Skip to main content
BenchLM
Data

Data as of November 19, 2026 · How the score is built

Superseded.Meta has newer models in this line:Muse Spark 1.1

Muse Spark

SupersededProprietaryReasoning

Decision readingMuse Spark scores 53.6 out of 100 and ranks #82 of 214. This profile shows 25 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #52. No comparable first-party API price is published in the catalog.

Email me when its price, rank or availability changes.

Capability

53.6/100

field median 48#82 of 214 ranked models

Public

#82of 214

Verified #72 of 145

Price

Not listed

input median $0.60No comparable first-party hosted token rate

Speed

Not measured

field median 93 tok/sTime to first token not measured

Context

262Ktokens

field median 256,000Reported for this model; direct source link not stored

Decision snapshot

Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.

Strongest published evidence

Multimodal & Grounded ranks #52. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Validate before choosing

25 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 25 displayable benchmark rows

Is Muse Spark right for your job?

Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.

Muse Spark has a newer version, Muse Spark 1.3. Where Muse Spark 1.3 ranks by benchmark score:

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #84 of 177Percentile 53rdWeight 22%5 benchmarksVerified
52.9
CodingRank #88 of 177Percentile 51stWeight 20%5 benchmarksVerified
49.2
ReasoningRank Not rankedWeight 17%1 benchmarkVerified
54.9
MultimodalRank #52 of 115Percentile 55thWeight 12%7 benchmarksVerified
58.6
KnowledgeRank #65 of 156Percentile 59thWeight 12%7 benchmarksVerified
54.6
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%0 benchmarksNot measured
Not measured
MathWeight 5%0 benchmarksNot measured
Not measured

25 of 923 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic5/5 verified
  2. Coding5/5 verified
  3. Reasoning1/1 verified
  4. Multimodal7/7 verified
  5. Knowledge7/7 verified
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. MathNot measured
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

Muse Spark category percentile values

  • Agentic53rd percentile
  • Coding51st percentile
  • ReasoningNot eligible
  • Multimodal55th percentile
  • Knowledge59th percentile
  • MultilingualNot eligible
  • Instruction followingNot eligible
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#84/177
  2. Coding#88/177
  3. ReasoningNot ranked
  4. Multimodal#52/115
  5. Knowledge#65/156
  6. MultilingualNot ranked
  7. Inst. FollowingNot ranked
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Every result says who ran the test. For this model, Meta ran 19 of 25. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.

Overall rank
#82
of 214 on the leaderboard
Reported by Meta
19
Shown with that label
Run by a benchmark
3
The benchmark’s own run
Independent runs
3
An outside evaluator’s run
Coding5 rows
Coding benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
SWE-bench Pro52.4%

Best verified: Claude Fable 5.2 · 93%

Gap40.6 behindReported by MetaCounts4% ref. weight
LiveCodeBench Pro80.0%

Best verified: Sakana Fugu-Ultra · 90.8%

Gap10.8 behindReported by MetaCounts2% ref. weight
SWE-bench VerifiedSoftware Engineering Benchmark Verified77.4%

Best verified: Claude Opus 5 · 96%

Gap18.6 behindReported by MetaShown only
Vibe Code BenchVibe Code Bench v1.119.67%

Best verified: Gemini 4 Argon · 91.90%

Gap72.2 behindRun by Vibe Code BenchShown only
SWE-bench (Vals)SWE-bench, Vals AI run74.4%

Best verified: Claude Opus 5 · 97.0%

Gap22.6 behindIndependent run: Vals AIShown only
Agentic5 rows
Agentic benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Claw-Eval63.8%

Best verified: Ornith-1.5-397B · 81.4%

Gap17.6 behindRun by Claw-EvalCounts3% ref. weight
DeepSearchQA74.8%

Best verified: Atria Dawn Preview · 96.0%

Gap21.2 behindReported by MetaCounts1% ref. weight
τ²-bench resultsτ²-Bench Tool-Agent-User Evaluation91.5%

Best verified: GPT-5.4 · 98.9%

Gap7.4 behindReported by MetaCounts0% ref. weight
Terminal-Bench 2.059%

Best verified: GPT-5.5 · 82%

Gap23 behindReported by MetaShown only
CyberGym43.5%

Best verified: MiMo-V2.6-Flash · 95.1%

Gap51.6 behindRun by CyberGymShown only
Reasoning1 row
Reasoning benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
ARC-AGI-2Abstraction and Reasoning Corpus for AGI v242.5%

Best verified: GPT-6.2 Astra · 95.8%

Gap53.3 behindReported by MetaCounts2% ref. weight
Multimodal7 rows
Multimodal benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
ScreenSpot Pro84.1%

Best verified: GPT-6 Astra · 92.7%

Gap8.6 behindReported by MetaCounts5% ref. weight
MMMU-ProMassive Multi-discipline Multimodal Understanding Pro80.4%

Best verified: GPT-6.1 Terra · 85.5%

Gap5.1 behindReported by MetaCounts4% ref. weight
SimpleVQA71.3%

Best verified: Qwen3.7 Plus · 81.7%

Gap10.4 behindReported by MetaCounts3% ref. weight
CharXivCharXiv Reasoning86.4%

Best verified: Qwen3.8 Max · 93.5%

Gap7.1 behindReported by MetaCounts3% ref. weight
ERQA64.7%

Best verified: Glimpse · 83.8%

Gap19 behindReported by MetaCounts3% ref. weight
ZeroBench33.0%

Best verified: Muse Spark Open · 50.0%

Gap17 behindReported by MetaCounts2% ref. weight
MedXpertQA (MM)MedXpertQA Multimodal78.4%

Best verified: Qwen3.8 Max · 80.4%

Gap2 behindReported by MetaCounts1% ref. weight
Knowledge7 rows
Knowledge benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
HLEHumanity's Last Exam50.4%

Best verified: Claude Fable 5.2 · 74.2%

Gap23.8 behindReported by MetaCounts4% ref. weight
HLE w/o toolsHumanity's Last Exam without tools42.8%

Best verified: Claude Fable 5.2 · 73.2%

Gap30.4 behindReported by MetaCounts4% ref. weight
HealthBench Hard42.8%

Best verified: Muse Spark · 42.8%

GapHighest listedReported by MetaCounts3% ref. weight
GPQA-DGPQA Diamond89.5%

Best verified: GPT-6.2 Astra · 97.0%

Gap7.5 behindReported by MetaCounts3% ref. weight
MedXpertQA (Text)MedXpertQA Text52.6%

Best verified: Muse Spark · 52.6%

GapHighest listedReported by MetaCounts2% ref. weight
GPQA Diamond (Vals)GPQA Diamond, Vals AI run89.6%

Best verified: Gemini 3.1 Pro · 95.5%

Gap5.9 behindIndependent run: Vals AIShown only
MMLU-Pro (Vals)MMLU-Pro, Vals AI run87.3%

Best verified: Claude Fable 5.1 · 92.4%

Gap5.1 behindIndependent run: Vals AIShown only

Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Apr 8, 2026 · you are here

    Muse Spark

    Score 53.6 · Price not listed

  2. Jul 9, 2026

    Muse Spark 1.1

    Score 59.6 · Price not listed

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
Not published
Context window
262K
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not disclosed by the provider
Availability
Not sourced yet
Cloud regions
Not tracked yet
Lifecycle
Superseded
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing record
Self-host
Weights are not published
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

Muse Spark ranks #82 of 214 on the public leaderboard with a score of 53.6/100. Its source-verified position is #72 of 145.

Muse Spark is a proprietary model with a 262K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Muse Spark has cybersecurity benchmark results. The cybersecurity benchmark comparison shows them beside other models, one security job at a time, with the access route for restricted models.

Official exact-value snapshot from Meta's April 8, 2026 Muse Spark launch post and evaluation methodology. BenchLM maps directly comparable benchmark keys from Meta's first-party charts as display-only rows when needed, while screenshot-only eval groupings such as Figure Understanding and the Contemplating-mode table remain outside the weighted BenchLM schema.

Muse Spark sits in the Muse Spark family with Muse Spark 1.3, Muse Spark 1.1, Muse Spark 1.2. 25 of 923 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Multimodal & Grounded at #52, while its lowest eligible position is Coding at #88. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Last updated November 19, 2026. Runtime fields remain blank until a sourced snapshot exists.

Questions

How does Muse Spark perform overall in AI benchmarks?

Muse Spark ranks #82 out of 214 models on the public BenchAlign leaderboard, with a score of 53.6/100. Its evidence status is Supported, and this profile shows 25 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is Muse Spark good for knowledge and understanding?

Muse Spark ranks #65 out of 156 eligible models for knowledge and understanding, with a public category score of 54.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Muse Spark good for coding and programming?

Muse Spark ranks #88 out of 177 eligible models for coding and programming, with a public category score of 49.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Muse Spark good for reasoning and logic?

Muse Spark has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Muse Spark good for agentic tool use and computer tasks?

Muse Spark ranks #84 out of 177 eligible models for agentic tool use and computer tasks, with a public category score of 52.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Muse Spark good for multimodal and grounded tasks?

Muse Spark ranks #52 out of 115 eligible models for multimodal and grounded tasks, with a public category score of 58.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Which sibling models are related to Muse Spark?

Muse Spark belongs to the Muse Spark family. Related tracked variants include Muse Spark 1.3, Muse Spark 1.1, Muse Spark 1.2. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does Muse Spark have full benchmark coverage on BenchLM?

No. Muse Spark currently has 39 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Muse Spark?

Muse Spark has a reported context window of 262K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.

Compare Muse Spark with every tracked model1032 comparisons