BenchLeader

GPT-5.4 vs Muse Spark 1.3

Full profiles: GPT-5.4 (OpenAI) and Muse Spark 1.3 (Meta): every benchmark, price and rank.

Updated · Data from 13 sources

As of 12 Nov 2026, GPT-5.4 and Muse Spark 1.3 are neck and neck on quality (63.1 vs 61.6 on the BenchLeader Index, inside the ±4.5 margin), and Muse Spark 1.3 is 2.8× cheaper at $2.00 vs $5.63 per 1M tokens blended. Choose GPT-5.4 for reasoning (66 vs 60), coding (65 vs 61), and maths (65 vs 63); choose Muse Spark 1.3 for fast first answers (27.6 s vs 111.3 s) and multimodal (66 vs 61) and agents & tools (65 vs 63), where it also streams ~1.5× faster.

Key facts (as of 12 Nov 2026)

  • GPT-5.4 scores 63.1 on the BenchLeader Index and Muse Spark 1.3 scores 61.6 (BenchLeader, 12 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 12 Nov 2026).
  • Muse Spark 1.3 costs $2.00 per 1M tokens blended (list price, 12 Nov 2026).
  • Muse Spark 1.3 streams ~1.5× faster than GPT-5.4 (Artificial Analysis, 7-day median, 12 Nov 2026).
  • Of the 19 benchmarks both models have, Muse Spark 1.3 leads 15 (BenchLeader, 12 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
CodingGPT-5.465 vs 61 category score; SciCode 56.6% vs 58.8%Medium
Agents & tool useMuse Spark 1.365 vs 63 category score; τ³-Banking (AA) 50.5% vs 39.6%Medium
MathsGPT-5.465 vs 63 category score; FrontierMath Tiers 1–3 78.6% vs 74.0%Medium
ReasoningGPT-5.466 vs 60 category score; Chess Puzzles 48.0% vs 37.0%Medium
KnowledgeGPT-5.459 vs 58 category scoreMedium
Long documentsEither66 vs 66 category score; AA-LCR v1.1 82.0% vs 83.0%Either
Images and other mediaMuse Spark 1.366 vs 61 category scoreMedium
Chat quality (human preference)–Only Muse Spark 1.3 has an Arena rating (69 category score)Not comparable
Lowest costMuse Spark 1.3$2.00 vs $5.63 per 1M blended; agentic coding session $0.092 vs $0.210–
Fastest first answerMuse Spark 1.327.6 s (Muse Spark 1.3 (max)) vs 111.3 s (GPT-5.4 (xhigh)) 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

  • GPT-5.4 (xhigh) and Muse Spark 1.3 (max) are neck and neck on quality (63.1 vs 61.6, within the ±4.5 margin).
  • GPT-5.4 (xhigh) is stronger in coding, knowledge, maths, reasoning.
  • Muse Spark 1.3 (max) is stronger in agents & tools, long context, multimodal.
  • Muse Spark 1.3 (max) is 2.8× cheaper ($2.00 vs $5.63 per 1M blended).
  • Muse Spark 1.3 (max) streams 2.0× faster (135 vs 68 tokens per second).

At a glance

SpecGPT-5.4Muse Spark 1.3
DeveloperOpenAIMeta
Released5 Mar 20262 Sep 2026
Context window (tokens)1,050,0001,048,576
Compared atGPT-5.4 (xhigh)Muse Spark 1.3 (max)
Open weightsNoNo
Price in / out / cached input per 1M$2.50 / $15.00 / $0.250$1.25 / $4.25 / $0.150

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-5.4 (xhigh)Muse Spark 1.3 (max)Leader
Reasoning65.660.0GPT-5.4
Coding64.760.5GPT-5.4
Agents & tools63.065.0Muse Spark 1.3
Maths65.062.7GPT-5.4
Knowledge58.657.5GPT-5.4
Instruction following72.4–not comparable
Human preference–69.0not comparable
Multimodal60.965.9Muse Spark 1.3
Long context65.766.3level

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 contextMultimodalGPT-5.4, Reasoning: 65.6GPT-5.4, Coding: 64.7GPT-5.4, Agents & tools: 63.0GPT-5.4, Maths: 65.0GPT-5.4, Knowledge: 58.6GPT-5.4, Long context: 65.7GPT-5.4, Multimodal: 60.9Muse Spark 1.3, Reasoning: 60.0Muse Spark 1.3, Coding: 60.5Muse Spark 1.3, Agents & tools: 65.0Muse Spark 1.3, Maths: 62.7Muse Spark 1.3, Knowledge: 57.5Muse Spark 1.3, Long context: 66.3Muse Spark 1.3, Multimodal: 65.9

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

Model, click to add or removeIndex

Where sources disagree

Across the 19 benchmarks both have, GPT-5.4 leads 4, Muse Spark 1.3 leads 15. Every overall index that rates both puts Muse Spark 1.3 ahead.

Overall indexGPT-5.4 (xhigh)Muse Spark 1.3 (max)Leader
BenchLeader Index63.161.6neck and neck
Arena Text1475†1496Muse Spark 1.3

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-5.4 (xhigh)Muse Spark 1.3 (max)
Blended price per 1M tokens$5.63$2.00
Input / output per 1M$2.50 / $15.00$1.25 / $4.25
Cached input per 1M$0.250$0.150
Price per task: chat reply$0.0055$0.0018
Price per task: summarize a 30-page report$0.039$0.018
Price per task: code edit$0.037$0.014
Price per task: agentic coding session$0.210$0.092
Price per task: structured extraction$0.0080$0.0034
Agentic coding session, input mostly cached$0.109$0.043
Cost per benchmark task (AA Index)–$2.39
Output tokens per task (AA Index)–91k
Of which reasoning–55k
Time per task (AA Index)–11 min
Output speed68 tok/s135 tok/s
Time to first answer111.3 s27.6 s
Time to a complete answer188.0 s79.0 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 (xhigh) scores 63.1 and takes 111 s to its first answer token; GPT-5.4 (low) scores 58.8 in 3 s, GPT-5.4 (high) scores 58.7 in 2 s. Muse Spark 1.3 (max) scores 61.6 and takes 28 s to its first answer token; Muse Spark 1.3 scores 60.3 in 3 s, Muse Spark 1.3 (xhigh) scores 58.0 in 14 s. 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

165 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-5.4 (xhigh)Muse Spark 1.3 (max)
BenchLeader IndexBenchLeader63.161.6
Agents & tools scoreBenchLeader63.065.0
Coding scoreBenchLeader64.760.5
Instruction following scoreBenchLeader72.4–
Knowledge scoreBenchLeader58.657.5
Long context scoreBenchLeader65.766.3
Maths scoreBenchLeader65.062.7
Multimodal scoreBenchLeader60.965.9
Reasoning scoreBenchLeader65.660.0
Human preference scoreBenchLeader–69.0
Blended price $/MBenchLeader$5.63$2.00
Output speedBenchLeader68 tok/s135 tok/s
Time to first answerBenchLeader111.3 s27.6 s
Context windowBenchLeader1,050,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.3%–
Humanity's Last ExamScale AI / CAIS36.2%–
SimpleBenchSimpleBench–81.8%†
Arena Hard PromptsArena (LMArena)1487†1516
LiveBench 2.0 ReasoningLiveBench–89.7%†
LiveBench 1.0 ReasoningLiveBench88.1%89.7%†
GPQA Diamond (AA)Artificial Analysis92.0%93.5%
Humanity's Last Exam (AA)Artificial Analysis43.7%48.7%
HLE-Diamond (AA)Artificial Analysis–33.7%
GPQA Diamond (Vals)Vals AI91.7%–
Kagi LLM BenchmarkKagi LLM Benchmark63.8%†–
ARC-AGI-1ARC Prize93.7%–
ARC-AGI-2ARC Prize74.0%–
ARC-AGI-3ARC Prize0.2%†–
CritPtArtificial Analysis23.4%24.9%
CritPt v2 hard subset (AA)Artificial Analysis–48.0%
MysteryMechanismVals AI–36.0%
Chess PuzzlesEpoch AI Benchmarking Hub48.0%37.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub37.0%25.0%
CL-benchEpoch AI Benchmarking Hub27.9%–
CL-bench LifeEpoch AI Benchmarking Hub21.7%–
LMCAEpoch AI Benchmarking Hub52.0%53.9%†
DTBenchEpoch AI Benchmarking Hub94.4%96.5%†
ForecastBenchForecastBench63.0%†65.5%
BTF-3Epoch AI Benchmarking Hub–14.1%†
Show all 165 benchmarks
MetricPublisherGPT-5.4 (xhigh)Muse Spark 1.3 (max)
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.9%†–
SciCodeSciCode56.6%58.8%
WeirdMLWeirdML77.7%–
GSO-BenchGSO-Bench31.4%–
Arena CodingArena (LMArena)1511†1533
Arena WebDevArena (LMArena)1399†1655
LiveBench 2.0 CodingLiveBench–84.4%†
LiveBench 1.0 CodingLiveBench77.5%81.1%†
SciCode (AA)Artificial Analysis–58.8%
LiveCodeBenchVals AI84.1%–
IOIVals AI–56.6%
SWE-bench (Vals)Vals AI78.2%–
SWE-Bench ProScale AI SEAL59.1%–
Code MigrationVals AI35.0%47.4%
ProgramBenchVals AI0.0%2.5%
SWE-bench MultimodalVals AI–43.1%
Vibe Code Bench 1-100Vals AI–20.5%
Vibe Code Bench v1.1Vals AI67.4%85.9%
SWE-Bench Pro (private)Scale AI SEAL59.1%–
SWE Atlas: Codebase QnAScale AI SEAL40.8%–
SWE Atlas: RefactoringScale AI SEAL44.3%–
SWE Atlas: Test WritingScale AI SEAL44.4%–
MirrorCodeEpoch AI Benchmarking Hub23.3%54.4%
DeepSWE v1.1Epoch AI Benchmarking Hub51.8%–
CursorBenchCursor–41.6%
ALE-BenchEpoch AI Benchmarking Hub1607†1688.3†
AlgoTuneAlgoTune1.9†–
FrontierSWEEpoch AI Benchmarking Hub–25.8%
Terminal-Bench 4.0 (AA)Artificial Analysis–33.3%
Terminal-Bench 2.1 (AA)Artificial Analysis78.3%84.3%
Startrise FrontendStartrise–74.7%†
GameBench 2 OverallDuelLab GameBench 254.0†57.6†
GameBench 2 by reasoning settingDuelLab GameBench 262.268.6†
Design Arena WebsiteDesign Arena1193†1341
FrontierCode 1.1 (AA)Artificial Analysis–40.6%
FrontierCode 2.0 (AA)Artificial Analysis–23.1%
Agents & tools
Terminal-BenchTerminal-Bench81.8%†14.8%†
APEX-AgentsMercor52.4%†47.6%
Arena AgentArena (LMArena)–2.2
LiveBench Long AgenticLiveBench–47.9%†
LiveBench BrowserLiveBench–30.9%†
LiveBench Agentic CodingLiveBench53.8%64.1%†
Terminal-Bench HardArtificial Analysis57.6%–
τ²-Bench Telecom (AA)Artificial Analysis87.1%–
Terminal-Bench 2.1 (Vals)Vals AI–79.0%
MCP AtlasScale AI SEAL70.6%–
HiL-BenchScale AI SEAL9.7%†66.9%†
τ³-bench Bankingτ²-bench39.4%–
τ³-Banking (AA)Artificial Analysis39.6%50.5%
ITBench SRE (AA)Artificial Analysis–33.2%
Analyst Agent (AA)Artificial Analysis–37.5%
APEX-Agents (AA)Artificial Analysis33.3%–
CUA-benchVals AI–5.8%
CyberBenchVals AI–72.7%
Finance Agent v2Vals AI–60.0%
Harvey's Legal Agent Benchmark v1Vals AI0.0%23.8%
Legal Research BenchVals AI–55.3%
SkillsBenchVals AI51.7%–
SREBenchVals AI–3.8%
Tax Agent BenchVals AI–42.4%
Terminal-Bench 2.0 (Vals)Vals AI58.4%†–
Terminal-Bench 4.0 (Vals)Vals AI–24.8%
Terminal-Bench ScienceVals AI–10.0%
Arena SearchArena (LMArena)1196†–
DeepResearch BenchDeepResearch Bench35.1%†–
PostTrainBenchEpoch AI Benchmarking Hub17.8%†–
METR Time HorizonsMETR74.3%–
GBAEvalEpoch AI Benchmarking Hub45.1%†–
Vending-Bench 2Andon Labs6144.2†–
AutomationBenchArtificial Analysis–57.9%
GDP.pdf (AA)Artificial Analysis–26.6%
Harvey LAB-AA v1.1Harvey–8.9%
AA-Briefcase v1.1Artificial Analysis–1581
Design Arena AgenticDesign Arena1035†1276
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–10.9%
DeepSearchQAGoogle63.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub78.6%74.0%
FrontierMath Tier 4Epoch AI Benchmarking Hub49.0%46.3%
OTIS Mock AIMEEpoch AI Benchmarking Hub95.3%99.2%†
ProofBenchVals AI56.0%58.0%
LiveBench MathematicsLiveBench94.2%96.0%†
AIME (Vals)Vals AI96.7%–
AIME 2026MathArena99.2%–
HMMT February 2026MathArena97.7%–
USAMO 2026MathArena95.2%–
MathArena ApexMathArena54.2%–
Arena MathsArena (LMArena)1459†1506
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub45.1%–
LiveBench 2.0 Data AnalysisLiveBench–79.6%†
LiveBench ResearchLiveBench–82.5%†
LiveBench 1.0 Data AnalysisLiveBench79.3%79.6%†
AA-Omniscience v1.1Artificial Analysis–22.4
MMLU-ProVals AI87.5%–
LegalBenchVals AI86.0%–
CorpFinVals AI65.3%–
TaxEvalVals AI74.0%–
MedQAVals AI96.1%–
PRBench FinanceScale AI SEAL45.6%†59.5%†
PRBench LegalScale AI SEAL44.4%†61.6%†
MultiNRCScale AI SEAL58.3%†–
CaseLaw v2Vals AI63.8%–
Excel Modeling BenchmarkVals AI–67.4%
MedCodeVals AI41.3%–
MedScribeVals AI77.5%–
DrugDiscoveryBenchScale AI SEAL–62.2%†
EBR-benchEpoch AI Benchmarking Hub25.4%–
GDP.pdfEpoch AI Benchmarking Hub–27.6%†
AA-Omniscience v1.1: accuracyArtificial Analysis–38.0%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–74.8%
Instruction following
LiveBench LanguageLiveBench82.6%82.8%†
LiveBench Instruction FollowingLiveBench70.2%78.0%†
IFBenchArtificial Analysis74.0%–
Arena Instruction FollowingArena (LMArena)1460†1485
Human preference
Arena TextArena (LMArena)1465†1496
EQ-Bench 4EQ-Bench1258†–
Arena Creative WritingArena (LMArena)1433†1468
Arena Multi-turnArena (LMArena)1480†1493
Arena Longer QueriesArena (LMArena)1477†1498
Multimodal
Arena VisionArena (LMArena)1292†1310
LiveBench DesignLiveBench–74.8%†
MMMU-ProArtificial Analysis78.4%82.0%†
VISTAScale AI SEAL50.9%†–
MMMU-Pro (Vals)Vals AI87.5%–
MortgageTaxVals AI68.3%–
VTBScale AI SEAL29.2%†–
GeoBenchGeoBench–86.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub27.1%†–
Code2Video-AAArtificial Analysis–1019
AA-3DArtificial Analysis–1032
Long context
AA-LCR v1.1Artificial Analysis82.0%83.0%
Arena DocumentArena (LMArena)1471†1474
MLCRArtificial Analysis–13.9%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.8†158.2†
LiveBench 2.0LiveBench–68.6%†
LiveBench 1.0LiveBench78.0%81.6%†
AA Intelligence Index v5.0Artificial Analysis–36.6
AA Intelligence Index v4.3.2Artificial Analysis39.048.1
AA Progress Index v1Artificial Analysis311.6324.5
Vals RSI IndexVals AI15.5%19.6%
Safety & honesty
MASKScale AI SEAL89.7%†–

Data as of 2026-11-12. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-5.4 (xhigh): 1 new result (MirrorCode).
  • Muse Spark 1.3 (max): 1 new result (MirrorCode).
  • Muse Spark 1.3 (max): 1 new result (ForecastBench).
  • Muse Spark 1.3 (max): 1 score revision.
  • GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • GPT-5.4 (xhigh): 1 score revision.
  • Muse Spark 1.3 (max): 1 score revision.
  • Muse Spark 1.3 (max): 1 score revision.
  • Muse Spark 1.3 (max): BenchLeader Index 64.5 → 61.8.
  • GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).

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

GPT-5.4 vs Muse Spark 1.3: questions

Is GPT-5.4 better than Muse Spark 1.3?
GPT-5.4 (xhigh) and Muse Spark 1.3 (max) are neck and neck on quality (63.1 vs 61.6, within the ±4.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 12 Nov 2026, so check the category scores for your use.
GPT-5.4 vs Muse Spark 1.3: which is cheaper, and will that change?
Muse Spark 1.3 is cheaper today: $2.00 against $5.63 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.4 or Muse Spark 1.3 better for coding?
GPT-5.4 scores higher in coding (65 vs 61 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 56.6% for GPT-5.4 against 58.8% for Muse Spark 1.3.
Which is faster, GPT-5.4 or Muse Spark 1.3?
Muse Spark 1.3 streams ~1.5× faster (135 vs 68 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.4 or Muse Spark 1.3 better for agents and tool use?
Muse Spark 1.3 scores higher in agentic tasks (65 vs 63 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 39.6% for GPT-5.4 against 50.5% for Muse Spark 1.3.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (66 vs 66). Both take about 1.1M tokens: GPT-5.4 1,050,000, Muse Spark 1.3 1,048,576.
Which has lower latency?
Muse Spark 1.3 answers first: 27.6 s against 111.3 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 GPT-5.4 vs Muse Spark 1.3?
Across the 19 benchmarks both have, GPT-5.4 leads 4, Muse Spark 1.3 leads 15. Every overall index that rates both puts Muse Spark 1.3 ahead.
When was Muse Spark 1.3 released?
Muse Spark 1.3 was released on 2 Sep 2026.