Muse Wonder Full on HealthBench Professional
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.
Where it sits on the board
The models ranked around Muse Wonder Full, by length-adjusted score. Differences are against Muse Wonder Full.
| Rank | Model | Length-adjusted | Before the adjustment | Difference |
|---|---|---|---|---|
| 8 | 0.642 | 0.672 | +0.019 | |
| 9 | 0.633 | 0.689 | +0.010 | |
| 10 | 0.627 | 0.642 | +0.004 | |
| 11 | 0.623 | – | – | |
| 12 | 0.621 | 0.742 | -0.002 | |
| 13 | 0.608 | 0.612 | -0.015 | |
| 14 | 0.608 | 0.595 | -0.015 |
Result and API facts
| Rank | 11 of 43 |
|---|---|
| Length-adjusted score | 0.623 |
| Score before the length adjustment | not printed in the source |
| Lab | Meta |
| Context window | 1M tokens |
| API price per 1M tokens | no published list pricing |
| License | proprietary |
| Source | Muse Wonder Model Card (model card) |
| Released | 2026-10-12 |
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).
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.
Head to head
Score-difference matrixPairings 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)
- Muse Wonder Full vs Claude Sonnet 5.5
- Muse Wonder Full vs Claude Fable 5
- Muse Wonder Full vs Claude Opus 5.5
- Muse Wonder Full vs GPT-6 Luna (Anthropic run)
- Muse Wonder Full vs Claude Haiku 5.5
- Muse Wonder Full vs GPT-6 Astra
- Muse Wonder Full vs GPT-6.1 Sol
- Muse Wonder Full vs Claude Fable 5 (September card)
- Muse Wonder Full vs GPT-6.1 Terra
- Muse Wonder Full vs Claude Fable 5.1
- Muse Wonder Full vs GPT-6 Luna
- Muse Wonder Full vs GPT-6 Sol
- Muse Wonder Full vs GPT-5.6 Sol
- Muse Wonder Full vs Muse Wonder
- Muse Wonder Full vs Claude Opus 5
- Muse Wonder Full vs Muse Spark 1.1
- Muse Wonder Full vs Claude Sonnet 5
- Muse Wonder Full vs GPT-5.6 Terra
- Muse Wonder Full vs Claude Opus 4.8 (Opus 4.8 grader)
- Muse Wonder Full vs Grok 4.7
- Muse Wonder Full vs Claude Opus 4.8
- Muse Wonder Full vs GPT-5.6 Luna
- Muse Wonder Full vs Gemini 4 Argon
- Muse Wonder Full vs Muse Spark
- Muse Wonder Full vs GPT-5.6 Sol (August)
- Muse Wonder Full vs Kimi K3
- Muse Wonder Full vs GLM 5.3
- Muse Wonder Full vs Claude Opus 4.7
- Muse Wonder Full vs GPT-5.5
- Muse Wonder Full vs Gemini 3.8 Flash
- Muse Wonder Full vs DeepSeek V4.1 Flash
- Muse Wonder Full vs Grok 4.6
- Muse Wonder Full vs GPT-5.4
- Muse Wonder Full vs GPT-5
- Muse Wonder Full vs GPT-5.2
- Muse Wonder Full vs Claude Sonnet 4.6
- Muse Wonder Full vs GPT-5.6 Luna (August)
- Muse Wonder Full vs GPT-5.1
- Muse Wonder Full vs GPT-5.5 Instant
- Muse Wonder Full vs MAI-Thinking-1
- Muse Wonder Full vs Claude Haiku 4.5
Where the scores come from and how they are read is on the methodology page. The full ranking is on the leaderboard.