BenchLeader

GPT-6.1 Sol vs Muse Spark

Full profiles: GPT-6.1 Sol (OpenAI) and Muse Spark (Meta): every benchmark, price and rank.

Updated · Data from 13 sources

As of 10 Nov 2026, GPT-6.1 Sol is ahead of Muse Spark on quality (66.9 vs 64.2 on the BenchLeader Index). GPT-6.1 Sol leads in every category we measure both in.

Key facts (as of 10 Nov 2026)

  • GPT-6.1 Sol scores 66.9 on the BenchLeader Index and Muse Spark scores 64.2 (BenchLeader, 10 Nov 2026).
  • GPT-6.1 Sol costs $4.00 per 1M tokens blended (list price, 10 Nov 2026).
  • Of the 19 benchmarks both models have, GPT-6.1 Sol leads 15 (BenchLeader, 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-6.1 Sol71 vs 65 category score; SciCode 54.2% vs 51.5%Medium
Agents & tool useEither65 vs 65 category scoreEither
MathsGPT-6.1 Sol72 vs 59 category score; Arena Maths 1502 vs 1469High
ReasoningGPT-6.1 Sol72 vs 67 category score; GPQA Diamond 95.4% vs 89.8%Medium
KnowledgeGPT-6.1 Sol72 vs 63 category score; MedScribe 86.5% vs 85.9%High
Long documentsGPT-6.1 Sol66 vs 64 category score; AA-LCR v1.1 83.0% vs 78.0%Medium
Images and other mediaGPT-6.1 Sol66 vs 64 category score; MMMU-Pro 86.0% vs 80.5%Medium
Chat quality (human preference)Either67 vs 68 on Arena votesEither
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-6.1 Sol (max) leads on quality: 66.9 vs 64.2.
  • GPT-6.1 Sol (max) is stronger in coding, knowledge, long context, maths, multimodal, reasoning.
  • Muse Spark is stronger in agents & tools, human preference, instruction following.

At a glance

SpecGPT-6.1 SolMuse Spark
DeveloperOpenAIMeta
Released29 Sep 20268 Apr 2026
Context window (tokens)1,050,000262,144
Compared atGPT-6.1 Sol (max)Muse Spark
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.100–

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-6.1 Sol (max)Muse SparkLeader
Reasoning71.767.4GPT-6.1 Sol
Coding71.465.2GPT-6.1 Sol
Agents & tools64.565.0level
Maths72.059.2GPT-6.1 Sol
Knowledge72.163.1GPT-6.1 Sol
Instruction following–76.9not comparable
Human preference67.368.1level
Multimodal65.764.2GPT-6.1 Sol
Long context66.363.6GPT-6.1 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-6.1 Sol, Reasoning: 71.7GPT-6.1 Sol, Coding: 71.4GPT-6.1 Sol, Agents & tools: 64.5GPT-6.1 Sol, Maths: 72.0GPT-6.1 Sol, Knowledge: 72.1GPT-6.1 Sol, Long context: 66.3GPT-6.1 Sol, Multimodal: 65.7GPT-6.1 Sol, Human preference: 67.3Muse Spark, Reasoning: 67.4Muse 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: 68.1

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

ModelIndex

Where sources disagree

Across the 19 benchmarks both have, GPT-6.1 Sol leads 15, Muse Spark leads 4. Independent sources split: GPT-6.1 Sol leads on BenchLeader Index; Muse Spark leads on Arena Text.

Overall indexGPT-6.1 Sol (max)Muse SparkLeader
BenchLeader Index66.964.2GPT-6.1 Sol
Arena Text14821489Muse 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-6.1 Sol (max)Muse Spark
Blended price per 1M tokens$4.00–
Input / output per 1M$2.00 / $10.00– / –
Cached input per 1M$0.100–
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$0.074–
Cost per benchmark task (AA Index)$1.27–
Output tokens per task (AA Index)68k–
Of which reasoning49k–
Time per task (AA Index)20 min–
Output speed56 tok/s–
Time to first answer151.0 s–
Time to a complete answer364.9 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Sol (max) scores 66.9 and takes 151 s to its first answer token; GPT-6.1 Sol (xhigh) scores 63.8 in 62 s, GPT-6.1 Sol (high) scores 63.6 in 33 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

148 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-6.1 Sol (max)Muse Spark
BenchLeader IndexBenchLeader66.964.2
Agents & tools scoreBenchLeader64.565.0
Coding scoreBenchLeader71.465.2
Human preference scoreBenchLeader67.368.1
Knowledge scoreBenchLeader72.163.1
Long context scoreBenchLeader66.363.6
Maths scoreBenchLeader72.059.2
Multimodal scoreBenchLeader65.764.2
Reasoning scoreBenchLeader71.767.4
Instruction following scoreBenchLeader–76.9
Blended price $/MBenchLeader$4.00–
Output speedBenchLeader56 tok/s–
Time to first answerBenchLeader151.0 s–
Context windowBenchLeader1,050,000 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub95.4%89.8%
Humanity's Last ExamScale AI / CAIS–40.6%
Arena Hard PromptsArena (LMArena)15061506
LiveBench 2.0 ReasoningLiveBench92.6%†–
LiveBench 1.0 ReasoningLiveBench92.6%–
GPQA Diamond (AA)Artificial Analysis–88.4%
Humanity's Last Exam (AA)Artificial Analysis52.9%40.7%
HLE-Diamond (AA)Artificial Analysis58.8%–
GPQA Diamond (Vals)Vals AI–89.7%
ARC-AGI-1ARC Prize96.5%–
ARC-AGI-2ARC Prize94.2%–
ARC-AGI-3ARC Prize96.2%–
CritPtArtificial Analysis31.7%11.3%
CritPt v2 hard subset (AA)Artificial Analysis69.5%–
MysteryMechanismVals AI46.4%–
Chess PuzzlesEpoch AI Benchmarking Hub68.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub80.0%–
LMCAEpoch AI Benchmarking Hub62.8%–
DTBenchEpoch AI Benchmarking Hub96.5%–
Coding
SciCodeSciCode54.2%51.5%
FrontierCodeCognition50.2%†–
Arena CodingArena (LMArena)15401529
Arena WebDevArena (LMArena)1743–
LiveBench 2.0 CodingLiveBench82.1%†–
LiveBench 1.0 CodingLiveBench80.4%–
Show all 148 benchmarks
MetricPublisherGPT-6.1 Sol (max)Muse Spark
Coding
SciCode (AA)Artificial Analysis54.2%–
IOIVals AI96.9%–
SWE-bench (Vals)Vals AI–74.4%
SWE-Bench ProScale AI SEAL–55.0%
Code MigrationVals AI65.1%–
Code Migration v1.1Vals AI77.3%–
ProgramBenchVals AI3.0%–
SWE-bench MultimodalVals AI43.5%–
Vibe Code Bench v1.1Vals AI88.9%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 Hub2743.8–
Terminal-Bench 4.0 (AA)Artificial Analysis56.1%–
Terminal-Bench 2.1 (AA)Artificial Analysis–62.2%
Startrise FrontendStartrise78.6%†–
GameBench 2 OverallDuelLab GameBench 284.8†–
GameBench 2 by reasoning settingDuelLab GameBench 292.0†–
Design Arena WebsiteDesign Arena1309†1257
FrontierCode 1.1 (AA)Artificial Analysis49.1%–
FrontierCode 2.0 (AA)Artificial Analysis40.6%–
Agents & tools
Terminal-BenchTerminal-Bench60.9%–
APEX-AgentsMercor60.0%–
Arena AgentArena (LMArena)12.5–
LiveBench Long AgenticLiveBench65.6%†–
LiveBench BrowserLiveBench93.3%†–
LiveBench Agentic CodingLiveBench54.5%–
Terminal-Bench HardArtificial Analysis–45.5%
τ²-Bench Telecom (AA)Artificial Analysis–91.5%
MCP AtlasScale AI SEAL–82.2%
HiL-BenchScale AI SEAL62.3%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis54.8%–
GDPval-AA v2.1Artificial Analysis1608–
Analyst Agent (AA)Artificial Analysis50.0%–
CyberBenchVals AI39.3%–
Finance Agent v2Vals AI52.0%–
Finance Agent v2.1Vals AI61.8%–
Harvey's Legal Agent Benchmark v1.1Vals AI6.3%–
Harvey's Legal Agent Benchmark v1Vals AI5.4%–
Legal Research BenchVals AI38.5%–
Robo-benchVals AI28.3%–
SREBenchVals AI50.8%–
Tax Agent BenchVals AI21.8%–
Terminal-Bench 2.0 (Vals)Vals AI–59.5%
Terminal-Bench 4.0 (Vals)Vals AI55.0%–
Terminal-Bench ScienceVals AI52.9%–
Arena SearchArena (LMArena)1249–
Vending-Bench 2Andon Labs12860.6†–
AutomationBenchArtificial Analysis64.9%–
GDP.pdf (AA)Artificial Analysis31.0%–
Harvey LAB-AA v1.1Harvey6.9%–
AA-Briefcase v1.1Artificial Analysis1555–
GDPxGDPx by SemiAnalysis8.4%–
Design Arena AgenticDesign Arena1423–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis58.1%–
FACTS SearchGoogle92.8%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub93.7%–
FrontierMath Tier 4Epoch AI Benchmarking Hub100.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%88.9%
ProofBenchVals AI99.0%†17.0%
LiveBench MathematicsLiveBench96.8%–
AIME (Vals)Vals AI–96.9%
Arena MathsArena (LMArena)15021469
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub73.9%–
LiveBench 2.0 Data AnalysisLiveBench82.7%†–
LiveBench ResearchLiveBench90.0%†–
LiveBench 1.0 Data AnalysisLiveBench82.7%–
AA-Omniscience v1.1Artificial Analysis42.0–
MMLU-ProVals AI–87.3%
LegalBenchVals AI–84.2%
CorpFinVals AI–65.1%
TaxEvalVals AI–77.7%
PRBench FinanceScale AI SEAL46.2%†52.4%
PRBench LegalScale AI SEAL47.9%†52.3%
MultiNRCScale AI SEAL–59.0%
BioMysteryBenchVals AI79.6%–
CaseLaw v2Vals AI–63.1%
ClaimBenchVals AI100.0%–
Excel Modeling BenchmarkVals AI70.8%–
Excel Modeling Benchmark v1.1Vals AI71.1%–
MedCodeVals AI48.8%51.3%
MedScribeVals AI86.5%85.9%
Public Benefits Bench v1.1Vals AI59.3%–
EBR-benchEpoch AI Benchmarking Hub54.3%–
GDP.pdfEpoch AI Benchmarking Hub35.0%–
AA-Omniscience v1.1: accuracyArtificial Analysis61.8%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis48.1%–
HealthBench Professional (AA)OpenAI65.1%–
Instruction following
LiveBench LanguageLiveBench90.1%–
LiveBench Instruction FollowingLiveBench74.2%–
IFBenchArtificial Analysis–75.9%
MultiChallengeScale AI SEAL82.0%†75.5%
TutorBenchScale AI SEAL–68.5%
Arena Instruction FollowingArena (LMArena)14831465
Human preference
Arena TextArena (LMArena)14821489
EQ-Bench 4EQ-Bench1272†–
Arena Creative WritingArena (LMArena)14491464
Arena Multi-turnArena (LMArena)14881493
Arena Longer QueriesArena (LMArena)14891475
Multimodal
Arena VisionArena (LMArena)12861306
LiveBench DesignLiveBench79.6%†–
MMMU-ProArtificial Analysis86.0%80.5%
MMMU-Pro (official)MMMU–80.4%†
MMMU-Pro (Vals)Vals AI–87.4%
SAGEVals AI90.5%–
Blueprint-Bench 2Epoch AI Benchmarking Hub43.2%†–
Code2Video-AAArtificial Analysis1369–
AA-3DArtificial Analysis1121–
Long context
AA-LCR v1.1Artificial Analysis83.0%78.0%
Arena DocumentArena (LMArena)–1467
MLCRArtificial Analysis38.3%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.9†153.1
LiveBench 2.0LiveBench81.4%†–
LiveBench 1.0LiveBench81.6%–
AA Intelligence Index v5.0Artificial Analysis54.6–
AA Intelligence Index v4.3.2Artificial Analysis51.831.3
AA Progress Index v1Artificial Analysis348.5289.1
Vals IndexVals AI63.9–
Vals Finance IndexVals AI55.8%–
Vals RSI IndexVals AI26.6%–
Vals Science IndexVals AI59.6%–
Vals Router IndexVals AI63.9%†–
Safety & honesty
FORTRESSScale AI SEAL–20.2%

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-6.1 Sol (max): BenchLeader Index 67.4 → 66.9.
  • GPT-6.1 Sol (max): 2 score revisions.
  • GPT-6.1 Sol (max): 3 score revisions.
  • Muse Spark: BenchLeader Index 64.6 → 64.1.
  • Muse Spark: 1 score revision.
  • GPT-6.1 Sol (max): 1 score revision.
  • GPT-6.1 Sol (max): 1 new result (MirrorCode).
  • GPT-6.1 Sol (max): 1 score revision.
  • GPT-6.1 Sol (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $0.72/M to $1.27/M (76% up).
  • Muse Spark: 1 new result (AA Progress Index v1).

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

GPT-6.1 Sol vs Muse Spark: questions

Is GPT-6.1 Sol better than Muse Spark?
GPT-6.1 Sol (max) leads on quality: 66.9 vs 64.2. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 10 Nov 2026, but check the category scores for your use.
Is GPT-6.1 Sol or Muse Spark better for coding?
GPT-6.1 Sol scores higher in coding (71 vs 65 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 54.2% for GPT-6.1 Sol against 51.5% for Muse Spark.
Is GPT-6.1 Sol or Muse Spark better for agents and tool use?
They are level in agentic tasks (65 vs 65 on the category index).
Which is better for long documents?
GPT-6.1 Sol scores higher on long-context benchmarks (66 vs 64). GPT-6.1 Sol accepts more context: 1,050,000 against 262,144 tokens for Muse Spark.
Do independent benchmarks agree on GPT-6.1 Sol vs Muse Spark?
Across the 19 benchmarks both have, GPT-6.1 Sol leads 15, Muse Spark leads 4. Independent sources split: GPT-6.1 Sol leads on BenchLeader Index; Muse Spark leads on Arena Text.
More questions (1)
When was GPT-6.1 Sol released?
GPT-6.1 Sol was released on 29 Sep 2026.