BenchLeader

GPT-5.5 vs Muse Spark 1.2

Full profiles: GPT-5.5 (OpenAI) and Muse Spark 1.2 (Meta): every benchmark, price and rank.

Updated · Data from 13 sources

As of 10 Nov 2026, GPT-5.5 and Muse Spark 1.2 are neck and neck on quality (64.2 vs 61.7 on the BenchLeader Index, inside the ±6.3 margin), and Muse Spark 1.2 is 5.6× cheaper at $2.00 vs $11.25 per 1M tokens blended. Choose GPT-5.5 for agents & tools (62 vs 56), coding (61 vs 55), and long context (67 vs 64); choose Muse Spark 1.2 for fast first answers (7.9 s vs 28.6 s) and multimodal (65 vs 62) and knowledge (65 vs 64), where it also streams ~2× faster.

Key facts (as of 10 Nov 2026)

  • GPT-5.5 scores 64.2 on the BenchLeader Index and Muse Spark 1.2 scores 61.7 (BenchLeader, 10 Nov 2026).
  • GPT-5.5 costs $11.25 per 1M tokens blended (list price, 10 Nov 2026).
  • Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 10 Nov 2026).
  • Muse Spark 1.2 streams ~2× faster than GPT-5.5 (Artificial Analysis, 7-day median, 10 Nov 2026).
  • Of the 51 benchmarks both models have, GPT-5.5 leads 31 (BenchLeader, 10 Nov 2026).
  • On Arena WebDev, GPT-5.5 is rated 1512 and Muse Spark 1.2 1534 (LMArena, as published by 10 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-5.561 vs 55 category score; WeirdML 84.9% vs 60.3%Medium
Agents & tool useGPT-5.562 vs 56 category score; τ³-Banking (AA) 39.0% vs 34.9%Medium
MathsGPT-5.570 vs 67 category score; LiveBench Mathematics 95.9% vs 91.2%Medium
ReasoningEither68 vs 68 category score; LiveBench 1.0 Reasoning 89.7% vs 90.0%Either
KnowledgeMuse Spark 1.265 vs 64 category score; MMLU-Pro 88.3% vs 88.1%Medium
Long documentsGPT-5.567 vs 64 category score; AA-LCR v1.1 84.3% vs 79.0%Medium
Images and other mediaMuse Spark 1.265 vs 62 category score; MMMU-Pro (Vals) 86.1% vs 88.3%Medium
Chat quality (human preference)–Only Muse Spark 1.2 has an Arena rating (69 category score)Not comparable
Lowest costMuse Spark 1.2$2.00 vs $11.25 per 1M blended; agentic coding session $0.092 vs $0.420–
Fastest first answerMuse Spark 1.27.9 s (Muse Spark 1.2 (xhigh)) vs 28.6 s (GPT-5.5 (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-5.5 (xhigh) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.2 vs 61.7, within the ±6.3 margin).
  • GPT-5.5 (xhigh) is stronger in agents & tools, coding, instruction following, long context, maths.
  • Muse Spark 1.2 (xhigh) is stronger in knowledge, multimodal, human preference.
  • Muse Spark 1.2 (xhigh) is 5.6× cheaper ($2.00 vs $11.25 per 1M blended).
  • Muse Spark 1.2 (xhigh) streams 2.4× faster (192 vs 79 tokens per second).

At a glance

SpecGPT-5.5Muse Spark 1.2
DeveloperOpenAIMeta
Released23 Apr 20265 Aug 2026
Context window (tokens)1,050,0001,048,576
Compared atGPT-5.5 (xhigh)Muse Spark 1.2 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $30.00 / $0.500$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-5.5 (xhigh)Muse Spark 1.2 (xhigh)Leader
Reasoning68.368.3level
Coding60.955.0GPT-5.5
Agents & tools61.855.5GPT-5.5
Maths69.667.2GPT-5.5
Knowledge63.764.7Muse Spark 1.2
Instruction following74.0–not comparable
Human preference–68.7not comparable
Multimodal62.365.3Muse Spark 1.2
Long context67.064.2GPT-5.5

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-5.5, Reasoning: 68.3GPT-5.5, Coding: 60.9GPT-5.5, Agents & tools: 61.8GPT-5.5, Maths: 69.6GPT-5.5, Knowledge: 63.7GPT-5.5, Long context: 67.0GPT-5.5, Multimodal: 62.3Muse Spark 1.2, Reasoning: 68.3Muse Spark 1.2, Coding: 55.0Muse Spark 1.2, Agents & tools: 55.5Muse Spark 1.2, Maths: 67.2Muse Spark 1.2, Knowledge: 64.7Muse Spark 1.2, Long context: 64.2Muse Spark 1.2, Multimodal: 65.3

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

ModelIndex

Where sources disagree

Across the 51 benchmarks both have, GPT-5.5 leads 31, Muse Spark 1.2 leads 19 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.2 ahead.

Overall indexGPT-5.5 (xhigh)Muse Spark 1.2 (xhigh)Leader
BenchLeader Index64.261.7neck and neck
Arena Text1481†1494Muse Spark 1.2

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-5.5 (xhigh)Muse Spark 1.2 (xhigh)
Blended price per 1M tokens$11.25$2.00
Input / output per 1M$5.00 / $30.00$1.25 / $4.25
Cached input per 1M$0.500$0.150
Price per task: chat reply$0.011$0.0018
Price per task: summarize a 30-page report$0.078$0.018
Price per task: code edit$0.075$0.014
Price per task: agentic coding session$0.420$0.092
Price per task: structured extraction$0.016$0.0034
Agentic coding session, input mostly cached$0.217$0.043
Output speed79 tok/s192 tok/s
Time to first answer28.6 s7.9 s
Time to a complete answer75.1 s26.6 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.5 (xhigh) scores 64.2 and takes 29 s to its first answer token; GPT-5.5 (high) scores 63.7 in 18 s, GPT-5.5 scores 61.7 in 2 s. Muse Spark 1.2 (xhigh) scores 61.7 and takes 8 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.

MetricPublisherGPT-5.5 (xhigh)Muse Spark 1.2 (xhigh)
BenchLeader IndexBenchLeader64.261.7
Agents & tools scoreBenchLeader61.855.5
Coding scoreBenchLeader60.955.0
Instruction following scoreBenchLeader74.0–
Knowledge scoreBenchLeader63.764.7
Long context scoreBenchLeader67.064.2
Maths scoreBenchLeader69.667.2
Multimodal scoreBenchLeader62.365.3
Reasoning scoreBenchLeader68.368.3
Human preference scoreBenchLeader–68.7
Blended price $/MBenchLeader$11.25$2.00
Output speedBenchLeader79 tok/s192 tok/s
Time to first answerBenchLeader28.6 s7.9 s
Context windowBenchLeader1,050,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.7%†–
SimpleBenchSimpleBench69.0%†74.5%†
Arena Hard PromptsArena (LMArena)1499†1515
LiveBench 1.0 ReasoningLiveBench89.7%90.0%
GPQA Diamond (AA)Artificial Analysis93.5%90.4%
Humanity's Last Exam (AA)Artificial Analysis45.8%45.5%
GPQA Diamond (Vals)Vals AI93.2%–
Kagi LLM BenchmarkKagi LLM Benchmark88.8%†–
ARC-AGI-1ARC Prize95.0%–
ARC-AGI-2ARC Prize85.0%–
ARC-AGI-3ARC Prize0.4%†–
CritPtArtificial Analysis27.1%17.7%
Chess PuzzlesEpoch AI Benchmarking Hub63.0%27.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub56.0%–
CL-bench LifeEpoch AI Benchmarking Hub22.2%†–
LMCAEpoch AI Benchmarking Hub54.3%48.4%
DTBenchEpoch AI Benchmarking Hub96.0%94.7%
ForecastBenchForecastBench64.2%†–
BTF-3Epoch AI Benchmarking Hub14.3%†–
Coding
SciCodeSciCode55.8%57.4%
WeirdMLWeirdML84.9%60.3%
FrontierCodeCognition43.0%†–
GSO-BenchGSO-Bench40.2%–
Arena CodingArena (LMArena)1510†1543
Arena WebDevArena (LMArena)15121534
Show all 134 benchmarks
MetricPublisherGPT-5.5 (xhigh)Muse Spark 1.2 (xhigh)
Coding
LiveBench 1.0 CodingLiveBench82.2%77.5%
LiveCodeBenchVals AI85.3%–
IOIVals AI–21.8%
SWE-bench (Vals)Vals AI82.6%86.6%
Code MigrationVals AI45.2%29.9%
ProgramBenchVals AI0.5%0.5%
Vibe Code Bench v1.1Vals AI69.8%79.1%
SWE Atlas: Codebase QnAScale AI SEAL45.4%–
SWE Atlas: RefactoringScale AI SEAL44.8%–
SWE Atlas: Test WritingScale AI SEAL42.6%–
MirrorCodeEpoch AI Benchmarking Hub10.0%†–
Surface Evolver BenchEpoch AI Benchmarking Hub88.1%†–
DeepSWE v1.1Epoch AI Benchmarking Hub67.0%54.9%
ALE-BenchEpoch AI Benchmarking Hub1943.0–
FrontierSWEEpoch AI Benchmarking Hub–12.0%
Terminal-Bench 4.0 (AA)Artificial Analysis14.7%7.1%
Terminal-Bench 2.1 (AA)Artificial Analysis84.3%80.2%
Startrise FrontendStartrise–70.3%†
GameBench 2 OverallDuelLab GameBench 249.0†51.7†
GameBench 2 by reasoning settingDuelLab GameBench 259.757.4
Design Arena WebsiteDesign Arena1252†1310†
Agents & tools
Terminal-BenchTerminal-Bench84.7%†–
OSWorld-Verified 2.0OSWorld13.0%–
Remote Labor IndexScale AI / CAIS6.3%†–
APEX-AgentsMercor55.1%†45.4%†
Arena AgentArena (LMArena)–-8
LiveBench Agentic CodingLiveBench54.0%57.6%
Terminal-Bench HardArtificial Analysis60.6%–
τ²-Bench Telecom (AA)Artificial Analysis93.9%–
Terminal-Bench 2.1 (Vals)Vals AI76.4%†69.7%
MCP AtlasScale AI SEAL75.3%–
HiL-BenchScale AI SEAL39.7%†–
τ³-bench Bankingτ²-bench44.6%–
τ³-Banking (AA)Artificial Analysis39.0%34.9%
ITBench SRE (AA)Artificial Analysis45.8%–
Analyst Agent (AA)Artificial Analysis50.0%–
APEX-Agents (AA)Artificial Analysis37.7%–
CyberBenchVals AI–69.5%
Finance Agent v2Vals AI51.8%60.6%
Harvey's Legal Agent Benchmark v1Vals AI3.8%25.4%
Legal Research BenchVals AI40.4%43.8%
SkillsBenchVals AI62.2%53.0%
SREBenchVals AI3.8%0.0%
Tax Agent BenchVals AI21.8%32.8%
Terminal-Bench 2.0 (Vals)Vals AI73.2%†–
Terminal-Bench 4.0 (Vals)Vals AI–6.1%
Time Horizon Index: KSPVals AI8.3%–
Arena SearchArena (LMArena)1226†–
DeepResearch BenchDeepResearch Bench54.0%†–
PostTrainBenchEpoch AI Benchmarking Hub27.2%–
ExploitBenchEpoch AI Benchmarking Hub47.4%†–
GBAEvalEpoch AI Benchmarking Hub53.2%†–
Vending-Bench 2Andon Labs7523.8†–
AutomationBenchArtificial Analysis47.3%40.6%
GDP.pdf (AA)Artificial Analysis21.2%17.4%
EnterpriseOps-GymArtificial Analysis46.6%47.3%
AA-Briefcase v1.1Artificial Analysis11351324
Design Arena AgenticDesign Arena1105†1178†
RoboDojo (LLM as robot policy)RoboDojo1.1†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub85.3%–
FrontierMath Tier 4Epoch AI Benchmarking Hub72.5%–
OTIS Mock AIMEEpoch AI Benchmarking Hub84.4%†–
ProofBenchVals AI50.0%43.0%†
LiveBench MathematicsLiveBench95.9%91.2%
AIME 2026MathArena100.0%–
HMMT February 2026MathArena98.5%–
USAMO 2026MathArena98.2%–
MathArena ApexMathArena80.2%–
Arena MathsArena (LMArena)1500†1490
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub63.0%60.3%
LiveBench 1.0 Data AnalysisLiveBench81.6%76.5%
MMLU-ProVals AI88.1%88.3%
LegalBenchVals AI86.5%85.3%
CorpFinVals AI68.4%70.9%
TaxEvalVals AI75.0%80.4%
BioMysteryBenchVals AI–64.8%
CaseLaw v2Vals AI66.2%–
Excel Modeling BenchmarkVals AI64.5%57.0%
MedCodeVals AI49.1%49.4%
MedScribeVals AI86.9%90.1%
Public Benefits Bench v1.1Vals AI60.9%68.5%
DrugDiscoveryBenchScale AI SEAL51.6%–
EBR-benchEpoch AI Benchmarking Hub34.3%–
GDP.pdfEpoch AI Benchmarking Hub26.0%16.0%
Instruction following
LiveBench LanguageLiveBench87.4%78.6%
LiveBench Instruction FollowingLiveBench70.7%74.3%
IFBenchArtificial Analysis75.8%–
Arena Instruction FollowingArena (LMArena)1475†1479
Human preference
Arena TextArena (LMArena)1476†1494
EQ-Bench 4EQ-Bench1295†–
Arena Creative WritingArena (LMArena)1448†1443
Arena Multi-turnArena (LMArena)1484†1512
Arena Longer QueriesArena (LMArena)1486†1491
Multimodal
Arena VisionArena (LMArena)1296†1305
MMMU-ProArtificial Analysis79.9%–
MMMU-Pro (Vals)Vals AI88.3%86.1%
MortgageTaxVals AI68.8%65.4%
Blueprint-Bench 2Epoch AI Benchmarking Hub36.2%†–
Code2Video-AAArtificial Analysis1000–
Long context
AA-LCR v1.1Artificial Analysis84.3%79.0%
Arena DocumentArena (LMArena)1479†–
MLCRArtificial Analysis28.9%7.2%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub160.1†155†
LiveBench 1.0LiveBench80.2%78.0%
AA Intelligence Index v4.3.2Artificial Analysis38.439.6
AA Progress Index v1Artificial Analysis320309.1
Vals RSI IndexVals AI16.5%–
Vals Multimodal IndexVals AI68.1%69.8%†
Safety & honesty
FORTRESSScale AI SEAL16.3%–

Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-5.5 (xhigh): 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.
  • GPT-5.5 (xhigh): 1 new result (AA Progress Index v1).
  • Muse Spark 1.2 (xhigh): 1 new result (AA Progress Index v1).
  • Muse Spark 1.2 (xhigh): cost per task moved from $1.29/M to $0.81/M (37% down).
  • GPT-5.5 (xhigh): cost per task moved from $2.63/M to $2.10/M (20% down).
  • Muse Spark 1.2 (xhigh): cost per task moved from $0.97/M to $1.29/M (32% up).
  • GPT-5.5 (xhigh): 1 new result (AA-Briefcase v1.1).

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

GPT-5.5 vs Muse Spark 1.2: questions

Is GPT-5.5 better than Muse Spark 1.2?
GPT-5.5 (xhigh) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.2 vs 61.7, within the ±6.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 10 Nov 2026, so check the category scores for your use.
GPT-5.5 vs Muse Spark 1.2: which is cheaper, and will that change?
Muse Spark 1.2 is cheaper today: $2.00 against $11.25 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.5 or Muse Spark 1.2 better for coding?
GPT-5.5 scores higher in coding (61 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1512 for GPT-5.5 against 1534 for Muse Spark 1.2.
Which is faster, GPT-5.5 or Muse Spark 1.2?
Muse Spark 1.2 streams ~2× faster (192 vs 79 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.5 or Muse Spark 1.2 better for agents and tool use?
GPT-5.5 scores higher in agentic tasks (62 vs 56 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 39.0% for GPT-5.5 against 34.9% for Muse Spark 1.2.
More questions (4)
Which is better for long documents?
GPT-5.5 scores higher on long-context benchmarks (67 vs 64). Both take about 1.1M tokens: GPT-5.5 1,050,000, Muse Spark 1.2 1,048,576.
Which has lower latency?
Muse Spark 1.2 answers first: 7.9 s against 28.6 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-5.5 vs Muse Spark 1.2?
Across the 51 benchmarks both have, GPT-5.5 leads 31, Muse Spark 1.2 leads 19 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.2 ahead.
When was Muse Spark 1.2 released?
Muse Spark 1.2 was released on 5 Aug 2026.