BenchLeader

Muse Spark vs Step 5 Preview

Full profiles: Muse Spark (Meta) and Step 5 Preview (StepFun): every benchmark, price and rank.

Updated · Data from 8 sources

As of 16 Nov 2026, Muse Spark is ahead of Step 5 Preview on quality (64.2 vs 56.0 on the BenchLeader Index). Choose Muse Spark for agents & tools (65 vs 49), reasoning (67 vs 52), and coding (65 vs 50); choose Step 5 Preview for long context (69 vs 64) and maths (60 vs 59).

Key facts (as of 16 Nov 2026)

  • Muse Spark scores 64.2 on the BenchLeader Index and Step 5 Preview scores 56.0 (BenchLeader, 16 Nov 2026).
  • Step 5 Preview costs $1.43 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 19 benchmarks both models have, Step 5 Preview leads 10 (BenchLeader, 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingMuse Spark65 vs 50 category score; Arena Coding 1529 vs 1505High
Agents & tool useMuse Spark65 vs 49 category score; GDPval-AA v2.1 1006 vs 1591High
MathsStep 5 Preview60 vs 59 category score; Arena Maths 1470 vs 1469Medium
ReasoningMuse Spark67 vs 52 category score; Arena Hard Prompts 1506 vs 1477High
KnowledgeMuse Spark63 vs 54 category scoreHigh
Long documentsStep 5 Preview69 vs 64 category score; AA-LCR v1.1 88.3% vs 78.0%Medium
Images and other mediaMuse Spark64 vs 59 category score; Arena Vision 1306 vs 1263Medium
Chat quality (human preference)Muse Spark68 vs 63 on Arena votesMedium
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Muse Spark leads on quality: 64.2 vs 56.0.
  • Muse Spark is stronger in agents & tools, coding, human preference, knowledge, multimodal, reasoning.
  • Step 5 Preview is stronger in long context, maths.

At a glance

SpecMuse SparkStep 5 Preview
DeveloperMetaStepFun
Released8 Apr 202618 Sep 2026
Context window (tokens)262,1441,000,000
Compared atMuse SparkStep 5 Preview
Open weightsNoYes
Price in / out / cached input per 1M–$1.00 / $2.70 / $0.105

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryMuse SparkStep 5 PreviewLeader
Reasoning67.451.7Muse Spark
Coding65.149.9Muse Spark
Agents & tools65.049.1Muse Spark
Maths59.160.1Step 5 Preview
Knowledge63.153.7Muse Spark
Instruction following76.9–not comparable
Human preference68.163.1Muse Spark
Multimodal64.259.3Muse Spark
Long context63.669.0Step 5 Preview

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceMuse Spark, Reasoning: 67.4Muse Spark, Coding: 65.1Muse Spark, Agents & tools: 65.0Muse Spark, Maths: 59.1Muse Spark, Knowledge: 63.1Muse Spark, Long context: 63.6Muse Spark, Multimodal: 64.2Muse Spark, Human preference: 68.1Step 5 Preview, Reasoning: 51.7Step 5 Preview, Coding: 49.9Step 5 Preview, Agents & tools: 49.1Step 5 Preview, Maths: 60.1Step 5 Preview, Knowledge: 53.7Step 5 Preview, Long context: 69.0Step 5 Preview, Multimodal: 59.3Step 5 Preview, Human preference: 63.1

Not drawn, measured for fewer than two of these models: Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 19 benchmarks both have, Muse Spark leads 9, Step 5 Preview leads 10. Every overall index that rates both puts Muse Spark ahead.

Overall indexMuse SparkStep 5 PreviewLeader
BenchLeader Index64.256.0Muse Spark
Arena Text14891449Muse Spark

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureMuse SparkStep 5 Preview
Blended price per 1M tokens–$1.43
Input / output per 1M– / –$1.00 / $2.70
Cached input per 1M–$0.105
Price per task: chat reply–$0.0012
Price per task: summarize a 30-page report–$0.014
Price per task: code edit–$0.010
Price per task: agentic coding session–$0.071
Price per task: structured extraction–$0.0025
Agentic coding session, input mostly cached–$0.030
Cost per benchmark task (AA Index)–$2.35
Output tokens per task (AA Index)–113k
Of which reasoning–80k
Time per task (AA Index)–15 min
Output speed–124 tok/s
Time to first answer–23.5 s
Time to a complete answer, last measured 13 Nov 2026–54.4 s

Each model is compared at its best-ranked reasoning-effort setting. Muse Spark scores 64.2. Step 5 Preview scores 56.0 and takes 24 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

115 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherMuse SparkStep 5 Preview
BenchLeader IndexBenchLeader64.256.0
Agents & tools scoreBenchLeader65.049.1
Coding scoreBenchLeader65.149.9
Human preference scoreBenchLeader68.163.1
Instruction following scoreBenchLeader76.9–
Knowledge scoreBenchLeader63.153.7
Long context scoreBenchLeader63.669.0
Maths scoreBenchLeader59.160.1
Multimodal scoreBenchLeader64.259.3
Reasoning scoreBenchLeader67.451.7
Blended price $/MBenchLeader–$1.43
Output speedBenchLeader–124 tok/s
Time to first answerBenchLeader–23.5 s
Context windowBenchLeader262,144 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub89.8%–
Humanity's Last ExamScale AI / CAIS40.6%–
Arena Hard PromptsArena (LMArena)15061477
LiveBench 2.0 ReasoningLiveBench–83.8%†
GPQA Diamond (AA)Artificial Analysis88.4%–
Humanity's Last Exam (AA)Artificial Analysis40.7%46.5%
HLE-Diamond (AA)Artificial Analysis–24.3%
GPQA Diamond (Vals)Vals AI89.7%–
CritPtArtificial Analysis11.3%20.9%
CritPt v2 hard subset (AA)Artificial Analysis–32.5%
MysteryMechanismVals AI–18.5%
Arena ExpertArena (LMArena)14911489
Coding
SciCodeSciCode51.5%58.9%
Arena CodingArena (LMArena)15291505
Arena WebDevArena (LMArena)–1573†
LiveBench 2.0 CodingLiveBench–67.6%†
SciCode (AA)Artificial Analysis–58.9%
IOIVals AI–38.1%
SWE-bench (Vals)Vals AI74.4%–
SWE-Bench ProScale AI SEAL55.0%–
Code MigrationVals AI–39.0%
Code Migration v1.1Vals AI–47.0%
SWE-bench MultimodalVals AI–40.8%
Vibe Code Bench v1.1Vals AI19.7%70.4%
SWE-Bench Pro (private)Scale AI SEAL44.7%–
Show all 115 benchmarks
MetricPublisherMuse SparkStep 5 Preview
Coding
SWE Atlas v1.0: Codebase QnAScale AI SEAL24.2%–
SWE Atlas v1.0: Test WritingScale AI SEAL31.1%–
Terminal-Bench 4.0 (AA)Artificial Analysis–33.3%
Terminal-Bench 2.1 (AA)Artificial Analysis62.2%–
Design Arena WebsiteDesign Arena1253–
FrontierCode 1.1 (AA)Artificial Analysis–38.4%
FrontierCode 2.0 (AA)Artificial Analysis–12.0%
Agents & tools
Arena AgentArena (LMArena)–-3.7
LiveBench Long AgenticLiveBench–19.4%†
LiveBench BrowserLiveBench–24.8%†
Terminal-Bench HardArtificial Analysis45.5%–
τ²-Bench Telecom (AA)Artificial Analysis91.5%–
MCP AtlasScale AI SEAL82.2%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–54.3%
GDPval-AA v2.1Artificial Analysis10061591
ITBench SRE (AA)Artificial Analysis–55.6%
Analyst Agent (AA)Artificial Analysis–35.0%
APEX-Agents (AA)Artificial Analysis–38.0%
Finance Agent v2Vals AI–50.7%
Finance Agent v2.1Vals AI–58.9%
Harvey's Legal Agent Benchmark v1.1Vals AI–12.9%
Harvey's Legal Agent Benchmark v1Vals AI–9.2%
Legal Research BenchVals AI–40.4%
SREBenchVals AI–0.4%
Tax Agent BenchVals AI–27.3%
Terminal-Bench 2.0 (Vals)Vals AI59.5%–
Terminal-Bench 4.0 (Vals)Vals AI–31.8%
Terminal-Bench ScienceVals AI–2.9%
Arena Agent Task CompletionArena (LMArena)–-1.5
AutomationBenchArtificial Analysis–51.0%
GDP.pdf (AA)Artificial Analysis–14.8%
EnterpriseOps-GymArtificial Analysis–47.2%
AA-Briefcase v1.1Artificial Analysis6461424
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–2.4%
CWE-Bench (AA)Artificial Analysis–52.5%
DeepSec-Bench (AA)Artificial Analysis–15.8%
CyberGym end-to-end (AA)Artificial Analysis–74.8%
MKA (AA)Artificial Analysis–27.6%
Maths
OTIS Mock AIMEEpoch AI Benchmarking Hub88.9%–
ProofBenchVals AI17.0%42.0%
AIME (Vals)Vals AI96.9%–
Arena MathsArena (LMArena)14691470
Knowledge
LiveBench 2.0 Data AnalysisLiveBench–63.5%†
LiveBench ResearchLiveBench–75.5%†
AA-Omniscience v1.1Artificial Analysis–16.4
MMLU-ProVals AI87.3%–
LegalBenchVals AI84.2%–
CorpFinVals AI65.1%–
TaxEvalVals AI77.7%–
PRBench FinanceScale AI SEAL52.4%–
PRBench LegalScale AI SEAL52.3%–
MultiNRCScale AI SEAL59.0%–
BioMysteryBenchVals AI–67.4%
CaseLaw v2Vals AI63.1%–
Excel Modeling BenchmarkVals AI–57.1%
Excel Modeling Benchmark v1.1Vals AI–69.5%
MedCodeVals AI51.3%–
MedScribeVals AI85.9%–
Public Benefits Bench v1.1Vals AI–58.1%
AA-Omniscience v1.1: accuracyArtificial Analysis–36.4%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–68.7%
Instruction following
IFBenchArtificial Analysis75.9%–
MultiChallengeScale AI SEAL75.5%–
TutorBenchScale AI SEAL68.5%–
Arena Instruction FollowingArena (LMArena)14651450
Human preference
Arena TextArena (LMArena)14891449
Arena Creative WritingArena (LMArena)14641413
Arena Multi-turnArena (LMArena)14931445
Arena Longer QueriesArena (LMArena)14761461
Multimodal
Arena VisionArena (LMArena)13061263
LiveBench DesignLiveBench–70.8%†
MMMU-ProArtificial Analysis80.5%76.4%
MMMU-Pro (Vals)Vals AI87.4%–
Code2Video-AAArtificial Analysis–821
AA-3DArtificial Analysis–859
Long context
AA-LCR v1.1Artificial Analysis78.0%88.3%
Arena DocumentArena (LMArena)1467–
MLCRArtificial Analysis–18.3%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub153.1–
LiveBench 2.0LiveBench–54.9%†
AA Intelligence Index v5.0.1Artificial Analysis–28.5
AA Intelligence Index v4.3.2Artificial Analysis31.343.7
AA Progress Index v1Artificial Analysis289.1318.2
Vals IndexVals AI–54.8
Vals Finance IndexVals AI–55.4%
Vals Science IndexVals AI–29.6%
Vals Legal IndexVals AI–70.2%
AA Cyber IndexArtificial Analysis–47.7
Safety & honesty
FORTRESSScale AI SEAL20.2%–
Metadata
AA Openness IndexArtificial Analysis–33.3

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Step 5 Preview: BenchLeader Index 54.2 → 56.0.
  • Step 5 Preview: BenchLeader Index 54.7 → 54.2.
  • Muse Spark: 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • Step 5 Preview: 1 score revision.
  • Step 5 Preview: 7 score revisions.
  • Muse Spark: BenchLeader Index 64.6 → 64.1.
  • Muse Spark: 1 score revision.
  • Step 5 Preview: 2 new results (Vals Index, Harvey's Legal Agent Benchmark v1.1).
  • Step 5 Preview: 1 score revision.
  • Step 5 Preview: BenchLeader Index 58.0 → 54.7.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Muse Spark vs Step 5 Preview: questions

Is Muse Spark better than Step 5 Preview?
Muse Spark leads on quality: 64.2 vs 56.0. The BenchLeader Index combines every independent quality benchmark; Muse Spark is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Is Muse Spark or Step 5 Preview better for coding?
Muse Spark scores higher in coding (65 vs 50 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 51.5% for Muse Spark against 58.9% for Step 5 Preview.
Is Muse Spark or Step 5 Preview better for agents and tool use?
Muse Spark scores higher in agentic tasks (65 vs 49 on the category index, where 50 is average).
Which is better for long documents?
Step 5 Preview scores higher on long-context benchmarks (69 vs 64). Step 5 Preview accepts more context: 1,000,000 against 262,144 tokens for Muse Spark.
Do independent benchmarks agree on Muse Spark vs Step 5 Preview?
Across the 19 benchmarks both have, Muse Spark leads 9, Step 5 Preview leads 10. Every overall index that rates both puts Muse Spark ahead.
More questions (1)
When was Step 5 Preview released?
Step 5 Preview was released on 18 Sep 2026.