540, Muse Wonder Full by 0.083
  • Muse Wonder Full vs Kimi K3
    0.623 vs 0.532, Muse Wonder Full by 0.091
  • Muse Wonder Full vs GLM 5.3
    0.623 vs 0.528, Muse Wonder Full by 0.095
  • Muse Wonder Full vs Claude Opus 4.7
    0.623 vs 0.519, Muse Wonder Full by 0.104
  • Muse Wonder Full vs GPT-5.5
    0.623 vs 0.518, Muse Wonder Full by 0.105
  • Muse Wonder Full vs Gemini 3.8 Flash
    0.623 vs 0.517, Muse Wonder Full by 0.106
  • Muse Wonder Full vs DeepSeek V4.1 Flash
    0.623 vs 0.507, Muse Wonder Full by 0.116
  • Muse Wonder Full vs Grok 4.6
    0.623 vs 0.485, Muse Wonder Full by 0.138
  • Muse Wonder Full vs GPT-5.4
    0.623 vs 0.481, Muse Wonder Full by 0.142
  • Muse Wonder Full vs GPT-5
    0.623 vs 0.462, Muse Wonder Full by 0.161
  • Muse Wonder Full vs GPT-5.2
    0.623 vs 0.459, Muse Wonder Full by 0.164
  • Muse Wonder Full vs Claude Sonnet 4.6
    0.623 vs 0.442, Muse Wonder Full by 0.181
  • Muse Wonder Full vs GPT-5.6 Luna (August)
    0.623 vs 0.441, Muse Wonder Full by 0.182
  • Muse Wonder Full vs GPT-5.1
    0.623 vs 0.396, Muse Wonder Full by 0.227
  • Muse Wonder Full vs GPT-5.5 Instant
    0.623 vs 0.384, Muse Wonder Full by 0.239
  • Muse Wonder Full vs MAI-Thinking-1
    0.623 vs 0.350, Muse Wonder Full by 0.273
  • Muse Wonder Full vs Claude Haiku 4.5
    0.623 vs 0.322, Muse Wonder Full by 0.301

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