Muse Spark
Released 8 Apr 20261.0M contextproprietaryAlso written as Muse Spark (2026-04-08), Muse Spark Thinking, Muse Spark 1.0
4 results on 4 of 14 boards, latest measured Sep 2026. Compare with other models
On the Clinical Benchmarks Index
The top 15 on the index, then Muse Spark at rank 24. Select a column to open that model.
Board by board
Muse Spark against the top 10 on each board it has a result on, on that board's own scale. Its own column is in colour.
HealthBench Professionalrank 26 of 43
- 0.703GPT-6 Astra (Anthropic run)
- 0.692Claude Sonnet 5.5
- 0.660Claude Fable 5
- 0.656Claude Opus 5.5
- 0.655GPT-6 Luna (Anthropic run)
- 0.648Claude Haiku 5.5
- 0.642GPT-6.1 Sol
- 0.627GPT-6.1 Terra
- 0.623Muse Wonder Full
- 0.541Muse Spark
37 modelsFull board
MedXpertQA (MM)rank 5 of 22
- 81.5GPT-5.6 Sol
- 81.3Gemini 3.1 Pro
- 80.4Qwen3.8 Max
- 80.0Claude Fable 5
- 78.4Muse Spark
- 77.1GPT-5.4
- 76.0Gemini-3 Pro
- 73.3GPT-5.2
- 71.7Claude Opus 4.8
- 71.0Qwen3.7 Plus
22 modelsFull board
MedScribe (Vals AI)rank 23 of 106
- 91.43Claude Opus 5.5
- 91.29Claude Fable 5.1
- 91.10Claude Sonnet 5.5
- 90.98Claude Opus 5
- 90.06Muse Spark 1.2
- 89.38Grok 4.7
- 88.94GLM 5.3 Flash
- 88.89Muse Spark 1.1
- 88.81GLM 5.3
- 85.90Muse Spark
95 modelsFull board
MedCode (Vals AI)rank 15 of 104
- 63.57Claude Opus 5
- 59.06Gemini 3.1 Pro Preview (02/26)
- 58.80Gemini 4 Argon
- 56.07Claude Fable 5
- 55.92Gemini 3 Flash (12/25)
- 55.83Gemini 3.5 Flash
- 54.86Claude Opus 4.7
- 53.51Claude Fable 5.1
- 53.39Gemini 3.7 Flash
- 51.31Muse Spark
95 modelsFull board
Every result, with its source
Each line sits on its own board's scale. Tall tick: the board leader.
Clinical reasoning and knowledge
- HealthBench Professionallength-normalized, GPT-5.4 low-reasoning grader; Muse Spark (1.0) column in the Muse Spark 1.1 Evaluation Report Figure 440.541Rank 26 of 43Leader GPT-6 Astra (Anthropic run) 0.703
- MedXpertQA (MM)Meta's Muse Spark launch table (Meta reports the better of vendor self-reports and its own reproduction)78.4Rank 5 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
Documentation and coding
- MedScribe (Vals AI)model ID meta/muse_spark; temperature=1; max_output_tokens=3000085.90Rank 23 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedCode (Vals AI)model ID meta/muse_spark; temperature=1; max_output_tokens=3000051.31Rank 15 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
Index working
Show the working: each board’s result, how hard the board runs and the field average
The Clinical Benchmarks Index is this site's own calculation from 12 boards. How it is computed
- HealthBench Professional0.54154.1+5.0 easy board49.10.743 weightlength-normalized, GPT-5.4 low-reasoning grader; Muse Spark (1.0) column in the Muse Spark 1.1 Evaluation Report Figure 44
- MedScribe (Vals AI)85.9085.9+33.8 easy board52.10.15 weight, near its ceilingNear its ceiling: leader 91.4, weight 0.15model ID meta/muse_spark; temperature=1; max_output_tokens=30000
- MedCode (Vals AI)51.3151.3−3.3 hard board54.60.319 weightmodel ID meta/muse_spark; temperature=1; max_output_tokens=30000
- MedXpertQA (MM)78.478.4+22.0 easy board56.40.162 weight, near its ceilingNear its ceiling: leader 81.5, weight 0.162Meta's Muse Spark launch table (Meta reports the better of vendor self-reports and its own reproduction)
- Adjusted average of 4 boards, by weight
- 51.6
- Field average, counts for 27.3% with 4 of 12 boards
- 44.2
- Index
- = 49.6
Score: the result on the board’s own 0 to 100 scale (dot; tick: the board’s leader). Board runs: how far the board’s scores sit above or below the same models’ scores on the other boards. Adjusted: the score minus that offset. The index is the adjusted average with the field average mixed in, more of it the fewer boards a model has. 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
26HealthBench Professional length-normalized 0.541
Printed as 54.1Vendor-reported, measured Jul 2026Configuration: length-normalized, GPT-5.4 low-reasoning grader; Muse Spark (1.0) column in the Muse Spark 1.1 Evaluation Report Figure 44Muse Spark 1.1 Evaluation Report model card, Meta, 9 Jul 2026. p. 101, Figure 44 (image), row HealthBench Professional, column Muse Spark; protocol p. 104 (printed 103)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))
Every result from this document23MedScribe (Vals AI) muse_spark 85.90
Printed as 85.90%Official leaderboard, measured Sep 2026Configuration: model ID meta/muse_spark; temperature=1; max_output_tokens=30000Vals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 22 of 105 (Muse Spark), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["meta/muse_spark"].22 | Muse Spark | 85.90%±1.85 | N/A | 3m11s
Every result from this document15MedCode (Vals AI) muse_spark 51.31
Printed as 51.31%Official leaderboard, measured Sep 2026Configuration: model ID meta/muse_spark; temperature=1; max_output_tokens=30000Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 14 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["meta/muse_spark"].14 | Muse Spark | 51.31%±2.24 | N/A | 2m03s
Every result from this document5MedXpertQA (MM) Meta's Muse Spark launch… 78.4
Printed as 78.4%Vendor-reported, measured Apr 2026Configuration: Meta's Muse Spark launch table (Meta reports the better of vendor self-reports and its own reproduction)Introducing Muse Spark: Scaling Towards Personal Superintelligence launch post, Meta, 8 Apr 2026. Launch-post benchmark table image, HEALTH section, row MedXpertQA (MM), column Muse Spark Thinking; the same table is page 5 of the Eval Methodology PDF; protocol p. 2: 'MedXpertQA Text/Multimodal: ... The multimodal variant contains 2,000 multimodal medical questions with clinical images (X-rays, histology, dermatology, etc.) and 5 answer choices (A-E). For grading, we use gpt-oss-120b to parse the predicted answer letter from free-form text.'MedXpertQA (MM) | Medical Multiple Choice | 78.4 | 64.8 | 81.3 | 77.1 | 65.8 (image table row; columns Muse Spark Thinking, Opus 4.6 Max, Gemini 3.1 Pro High, GPT 5.4 Xhigh, Grok 4.2 Reasoning)
Every result from this document- Also printed in Muse Spark Eval Methodology: 78.4, p. 5, benchmark table image, HEALTH section, row MedXpertQA (MM), column Muse Spark Thinking
- Mirrored by MedXpertQA (MM) Leaderboard & Scores - September 2026 | BenchLM.ai: 78.4%, BENCHMARK SCORE TABLE (8 MODELS), rank 3; the page says 'We mirror the published score view for MedXpertQA (MM)' and 'Updated September 4, 2026', citing Meta's Muse Spark Eval Methodology
Other Meta models: Llama 4 Maverick, Llama 4 Scout, Muse Spark 1.1, Muse Spark 1.2, Muse Spark 1.3, Muse Spark Open, Muse Wonder, Muse Wonder Full