BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

GPT-6 Sol vs Muse Spark

Full profiles: GPT-6 Sol (OpenAI) and Muse Spark (Meta): every benchmark, price and rank.

Updated · Data from 12 sources

As of 9 Nov 2026, GPT-6 Sol and Muse Spark are neck and neck on quality (62.9 vs 64.2 on the BenchLeader Index, inside the ±4.7 margin). Choose GPT-6 Sol for maths (69 vs 59), long context (67 vs 64), and coding (67 vs 65); choose Muse Spark for agents & tools (65 vs 60), human preference (68 vs 64), and multimodal (64 vs 61).

Key facts (as of 9 Nov 2026)

  • GPT-6 Sol scores 62.9 on the BenchLeader Index and Muse Spark scores 64.2 (BenchLeader, 9 Nov 2026).
  • GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 19 benchmarks both models have, Muse Spark leads 10 (BenchLeader, 9 Nov 2026).
GPT-6 Sol benchmarks max OpenAI Muse Spark benchmarks MetaAdd a third model

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-6 Sol67 vs 65 category score; SciCode 57.6% vs 51.5%Medium
Agents & tool useMuse Spark65 vs 60 category scoreMedium
MathsGPT-6 Sol69 vs 59 category score; OTIS Mock AIME 100.0% vs 88.9%High
ReasoningMuse Spark68 vs 66 category score; Arena Hard Prompts 1506 vs 1483Medium
KnowledgeMuse Spark63 vs 62 category score; MedCode 51.3% vs 47.1%Medium
Long documentsGPT-6 Sol67 vs 64 category score; AA-LCR v1.1 83.7% vs 78.0%Medium
Images and other mediaMuse Spark64 vs 61 category score; Arena Vision 1306 vs 1232Medium
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

  • GPT-6 Sol (max) and Muse Spark are neck and neck on quality (62.9 vs 64.2, within the ±4.7 margin).
  • GPT-6 Sol (max) is stronger in coding, long context, maths.
  • Muse Spark is stronger in agents & tools, human preference, knowledge, multimodal, reasoning, instruction following.

At a glance

SpecGPT-6 SolMuse Spark
DeveloperOpenAIMeta
Released22 Sep 20268 Apr 2026
Context window (tokens)1,050,000262,144
Compared atGPT-6 Sol (max)Muse Spark
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.200–

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-6 Sol (max)Muse SparkLeader
Reasoning66.267.5Muse Spark
Coding66.565.2GPT-6 Sol
Agents & tools59.665.0Muse Spark
Maths68.559.2GPT-6 Sol
Knowledge61.563.1Muse Spark
Instruction following–76.9not comparable
Human preference64.268.2Muse Spark
Multimodal60.764.2Muse Spark
Long context66.663.6GPT-6 Sol

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 contextMultimodalHumanpreferenceGPT-6 Sol, Reasoning: 66.2GPT-6 Sol, Coding: 66.5GPT-6 Sol, Agents & tools: 59.6GPT-6 Sol, Maths: 68.5GPT-6 Sol, Knowledge: 61.5GPT-6 Sol, Long context: 66.6GPT-6 Sol, Multimodal: 60.7GPT-6 Sol, Human preference: 64.2Muse Spark, Reasoning: 67.5Muse Spark, Coding: 65.2Muse Spark, Agents & tools: 65.0Muse Spark, Maths: 59.2Muse Spark, Knowledge: 63.1Muse Spark, Long context: 63.6Muse Spark, Multimodal: 64.2Muse Spark, Human preference: 68.2

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

ModelIndex

Where sources disagree

Across the 19 benchmarks both have, GPT-6 Sol leads 9, Muse Spark leads 10. Every overall index that rates both puts Muse Spark ahead.

Overall indexGPT-6 Sol (max)Muse SparkLeader
BenchLeader Index62.964.2neck and neck
Arena Text14571489Muse 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-6 Sol (max)Muse Spark
Blended price per 1M tokens$4.00–
Input / output per 1M$2.00 / $10.00– / –
Cached input per 1M$0.200–
Price per task: chat reply$0.0038–
Price per task: summarize a 30-page report$0.030–
Price per task: code edit$0.027–
Price per task: agentic coding session$0.160–
Price per task: structured extraction$0.0060–
Agentic coding session, input mostly cached$0.079–
Cost per benchmark task (AA Index)$2.47–
Output tokens per task (AA Index)54k–
Of which reasoning35k–
Time per task (AA Index)7 min–
Output speed121 tok/s–
Time to first answer72.1 s–
Time to a complete answer130.2 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-6 Sol (max) scores 62.9 and takes 72 s to its first answer token; GPT-6 Sol (xhigh) scores 58.6 in 24 s, GPT-6 Sol (high) scores 58.2 in 9 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

125 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-6 Sol (max)Muse Spark
BenchLeader IndexBenchLeader62.964.2
Agents & tools scoreBenchLeader59.665.0
Coding scoreBenchLeader66.565.2
Human preference scoreBenchLeader64.268.2
Knowledge scoreBenchLeader61.563.1
Long context scoreBenchLeader66.663.6
Maths scoreBenchLeader68.559.2
Multimodal scoreBenchLeader60.764.2
Reasoning scoreBenchLeader66.267.5
Instruction following scoreBenchLeader–76.9
Blended price $/MBenchLeader$4.00–
Output speedBenchLeader121 tok/s–
Time to first answerBenchLeader72.1 s–
Context windowBenchLeader1,050,000 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.3%89.8%
Humanity's Last ExamScale AI / CAIS–40.6%
Arena Hard PromptsArena (LMArena)14831506
LiveBench 1.0 ReasoningLiveBench88.7%–
GPQA Diamond (AA)Artificial Analysis–88.4%
Humanity's Last Exam (AA)Artificial Analysis47.9%40.7%
HLE-Diamond (AA)Artificial Analysis45.2%–
GPQA Diamond (Vals)Vals AI–89.7%
ARC-AGI-1ARC Prize95.5%–
ARC-AGI-2ARC Prize89.6%–
ARC-AGI-3ARC Prize23.0%–
CritPtArtificial Analysis30.9%11.3%
CritPt v2 hard subset (AA)Artificial Analysis66.5%–
MysteryMechanismVals AI30.2%–
Chess PuzzlesEpoch AI Benchmarking Hub56.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub56.0%–
LMCAEpoch AI Benchmarking Hub59.1%–
DTBenchEpoch AI Benchmarking Hub97.3%–
Coding
SciCodeSciCode57.6%51.5%
FrontierCodeCognition49.3%–
Arena CodingArena (LMArena)15201529
Arena WebDevArena (LMArena)1674–
LiveBench 1.0 CodingLiveBench81.8%–
SciCode (AA)Artificial Analysis57.6%–
IOIVals AI82.6%–
Show all 125 benchmarks
MetricPublisherGPT-6 Sol (max)Muse Spark
Coding
SWE-bench (Vals)Vals AI–74.4%
SWE-Bench ProScale AI SEAL–55.0%
Code MigrationVals AI57.2%–
ProgramBenchVals AI2.0%–
Vibe Code Bench v1.1Vals AI87.8%19.7%
SWE-Bench Pro (private)Scale AI SEAL–55.0%
SWE Atlas: Codebase QnAScale AI SEAL–24.2%
SWE Atlas: Test WritingScale AI SEAL–31.1%
ALE-BenchEpoch AI Benchmarking Hub2462–
Terminal-Bench 4.0 (AA)Artificial Analysis43.9%–
Terminal-Bench 2.1 (AA)Artificial Analysis–62.2%
GameBench 2 OverallDuelLab GameBench 272.9†–
GameBench 2 by reasoning settingDuelLab GameBench 279.3†–
Design Arena WebsiteDesign Arena1285†1258
FrontierCode 2.0 (AA)Artificial Analysis35.6%–
Agents & tools
Terminal-BenchTerminal-Bench50.3%–
APEX-AgentsMercor54.3%–
Arena AgentArena (LMArena)7–
LiveBench Agentic CodingLiveBench52.9%–
Terminal-Bench HardArtificial Analysis–45.5%
τ²-Bench Telecom (AA)Artificial Analysis–91.5%
Terminal-Bench 2.1 (Vals)Vals AI83.2%–
MCP AtlasScale AI SEAL–82.2%
ITBench SRE (AA)Artificial Analysis49.4%–
CyberBenchVals AI78.0%–
Finance Agent v2Vals AI49.0%–
Harvey's Legal Agent Benchmark v1Vals AI1.7%–
Legal Research BenchVals AI28.9%–
SREBenchVals AI30.5%–
Tax Agent BenchVals AI15.0%–
Terminal-Bench 2.0 (Vals)Vals AI–59.5%
Terminal-Bench 4.0 (Vals)Vals AI44.4%–
Terminal-Bench ScienceVals AI30.0%–
Arena SearchArena (LMArena)1229–
Vending-Bench 2Andon Labs14427.9†–
AutomationBenchArtificial Analysis61.6%–
GDP.pdf (AA)Artificial Analysis25.2%–
Harvey LAB-AA v1.1Harvey3.6%–
AA-Briefcase v1.1Artificial Analysis1476–
Design Arena AgenticDesign Arena1212†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis30.0%–
CWE-Bench (AA)Artificial Analysis64.2%–
DeepSec-Bench (AA)Artificial Analysis46.3%–
CyberGym end-to-end (AA)Artificial Analysis0.0%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub89.8%–
FrontierMath Tier 4Epoch AI Benchmarking Hub90.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%88.9%
ProofBenchVals AI83.0%†17.0%
LiveBench MathematicsLiveBench96.4%–
AIME (Vals)Vals AI–96.9%
Arena MathsArena (LMArena)14401468
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub60.7%–
LiveBench 1.0 Data AnalysisLiveBench81.2%–
AA-Omniscience v1.1Artificial Analysis21.4–
MMLU-ProVals AI–87.3%
LegalBenchVals AI–84.2%
CorpFinVals AI–65.1%
TaxEvalVals AI–77.7%
PRBench FinanceScale AI SEAL–52.4%
PRBench LegalScale AI SEAL38.6%†52.3%
MultiNRCScale AI SEAL–59.0%
BioMysteryBenchVals AI74.8%–
CaseLaw v2Vals AI–63.1%
Excel Modeling BenchmarkVals AI71.5%–
MedCodeVals AI47.1%51.3%
MedScribeVals AI82.0%85.9%
Public Benefits Bench v1.1Vals AI56.6%–
EBR-benchEpoch AI Benchmarking Hub53.3%–
GDP.pdfEpoch AI Benchmarking Hub26.4%–
AA-Omniscience v1.1: accuracyArtificial Analysis51.1%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis39.1%–
HealthBench Professional (AA)OpenAI62.3%–
Instruction following
LiveBench LanguageLiveBench85.3%–
LiveBench Instruction FollowingLiveBench68.6%–
IFBenchArtificial Analysis–75.9%
MultiChallengeScale AI SEAL–75.5%
TutorBenchScale AI SEAL–68.5%
Arena Instruction FollowingArena (LMArena)14481465
Human preference
Arena TextArena (LMArena)14571489
Arena Creative WritingArena (LMArena)14301464
Arena Multi-turnArena (LMArena)14661493
Arena Longer QueriesArena (LMArena)14661475
Multimodal
Arena VisionArena (LMArena)12321306
MMMU-ProArtificial Analysis83.0%80.5%
MMMU-Pro (official)MMMU–80.4%†
MMMU-Pro (Vals)Vals AI–87.4%
Blueprint-Bench 2Epoch AI Benchmarking Hub36.9%†–
AA-3DArtificial Analysis1131–
Long context
AA-LCR v1.1Artificial Analysis83.7%78.0%
Arena DocumentArena (LMArena)–1467
MLCRArtificial Analysis33.9%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub164.1†153.1
LiveBench 1.0LiveBench79.3%–
AA Intelligence Index v5.0Artificial Analysis44.2–
AA Intelligence Index v4.3.2Artificial Analysis47.631.3
AA Progress Index v1Artificial Analysis334289.1
Vals RSI IndexVals AI28.1%–
Vals Science IndexVals AI45.0%–
AA Cyber IndexArtificial Analysis36.8–
Safety & honesty
FORTRESSScale AI SEAL13.5%†20.2%

Data as of 2026-11-09. 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-6 Sol (max): BenchLeader Index 63.5 → 62.9.
  • GPT-6 Sol (max): 2 score revisions.
  • GPT-6 Sol (max): 1 score revision.
  • Muse Spark: BenchLeader Index 64.6 → 64.1.
  • GPT-6 Sol (max): 1 score revision.
  • Muse Spark: 1 score revision.
  • GPT-6 Sol (max): 6 new results (AA Intelligence Index v5.0, AA-Omniscience v1.1, CritPt v2 hard subset (AA)…).
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): 1 score revision.
  • GPT-6 Sol (max): BenchLeader Index 64.1 → 63.5.

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

GPT-6 Sol vs Muse Spark: questions

Is GPT-6 Sol better than Muse Spark?
GPT-6 Sol (max) and Muse Spark are neck and neck on quality (62.9 vs 64.2, within the ±4.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
Is GPT-6 Sol or Muse Spark better for coding?
GPT-6 Sol scores higher in coding (67 vs 65 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 57.6% for GPT-6 Sol against 51.5% for Muse Spark.
Is GPT-6 Sol or Muse Spark better for agents and tool use?
Muse Spark scores higher in agentic tasks (65 vs 60 on the category index, where 50 is average).
Which is better for long documents?
GPT-6 Sol scores higher on long-context benchmarks (67 vs 64). GPT-6 Sol accepts more context: 1,050,000 against 262,144 tokens for Muse Spark.
Do independent benchmarks agree on GPT-6 Sol vs Muse Spark?
Across the 19 benchmarks both have, GPT-6 Sol leads 9, Muse Spark leads 10. Every overall index that rates both puts Muse Spark ahead.
More questions (1)
When was GPT-6 Sol released?
GPT-6 Sol was released on 22 Sep 2026.