BenchLeader

GPT-5.1 vs Muse Spark

Full profiles: GPT-5.1 (OpenAI) and Muse Spark (Meta): every benchmark, price and rank.

Updated · Data from 10 sources

As of 16 Nov 2026, Muse Spark is ahead of GPT-5.1 on quality (64.2 vs 57.5 on the BenchLeader Index). Muse Spark leads in every category we measure both in.

Key facts (as of 16 Nov 2026)

  • GPT-5.1 scores 57.5 on the BenchLeader Index and Muse Spark scores 64.2 (BenchLeader, 16 Nov 2026).
  • GPT-5.1 costs $3.44 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 37 benchmarks both models have, Muse Spark leads 30 (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 56 category score; Arena Coding 1529 vs 1492High
Agents & tool useMuse Spark65 vs 41 category score; MCP Atlas 82.2% vs 50.1%High
MathsEither59 vs 59 category score; Arena Maths 1459 vs 1469Either
ReasoningMuse Spark67 vs 53 category score; GPQA Diamond 89.8% vs 87.6%High
KnowledgeMuse Spark63 vs 59 category score; MMLU-Pro 87.3% vs 86.4%Medium
Long documentsEither65 vs 64 category score; AA-LCR v1.1 80.0% vs 78.0%Either
Images and other mediaMuse Spark64 vs 58 category score; Arena Vision 1306 vs 1249Medium
Following instructionsMuse Spark77 vs 71 category score; IFBench 75.9% vs 72.9%Medium
Chat quality (human preference)Muse Spark68 vs 64 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 57.5.
  • GPT-5.1 (high) is stronger in long context.
  • Muse Spark is stronger in agents & tools, coding, human preference, instruction following, knowledge, maths, multimodal, reasoning.

At a glance

SpecGPT-5.1Muse Spark
DeveloperOpenAIMeta
Released12 Nov 20258 Apr 2026
Context window (tokens)400,000262,144
Compared atGPT-5.1 (high)Muse Spark
Open weightsNoNo
Price in / out / cached input per 1M$1.25 / $10.00 / $0.125–

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.

CategoryGPT-5.1 (high)Muse SparkLeader
Reasoning53.067.4Muse Spark
Coding55.765.1Muse Spark
Agents & tools41.265.0Muse Spark
Maths58.559.1level
Knowledge58.663.1Muse Spark
Instruction following71.476.9Muse Spark
Human preference64.068.1Muse Spark
Multimodal57.964.2Muse Spark
Long context64.663.6level

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 & toolsMathsKnowledgeInstructionfollowingLong contextMultimodalHumanpreferenceGPT-5.1, Reasoning: 53.0GPT-5.1, Coding: 55.7GPT-5.1, Agents & tools: 41.2GPT-5.1, Maths: 58.5GPT-5.1, Knowledge: 58.6GPT-5.1, Instruction following: 71.4GPT-5.1, Long context: 64.6GPT-5.1, Multimodal: 57.9GPT-5.1, Human preference: 64.0Muse Spark, Reasoning: 67.4Muse Spark, Coding: 65.1Muse Spark, Agents & tools: 65.0Muse Spark, Maths: 59.1Muse Spark, Knowledge: 63.1Muse Spark, Instruction following: 76.9Muse Spark, Long context: 63.6Muse Spark, Multimodal: 64.2Muse Spark, Human preference: 68.1

Model, click to add or removeIndex

Where sources disagree

Across the 37 benchmarks both have, GPT-5.1 leads 6, Muse Spark leads 30 and 1 is a tie. Every overall index that rates both puts Muse Spark ahead.

Overall indexGPT-5.1 (high)Muse SparkLeader
BenchLeader Index57.564.2Muse Spark
Arena Text14551489Muse 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.

MeasureGPT-5.1 (high)Muse Spark
Blended price per 1M tokens$3.44–
Input / output per 1M$1.25 / $10.00– / –
Cached input per 1M$0.125–
Price per task: chat reply$0.0035–
Price per task: summarize a 30-page report$0.021–
Price per task: code edit$0.022–
Price per task: agentic coding session$0.115–
Price per task: structured extraction$0.0045–
Agentic coding session, input mostly cached$0.064–
Output speed88 tok/s–
Time to first answer36.8 s–
Time to a complete answer, last measured 13 Nov 202680.1 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.1 (high) scores 57.5 and takes 37 s to its first answer token; GPT-5.1 scores 56.1 in 1 s, GPT-5.1 (thinking) scores 54.6 in 1 s. Muse Spark scores 64.2. 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

98 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.

MetricPublisherGPT-5.1 (high)Muse Spark
BenchLeader IndexBenchLeader57.564.2
Agents & tools scoreBenchLeader41.265.0
Coding scoreBenchLeader55.765.1
Human preference scoreBenchLeader64.068.1
Instruction following scoreBenchLeader71.476.9
Knowledge scoreBenchLeader58.663.1
Long context scoreBenchLeader64.663.6
Maths scoreBenchLeader58.559.1
Multimodal scoreBenchLeader57.964.2
Reasoning scoreBenchLeader53.067.4
Blended price $/MBenchLeader$3.44–
Output speedBenchLeader88 tok/s–
Time to first answerBenchLeader36.8 s–
Context windowBenchLeader400,000 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub87.6%89.8%
Humanity's Last ExamScale AI / CAIS23.7%†40.6%
SimpleBenchSimpleBench53.2%–
Arena Hard PromptsArena (LMArena)14761506
GPQA Diamond (AA)Artificial Analysis87.3%88.4%
Humanity's Last Exam (AA)Artificial Analysis28.5%40.7%
GPQA Diamond (Vals)Vals AI86.6%89.7%
GPQA Diamond (HELM)HELM Capabilities44.2%†–
ARC-AGI-1ARC Prize72.8%–
ARC-AGI-2ARC Prize17.6%–
CritPtArtificial Analysis4.9%11.3%
Arena ExpertArena (LMArena)14811491
Chess PuzzlesEpoch AI Benchmarking Hub42.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub16.0%†–
CL-benchEpoch AI Benchmarking Hub23.7%–
CL-bench LifeEpoch AI Benchmarking Hub17.3%–
LMCAEpoch AI Benchmarking Hub43.9%–
DTBenchEpoch AI Benchmarking Hub90.1%–
ForecastBenchForecastBench62.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub68.0%–
SciCodeSciCode43.3%†51.5%
WeirdMLWeirdML60.8%–
GSO-BenchGSO-Bench13.7%–
Arena CodingArena (LMArena)14921529
Arena WebDevArena (LMArena)1342†–
Show all 98 benchmarks
MetricPublisherGPT-5.1 (high)Muse Spark
Coding
LiveCodeBenchVals AI86.5%–
SWE-bench (Vals)Vals AI69.8%74.4%
SWE-Bench ProScale AI SEAL–55.0%
SWE-bench Verified (bash only)SWE-bench66.0%†–
SWE-bench Verified (any scaffold)SWE-bench66.0%†–
Vibe Code Bench v1.1Vals AI24.6%19.7%
SWE-Bench Pro (private)Scale AI SEAL–44.7%
SWE Atlas v1.0: Codebase QnAScale AI SEAL–24.2%
SWE Atlas v1.0: Test WritingScale AI SEAL–31.1%
ALE-BenchEpoch AI Benchmarking Hub1192.2–
Terminal-Bench 2.1 (AA)Artificial Analysis52.4%62.2%
Design Arena WebsiteDesign Arena11791253
LiveCodeBench (AA)Artificial Analysis86.8%–
Agents & tools
Terminal-BenchTerminal-Bench47.6%†–
Terminal-Bench HardArtificial Analysis45.5%45.5%
τ²-Bench Telecom (AA)Artificial Analysis81.9%91.5%
MCP AtlasScale AI SEAL50.1%82.2%
GDPval-AA v2.1Artificial Analysis8341006
τ³-Banking (AA)Artificial Analysis15.9%–
Poker AgentVals AI1038.6%†–
Terminal-Bench 2.0 (Vals)Vals AI44.9%59.5%
Arena SearchArena (LMArena)1184†–
DeepResearch BenchDeepResearch Bench42.8%†–
Vending-Bench 2Andon Labs1473.4†–
AA-Briefcase v1.1Artificial Analysis–646
Design Arena AgenticDesign Arena1009†–
Maths
OTIS Mock AIMEEpoch AI Benchmarking Hub88.6%88.9%
ProofBenchVals AI–17.0%
AIME (Vals)Vals AI93.3%96.9%
MGSMVals AI93.0%–
MathArena ApexMathArena1.0%–
Omni-MATH (HELM)HELM Capabilities46.4%†–
Arena MathsArena (LMArena)14591469
AIME 2025 (AA)Artificial Analysis94.0%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub48.0%–
MMLU-ProVals AI86.4%87.3%
LegalBenchVals AI85.7%84.2%
CorpFinVals AI63.8%65.1%
TaxEvalVals AI74.9%77.7%
MedQAVals AI96.4%–
PRBench FinanceScale AI SEAL48.0%†52.4%
PRBench LegalScale AI SEAL49.3%†52.3%
MultiNRCScale AI SEAL49.0%†59.0%
MMLU-Pro (HELM)HELM Capabilities57.9%†–
CaseLaw v2Vals AI73.4%63.1%
MedCodeVals AI52.7%51.3%
MedScribeVals AI88.1%85.9%
Global-MMLU-Lite (AA)Artificial Analysis90.6%–
Instruction following
IFBenchArtificial Analysis72.9%75.9%
MultiChallengeScale AI SEAL63.4%†75.5%
TutorBenchScale AI SEAL54.1%†68.5%
IFEval (HELM)HELM Capabilities93.5%†–
WildBench (HELM)HELM Capabilities86.3%†–
Arena Instruction FollowingArena (LMArena)14501465
Human preference
Arena TextArena (LMArena)14551489
Arena Creative WritingArena (LMArena)14281464
Arena Multi-turnArena (LMArena)14641493
Arena Longer QueriesArena (LMArena)14601476
Multimodal
Arena VisionArena (LMArena)12491306
MMMU-ProArtificial Analysis75.5%80.5%
VISTAScale AI SEAL43.8%†–
MMMU-Pro (Vals)Vals AI83.2%87.4%
MortgageTaxVals AI61.4%–
VPCTEpoch AI Benchmarking Hub58.7%–
Long context
AA-LCR v1.1Artificial Analysis80.0%78.0%
Arena DocumentArena (LMArena)1416†1467
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub150.9†153.1
AA Intelligence Index v4.3.2Artificial Analysis24.731.3
AA Progress Index v1Artificial Analysis275.7289.1
HELM Capabilities meanHELM Capabilities65.6%†–
Safety & honesty
FORTRESSScale AI SEAL25.7%†20.2%
MASKScale AI SEAL86.3%†–
Metadata
AA Openness IndexArtificial Analysis5.6–

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

What changed

  • GPT-5.1 (high): 2 new results (GDPval-AA v2.1, AIME 2025 (AA)).
  • Muse Spark: 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • Muse Spark: BenchLeader Index 64.6 → 64.1.
  • Muse Spark: 1 score revision.
  • GPT-5.1 (high): 1 new result (AA Progress Index v1).
  • Muse Spark: 1 new result (AA Progress Index v1).
  • GPT-5.1 (high): 1 new result (Global-MMLU-Lite (AA)).
  • GPT-5.1 (high): BenchLeader Index 58.4 → 57.9.

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

GPT-5.1 vs Muse Spark: questions

Is Muse Spark better than GPT-5.1?
Muse Spark leads on quality: 64.2 vs 57.5. 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 GPT-5.1 or Muse Spark better for coding?
Muse Spark scores higher in coding (65 vs 56 on the category index, where 50 is average). On Arena Coding, the top shared coding benchmark, it is 1492 for GPT-5.1 against 1529 for Muse Spark.
Is GPT-5.1 or Muse Spark better for agents and tool use?
Muse Spark scores higher in agentic tasks (65 vs 41 on the category index, where 50 is average). On MCP Atlas, the top shared agents & tools benchmark, it is 50.1% for GPT-5.1 against 82.2% for Muse Spark.
Which is better for long documents?
They are level on long-context benchmarks (65 vs 64). GPT-5.1 accepts more context: 400,000 against 262,144 tokens for Muse Spark.
Do independent benchmarks agree on GPT-5.1 vs Muse Spark?
Across the 37 benchmarks both have, GPT-5.1 leads 6, Muse Spark leads 30 and 1 is a tie. Every overall index that rates both puts Muse Spark ahead.
More questions (1)
When was Muse Spark released?
Muse Spark was released on 8 Apr 2026.