BenchLeader

Muse Spark 1.1 vs Step 5 Preview

Full profiles: Muse Spark 1.1 (Meta) and Step 5 Preview (StepFun): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Muse Spark 1.1 is ahead of Step 5 Preview on quality (62.2 vs 56.0 on the BenchLeader Index), but Step 5 Preview is 1.4× cheaper at $1.43 vs $2.00 per 1M tokens blended. Muse Spark 1.1 leads in every category we measure both in. Muse Spark 1.1 streams faster.

Key facts (as of 16 Nov 2026)

  • Muse Spark 1.1 scores 62.2 on the BenchLeader Index and Step 5 Preview scores 56.0 (BenchLeader, 16 Nov 2026).
  • Muse Spark 1.1 costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Step 5 Preview costs $1.43 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Spark 1.1 streams faster than Step 5 Preview (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 13 benchmarks both models have, Muse Spark 1.1 leads 9 (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 Spark 1.166 vs 50 category score; Arena Coding 1533 vs 1505High
Agents & tool useMuse Spark 1.151 vs 49 category score; Arena Agent -8 vs -3.7Medium
MathsMuse Spark 1.161 vs 60 category score; Arena Maths 1493 vs 1470Medium
ReasoningMuse Spark 1.168 vs 52 category score; Arena Hard Prompts 1511 vs 1477High
KnowledgeMuse Spark 1.169 vs 54 category scoreHigh
Images and other mediaMuse Spark 1.164 vs 59 category score; Arena Vision 1292 vs 1263Medium
Chat quality (human preference)Muse Spark 1.165 vs 63 on Arena votesMedium
Lowest costStep 5 Preview$1.43 vs $2.00 per 1M blended; agentic coding session $0.071 vs $0.092–
Fastest first answerMuse Spark 1.11.8 s (Muse Spark 1.1) vs 23.5 s (Step 5 Preview) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Muse Spark 1.1 leads on quality: 62.2 vs 56.0.
  • Muse Spark 1.1 is stronger in agents & tools, coding, human preference, knowledge, maths, multimodal, reasoning.
  • Step 5 Preview is 1.4× cheaper ($1.43 vs $2.00 per 1M blended).
  • Muse Spark 1.1 streams 1.6× faster (193 vs 124 tokens per second).

At a glance

SpecMuse Spark 1.1Step 5 Preview
DeveloperMetaStepFun
Released9 Jul 202618 Sep 2026
Context window (tokens)1,048,5761,000,000
Compared atMuse Spark 1.1Step 5 Preview
Open weightsNoYes
Price in / out / cached input per 1M$1.25 / $4.25 / $0.150$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 Spark 1.1Step 5 PreviewLeader
Reasoning67.851.7Muse Spark 1.1
Coding65.849.9Muse Spark 1.1
Agents & tools50.949.1Muse Spark 1.1
Maths61.360.1Muse Spark 1.1
Knowledge69.253.7Muse Spark 1.1
Instruction following70.4–not comparable
Human preference64.563.1Muse Spark 1.1
Multimodal63.659.3Muse Spark 1.1
Long context–69.0not comparable

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 & toolsMathsKnowledgeMultimodalHumanpreferenceMuse Spark 1.1, Reasoning: 67.8Muse Spark 1.1, Coding: 65.8Muse Spark 1.1, Agents & tools: 50.9Muse Spark 1.1, Maths: 61.3Muse Spark 1.1, Knowledge: 69.2Muse Spark 1.1, Multimodal: 63.6Muse Spark 1.1, Human preference: 64.5Step 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, Multimodal: 59.3Step 5 Preview, Human preference: 63.1

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

Model, click to add or removeIndex

Where sources disagree

Across the 13 benchmarks both have, Muse Spark 1.1 leads 9, Step 5 Preview leads 4. Every overall index that rates both puts Muse Spark 1.1 ahead.

Overall indexMuse Spark 1.1Step 5 PreviewLeader
BenchLeader Index62.256.0Muse Spark 1.1
Arena Text14911449Muse Spark 1.1

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 Spark 1.1Step 5 Preview
Blended price per 1M tokens$2.00$1.43
Input / output per 1M$1.25 / $4.25$1.00 / $2.70
Cached input per 1M$0.150$0.105
Price per task: chat reply$0.0018$0.0012
Price per task: summarize a 30-page report$0.018$0.014
Price per task: code edit$0.014$0.010
Price per task: agentic coding session$0.092$0.071
Price per task: structured extraction$0.0034$0.0025
Agentic coding session, input mostly cached$0.043$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 speed193 tok/s124 tok/s
Time to first answer1.8 s23.5 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 1.1 scores 62.2 and takes 2 s to its first answer token; Muse Spark 1.1 (xhigh) scores 59.5 in 13 s. 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

134 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 Spark 1.1Step 5 Preview
BenchLeader IndexBenchLeader62.256.0
Agents & tools scoreBenchLeader50.949.1
Coding scoreBenchLeader65.849.9
Human preference scoreBenchLeader64.563.1
Instruction following scoreBenchLeader70.4–
Knowledge scoreBenchLeader69.253.7
Maths scoreBenchLeader61.360.1
Multimodal scoreBenchLeader63.659.3
Reasoning scoreBenchLeader67.851.7
Long context scoreBenchLeader–69.0
Blended price $/MBenchLeader$2.00$1.43
Output speedBenchLeader193 tok/s124 tok/s
Time to first answerBenchLeader1.8 s23.5 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
Arena Hard PromptsArena (LMArena)15111477
LiveBench 2.0 ReasoningLiveBench–83.8%†
LiveBench 1.0 ReasoningLiveBench87.7%†–
GPQA Diamond (AA)Artificial Analysis89.8%†–
Humanity's Last Exam (AA)Artificial Analysis46.2%†46.5%
HLE-Diamond (AA)Artificial Analysis–24.3%
GPQA Diamond (Vals)Vals AI91.2%†–
CritPtArtificial Analysis15.1%†20.9%
CritPt v2 hard subset (AA)Artificial Analysis–32.5%
MysteryMechanismVals AI–18.5%
Arena ExpertArena (LMArena)15041489
Chess PuzzlesEpoch AI Benchmarking Hub34.0%†–
LMCAEpoch AI Benchmarking Hub49.9%†–
DTBenchEpoch AI Benchmarking Hub94.4%†–
Coding
SciCodeSciCode58.8%58.9%
Arena CodingArena (LMArena)15331505
Arena WebDevArena (LMArena)15421573†
LiveBench 2.0 CodingLiveBench–67.6%†
LiveBench 1.0 CodingLiveBench77.2%†–
LiveCodeBenchVals AI85.9%†–
IOIVals AI–38.1%
SWE-bench (Vals)Vals AI82.0%†–
SWE-Bench ProScale AI SEAL61.5%–
Code MigrationVals AI31.1%†39.0%
Code Migration v1.1Vals AI–47.0%
Show all 134 benchmarks
MetricPublisherMuse Spark 1.1Step 5 Preview
Coding
ProgramBenchVals AI0.0%†–
SWE-bench MultimodalVals AI–40.8%
Vibe Code Bench v1.1Vals AI72.2%†70.4%
SWE-Bench Pro (private)Scale AI SEAL51.5%–
SWE Atlas v1.0: Codebase QnAScale AI SEAL42.2%†–
SWE Atlas v1.0: Test WritingScale AI SEAL41.5%†–
Surface Evolver BenchEpoch AI Benchmarking Hub52.5%†–
DeepSWE v1.1Epoch AI Benchmarking Hub53.3%–
Terminal-Bench 4.0 (AA)Artificial Analysis6.1%†33.3%
Terminal-Bench 2.1 (AA)Artificial Analysis77.9%†–
Design Arena WebsiteDesign Arena1263–
FrontierCode 1.1 (AA)Artificial Analysis–38.4%
FrontierCode 2.0 (AA)Artificial Analysis–12.0%
Agents & tools
APEX-AgentsMercor31.8%–
Arena AgentArena (LMArena)-8-3.7
LiveBench Long AgenticLiveBench–19.4%†
LiveBench BrowserLiveBench–24.8%†
LiveBench Agentic CodingLiveBench58.5%†–
Terminal-Bench 2.1 (Vals)Vals AI69.3%†–
MCP AtlasScale AI SEAL88.1%–
τ³-bench Bankingτ²-bench40.5%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis–54.3%
GDPval-AA v2.1Artificial Analysis1216†1591
τ³-Banking (AA)Artificial Analysis31.8%†–
ITBench SRE (AA)Artificial Analysis–55.6%
Analyst Agent (AA)Artificial Analysis–35.0%
APEX-Agents (AA)Artificial Analysis–38.0%
Finance Agent v2Vals AI57.2%†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 AI20.0%†9.2%
Legal Research BenchVals AI38.0%†40.4%
SkillsBenchVals AI59.2%†–
SREBenchVals AI–0.4%
Tax Agent BenchVals AI–27.3%
Terminal-Bench 4.0 (Vals)Vals AI–31.8%
Terminal-Bench ScienceVals AI–2.9%
Time Horizon Index: KSPVals AI1.7%†–
Arena Agent Task CompletionArena (LMArena)-6.5-1.5
GBAEvalEpoch AI Benchmarking Hub7.9%–
Vending-Bench 2Andon Labs6520.5–
AutomationBenchArtificial Analysis38.9%†51.0%
GDP.pdf (AA)Artificial Analysis14.4%†14.8%
EnterpriseOps-GymArtificial Analysis–47.2%
AA-Briefcase v1.1Artificial Analysis851†1424
Design Arena AgenticDesign Arena1172–
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
ProofBenchVals AI39.0%42.0%
LiveBench MathematicsLiveBench87.1%†–
Arena MathsArena (LMArena)14931470
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub57.8%–
LiveBench 2.0 Data AnalysisLiveBench–63.5%†
LiveBench ResearchLiveBench–75.5%†
LiveBench 1.0 Data AnalysisLiveBench72.5%†–
AA-Omniscience v1.1Artificial Analysis–16.4
MMLU-ProVals AI88.7%†–
LegalBenchVals AI85.0%†–
CorpFinVals AI71.3%†–
TaxEvalVals AI79.7%†–
PRBench FinanceScale AI SEAL55.0%–
PRBench LegalScale AI SEAL57.0%–
MultiNRCScale AI SEAL65.6%–
BioMysteryBenchVals AI–67.4%
Excel Modeling BenchmarkVals AI56.4%†57.1%
Excel Modeling Benchmark v1.1Vals AI–69.5%
MedScribeVals AI88.9%†–
Public Benefits Bench v1.1Vals AI61.3%†58.1%
GDP.pdfEpoch AI Benchmarking Hub15.0%–
AA-Omniscience v1.1: accuracyArtificial Analysis–36.4%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–68.7%
Instruction following
LiveBench LanguageLiveBench74.3%†–
LiveBench Instruction FollowingLiveBench69.6%†–
MultiChallengeScale AI SEAL75.3%–
Arena Instruction FollowingArena (LMArena)14731450
Human preference
Arena TextArena (LMArena)14911449
EQ-Bench 4EQ-Bench1244–
EQ-Bench Creative Writing v3EQ-Bench1928–
Arena Creative WritingArena (LMArena)14431413
Arena Multi-turnArena (LMArena)14971445
Arena Longer QueriesArena (LMArena)14811461
Multimodal
Arena VisionArena (LMArena)12921263
LiveBench DesignLiveBench–70.8%†
MMMU-ProArtificial Analysis–76.4%
MMMU-Pro (Vals)Vals AI86.6%†–
MortgageTaxVals AI66.1%†–
VTBScale AI SEAL44.8%–
Code2Video-AAArtificial Analysis–821
AA-3DArtificial Analysis–859
Long context
AA-LCR v1.1Artificial Analysis77.7%†88.3%
Arena DocumentArena (LMArena)1480–
MLCRArtificial Analysis7.2%†18.3%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub154.9–
LiveBench 2.0LiveBench–54.9%†
LiveBench 1.0LiveBench75.3%†–
AA Intelligence Index v5.0.1Artificial Analysis–28.5
AA Intelligence Index v4.3.2Artificial Analysis33.7†43.7
AA Progress Index v1Artificial Analysis302.7†318.2
Vals IndexVals AI–54.8
Vals Finance IndexVals AI–55.4%
Vals Science IndexVals AI–29.6%
Vals Multimodal IndexVals AI66.7%†–
Vals Legal IndexVals AI–70.2%
AA Cyber IndexArtificial Analysis–47.7
Safety & honesty
FORTRESSScale AI SEAL12.4%–
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.
  • Step 5 Preview: 1 score revision.
  • Step 5 Preview: 7 score revisions.
  • Muse Spark 1.1: 1 score revision.
  • Step 5 Preview: 2 new results (Vals Index, Harvey's Legal Agent Benchmark v1.1).
  • Muse Spark 1.1: 2 score revisions.
  • Step 5 Preview: 1 score revision.
  • Step 5 Preview: BenchLeader Index 58.0 → 54.7.
  • Step 5 Preview: 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 2 score revisions; Step 5 Preview cost per task moved from $1.03/M to $2.35/M (128% up).

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

Muse Spark 1.1 vs Step 5 Preview: questions

Is Muse Spark 1.1 better than Step 5 Preview?
Muse Spark 1.1 leads on quality: 62.2 vs 56.0. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.1 is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Muse Spark 1.1 vs Step 5 Preview: which is cheaper, and will that change?
Step 5 Preview is cheaper today: $1.43 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Muse Spark 1.1 or Step 5 Preview better for coding?
Muse Spark 1.1 scores higher in coding (66 vs 50 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 58.8% for Muse Spark 1.1 against 58.9% for Step 5 Preview.
Which is faster, Muse Spark 1.1 or Step 5 Preview?
Muse Spark 1.1 streams faster (193 vs 124 output tokens per second, Artificial Analysis 7-day median).
Is Muse Spark 1.1 or Step 5 Preview better for agents and tool use?
Muse Spark 1.1 scores higher in agentic tasks (51 vs 49 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is -8 for Muse Spark 1.1 against -3.7 for Step 5 Preview.
More questions (4)
Which is better for long documents?
Both take about 1M tokens: Muse Spark 1.1 1,048,576, Step 5 Preview 1,000,000.
Which has lower latency?
Muse Spark 1.1 answers first: 1.8 s against 23.5 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Muse Spark 1.1 vs Step 5 Preview?
Across the 13 benchmarks both have, Muse Spark 1.1 leads 9, Step 5 Preview leads 4. Every overall index that rates both puts Muse Spark 1.1 ahead.
When was Step 5 Preview released?
Step 5 Preview was released on 18 Sep 2026.