Muse Spark on HealthBench Professional
Muse Spark scores 0.541 on HealthBench Professional, rank 26 of 43 models on the board. Meta's April 2026 frontier model, the first of the Muse Spark line, with the lowest list price on this 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 Spark, by length-adjusted score. Differences are against Muse Spark.
| Rank | Model | Length-adjusted | Before the adjustment | Difference |
|---|---|---|---|---|
| 23 | 0.558 | – | +0.017 | |
| 24 | 0.557 | 0.598 | +0.016 | |
| 25 | 0.551 | 0.642 | +0.010 | |
| 26 | 0.541 | – | – | |
| 27 | 0.540 | 0.566 | -0.001 | |
| 28 | 0.532 | 0.569 | -0.009 | |
| 29 | 0.528 | 0.579 | -0.013 |
Result and API facts
| Rank | 26 of 43 |
|---|---|
| Length-adjusted score | 0.541 |
| Score before the length adjustment | not printed in the source |
| Lab | Meta |
| Context window | 1.0M tokens |
| API price per 1M tokens | no published list pricing |
| License | proprietary |
| Source | Muse Spark 1.1 Evaluation Report (model card) |
| Released | 2026-04-08 |
Source of this score
Read from Muse Spark 1.1 Evaluation Report (model card, Meta, 2026-07-09). Vendor-reported. Confidence: verified. Configuration: length-normalized, GPT-5.4 low-reasoning grader; Muse Spark (1.0) column in the Muse Spark 1.1 Evaluation Report Figure 44.
Health | HealthBench Professional | 59.3 | 54.1 | 41.6 | 55.8 | 51.8 (Figure 44 image table row; columns Muse Spark 1.1, Muse Spark, Gemini 3.1 Pro (high), Opus 4.8 (max), GPT 5.5 (xhigh))
Position in the field
The gap to the leader, GPT-6 Astra (Anthropic run) at 0.703, is 0.162. Directly above sits Gemini 4 Argon at 0.551. Directly below sits GPT-5.6 Sol (August) at 0.540. 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 Spark score on HealthBench Professional?
Muse Spark scores 0.541 on HealthBench Professional, which places it at rank 26 of 43 models on the board as of November 2, 2026. The number was read from Muse Spark 1.1 Evaluation Report, listed on the sources page.
How much does Muse Spark cost to run?
Meta has not published API pricing for Muse Spark.
Head to head
Score-difference matrixPairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.
- Muse Spark vs GPT-6 Astra (Anthropic run)
- Muse Spark vs Claude Sonnet 5.5
- Muse Spark vs Claude Fable 5
- Muse Spark vs Claude Opus 5.5
- Muse Spark vs GPT-6 Luna (Anthropic run)
- Muse Spark vs Claude Haiku 5.5
- Muse Spark vs GPT-6 Astra
- Muse Spark vs GPT-6.1 Sol
- Muse Spark vs Claude Fable 5 (September card)
- Muse Spark vs GPT-6.1 Terra
- Muse Spark vs Muse Wonder Full
- Muse Spark vs Claude Fable 5.1
- Muse Spark vs GPT-6 Luna
- Muse Spark vs GPT-6 Sol
- Muse Spark vs GPT-5.6 Sol
- Muse Spark vs Muse Wonder
- Muse Spark vs Claude Opus 5
- Muse Spark vs Muse Spark 1.1
- Muse Spark vs Claude Sonnet 5
- Muse Spark vs GPT-5.6 Terra
- Muse Spark vs Claude Opus 4.8 (Opus 4.8 grader)
- Muse Spark vs Grok 4.7
- Muse Spark vs Claude Opus 4.8
- Muse Spark vs GPT-5.6 Luna
- Muse Spark vs Gemini 4 Argon
- Muse Spark vs GPT-5.6 Sol (August)
- Muse Spark vs Kimi K3
- Muse Spark vs GLM 5.3
- Muse Spark vs Claude Opus 4.7
- Muse Spark vs GPT-5.5
- Muse Spark vs Gemini 3.8 Flash
- Muse Spark vs DeepSeek V4.1 Flash
- Muse Spark vs Grok 4.6
- Muse Spark vs GPT-5.4
- Muse Spark vs GPT-5
- Muse Spark vs GPT-5.2
- Muse Spark vs Claude Sonnet 4.6
- Muse Spark vs GPT-5.6 Luna (August)
- Muse Spark vs GPT-5.1
- Muse Spark vs GPT-5.5 Instant
- Muse Spark vs MAI-Thinking-1
- Muse Spark 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.