Muse Spark released
Meta · Model release
Source confirmed
Data as of October 5, 2026 · How the score is built
Superseded.Meta has newer models in this line:Muse Spark 1.1
SupersededProprietaryReasoning
Released Apr 8, 2026262K context
Muse Spark
Decision readingMuse Spark scores 60 out of 100 and ranks #49 of 212. This profile shows 27 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #14. No comparable first-party API price is published in the catalog.
Released Apr 8, 2026 — see all recent releases
Muse Spark will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
60/100
field median 51#49 of 212 ranked models
Public
#49of 212
Verified #32 of 83
Price
Not listed
input median $0.95No comparable first-party hosted token rate
Speed
Not measured
field median 90 tok/sTime to first token not measured
Context
262Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Multimodal & Grounded ranks #14. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
27 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 27 displayable benchmark rows
Follow model changesCategory 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 | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #43 of 119Percentile 64thWeight 22%5 benchmarksVerified | 49.8 | 5 benchmarks | Verified | |||
| CodingRank #39 of 144Percentile 73rdWeight 20%5 benchmarksVerified | 51.1 | 5 benchmarks | Verified | |||
| ReasoningRank Not rankedWeight 17%1 benchmarkVerified | 53.4 | 1 benchmark | Verified | |||
| MultimodalRank #14 of 49Percentile 73rdWeight 12%7 benchmarksVerified | 78.5 | 7 benchmarks | Verified | |||
| KnowledgeRank #40 of 171Percentile 77thWeight 12%7 benchmarksVerified | 60.3 | 7 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathRank Not rankedWeight 5%2 benchmarksVerified | 55.1 | 2 benchmarks | Verified |
27 of 649 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow 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.
- Agentic5/5 verified
- Coding5/5 verified
- Reasoning1/1 verified
- Multimodal7/7 verified
- Knowledge7/7 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math2/2 verified
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
- Agentic64th percentile
- Coding73rd percentile
- ReasoningNot eligible
- Multimodal73rd percentile
- Knowledge77th percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#43/119
- Coding#39/144
- ReasoningNot ranked
- Multimodal#14/49
- Knowledge#40/171
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Top decileTop quartileMid-fieldNot eligible
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score52.4% | Versus best verified row Best verified: Claude Opus 5.5 · 89.9% | Gap37.5 behind | Weight26% ref. weight | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score77.4% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap18.6 behind | WeightDisplay only | Provider exact |
| LiveCodeBench Pro | Score80.0% | Versus best verified row Best verified: Sakana Fugu-Ultra · 90.8% | Gap10.8 behind | WeightDisplay only | Provider exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score19.67% | Versus best verified row Best verified: Gemini 4 Argon · 91.90% | Gap72.2 behind | WeightDisplay only | Benchmark exact |
| SWE-bench (Vals)SWE-bench, Vals AI run | Score74.4% | Versus best verified row Best verified: Claude Opus 5 · 97.0% | Gap22.6 behind | WeightDisplay only | Verified |
Agentic5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score59% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap23 behind | Weight6% ref. weight | Provider exact |
| DeepSearchQA | Score74.8% | Versus best verified row Best verified: Atria Dawn Preview · 96.0% | Gap21.2 behind | Weight2% ref. weight | Provider exact |
| τ²-bench resultsτ²-Bench Tool-Agent-User Evaluation | Score91.5% | Versus best verified row Best verified: GPT-5.4 · 98.9% | Gap7.4 behind | WeightDisplay only | Provider exact |
| CyberGym | Score43.5% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap51.6 behind | WeightDisplay only | Benchmark exact |
| Claw-Eval | Score63.8% | Versus best verified row Best verified: Ornith-1.5-397B · 81.4% | Gap17.6 behind | WeightDisplay only | Benchmark exact |
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score42.5% | Versus best verified row Best verified: GPT-6 Astra · 95% | Gap52.5 behind | WeightWeighted 25% | Provider exact |
Multimodal7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score80.4% | Versus best verified row Best verified: Gemini 3.5 Flash · 83.6% | Gap3.2 behind | WeightWeighted 40% | Provider exact |
| CharXivCharXiv Reasoning | Score86.4% | Versus best verified row Best verified: Qwen3.8 Max · 93.5% | Gap7.1 behind | WeightWeighted 20% | Provider exact |
| ERQA | Score64.7% | Versus best verified row Best verified: Qwen3.8 Max · 77.8% | Gap13.1 behind | WeightDisplay only | Provider exact |
| SimpleVQA | Score71.3% | Versus best verified row Best verified: Qwen3.7 Plus · 81.7% | Gap10.4 behind | WeightDisplay only | Provider exact |
| ScreenSpot Pro | Score84.1% | Versus best verified row Best verified: GPT-6 Astra · 92.7% | Gap8.6 behind | WeightDisplay only | Provider exact |
| ZeroBench | Score33.0% | Versus best verified row Best verified: Muse Spark · 33.0% | GapBest verified | WeightDisplay only | Provider exact |
| MedXpertQA (MM)MedXpertQA Multimodal | Score78.4% | Versus best verified row Best verified: Qwen3.8 Max · 80.4% | Gap2 behind | WeightDisplay only | Provider exact |
Knowledge7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score50.4% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap14.6 behind | Weight44% ref. weight | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score42.8% | Versus best verified row Best verified: Claude Opus 5.5 · 64.4% | Gap21.6 behind | Weight7% ref. weight | Provider exact |
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | Score87.3% | Versus best verified row Best verified: Claude Fable 5.1 · 92.4% | Gap5.1 behind | Weight6% ref. weight | Verified |
| GPQA Diamond (Vals)GPQA Diamond, Vals AI run | Score89.6% | Versus best verified row Best verified: Gemini 3.1 Pro · 95.5% | Gap5.9 behind | Weight2% ref. weight | |
| GPQA-DGPQA Diamond | Score89.5% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap6.5 behind | WeightDisplay only | Provider exact |
| HealthBench Hard | Score42.8% | Versus best verified row Best verified: Muse Spark · 42.8% | GapBest verified | WeightDisplay only | Provider exact |
| MedXpertQA (Text)MedXpertQA Text | Score52.6% | Versus best verified row Best verified: Muse Spark · 52.6% | GapBest verified | WeightDisplay only | Provider exact |
Math2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score39.000% | Versus best verified row Best verified: GPT-5.6 Sol · 89.000% | Gap50 behind | WeightWeighted 30% | Benchmark exact |
| FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4 | Score14.600% | Versus best verified row Best verified: GPT-6 Astra · 97.600% | Gap83 behind | WeightWeighted 10% | Benchmark exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 27 rowsLineage
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.
Radar
Full release historyMuse Spark release history
Radar confirmed these at the source. Use Muse Spark in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
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 #49 of 212 on the public leaderboard with a score of 59.99/100. Its source-verified position is #32 of 83.
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.
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. 27 of 649 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #14, while its lowest eligible position is Agentic at #43. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Last updated October 5, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Muse Spark perform overall in AI benchmarks?
Muse Spark ranks #49 out of 212 models on the public BenchAlign leaderboard, with a score of 59.99/100. Its evidence status is Supported, and this profile shows 27 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 #40 out of 171 eligible models for knowledge and understanding, with a public category score of 60.3/100. 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 #39 out of 144 eligible models for coding and programming, with a public category score of 51.1/100. 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 mathematics?
Muse Spark has source-displayable benchmark coverage for mathematics, 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 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 #43 out of 119 eligible models for agentic tool use and computer tasks, with a public category score of 49.8/100. 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 #14 out of 49 eligible models for multimodal and grounded tasks, with a public category score of 78.5/100. 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 40 source-displayable rows across 649 tracked benchmark slots. 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.