BenchLeader

Muse Spark 1.3 vs Qwen3.6 Plus

Full profiles: Muse Spark 1.3 (Meta) and Qwen3.6 Plus (Alibaba): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, Muse Spark 1.3 and Qwen3.6 Plus are neck and neck on quality (61.6 vs 59.0 on the BenchLeader Index, inside the ±9.2 margin), and Qwen3.6 Plus is 1.8× cheaper at $1.13 vs $2.00 per 1M tokens blended. Choose Muse Spark 1.3 for knowledge (81 vs 57), agents & tools (61 vs 53), and reasoning (71 vs 63) and fast first answers (2.6 s vs 44.4 s), where it also streams ~1.5× faster; choose Qwen3.6 Plus for maths (58 vs 56).

Key facts (as of 16 Nov 2026)

  • Muse Spark 1.3 scores 61.6 on the BenchLeader Index and Qwen3.6 Plus scores 59.0 (BenchLeader, 16 Nov 2026).
  • Muse Spark 1.3 costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.6 Plus costs $1.13 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Spark 1.3 streams ~1.5× faster than Qwen3.6 Plus (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 3 benchmarks both models have, Muse Spark 1.3 leads 3 (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
Agents & tool useMuse Spark 1.361 vs 53 category scoreHigh
MathsQwen3.6 Plus58 vs 56 category scoreMedium
ReasoningMuse Spark 1.371 vs 63 category score; LMCA 53.9% vs 33.1%High
KnowledgeMuse Spark 1.381 vs 57 category scoreHigh
Chat quality (human preference)–Only Qwen3.6 Plus has an Arena rating (62 category score)Not comparable
Lowest costQwen3.6 Plus$1.13 vs $2.00 per 1M blended; agentic coding session $0.042 vs $0.092–
Fastest first answerMuse Spark 1.32.6 s (Muse Spark 1.3) vs 44.4 s (Qwen3.6 Plus) 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

  • Muse Spark 1.3 and Qwen3.6 Plus are neck and neck on quality (61.6 vs 59.0, within the ±9.2 margin).
  • Muse Spark 1.3 is stronger in agents & tools, knowledge, reasoning.
  • Qwen3.6 Plus is stronger in maths.
  • Qwen3.6 Plus is 1.8× cheaper ($1.13 vs $2.00 per 1M blended).
  • Muse Spark 1.3 streams 3.1× faster (163 vs 52 tokens per second).

At a glance

SpecMuse Spark 1.3Qwen3.6 Plus
DeveloperMetaAlibaba
Released2 Sep 202631 Mar 2026
Context window (tokens)1,048,5761,000,000
Compared atMuse Spark 1.3Qwen3.6 Plus
Open weightsNoNo
Price in / out / cached input per 1M$1.25 / $4.25 / $0.150$0.500 / $3.00 / $0.050

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.

CategoryMuse Spark 1.3Qwen3.6 PlusLeader
Reasoning71.062.9Muse Spark 1.3
Coding–50.8not comparable
Agents & tools61.353.1Muse Spark 1.3
Maths56.357.6Qwen3.6 Plus
Knowledge81.256.9Muse Spark 1.3
Instruction following–73.4not comparable
Human preference–62.4not comparable
Multimodal–60.3not comparable
Long context–63.8not comparable

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 avg75ReasoningAgents & toolsMathsKnowledgeMuse Spark 1.3, Reasoning: 71.0Muse Spark 1.3, Agents & tools: 61.3Muse Spark 1.3, Maths: 56.3Muse Spark 1.3, Knowledge: 81.2Qwen3.6 Plus, Reasoning: 62.9Qwen3.6 Plus, Agents & tools: 53.1Qwen3.6 Plus, Maths: 57.6Qwen3.6 Plus, Knowledge: 56.9

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

Model, click to add or removeIndex

Where sources disagree

Across the 3 benchmarks both have, Muse Spark 1.3 leads 3, Qwen3.6 Plus leads 0. Every overall index that rates both puts Muse Spark 1.3 ahead.

Overall indexMuse Spark 1.3Qwen3.6 PlusLeader
BenchLeader Index61.659.0neck and neck
Arena Text1497†1443Muse 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.

MeasureMuse Spark 1.3Qwen3.6 Plus
Blended price per 1M tokens$2.00$1.13
Input / output per 1M$1.25 / $4.25$0.500 / $3.00
Cached input per 1M$0.150$0.050
Price per task: chat reply$0.0018$0.0011
Price per task: summarize a 30-page report$0.018$0.0078
Price per task: code edit$0.014$0.0075
Price per task: agentic coding session$0.092$0.042
Price per task: structured extraction$0.0034$0.0016
Agentic coding session, input mostly cached$0.043$0.022
Output speed163 tok/s52 tok/s
Time to first answer2.6 s44.4 s
Time to a complete answer, last measured 13 Nov 2026–113.4 s

Each model is compared at its best-ranked reasoning-effort setting. Muse Spark 1.3 scores 61.6 and takes 3 s to its first answer token; Muse Spark 1.3 (max) scores 60.6 in 31 s, Muse Spark 1.3 (xhigh) scores 58.1 in 11 s. Qwen3.6 Plus scores 59.0 and takes 44 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

144 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.

MetricPublisherMuse Spark 1.3Qwen3.6 Plus
BenchLeader IndexBenchLeader61.659.0
Agents & tools scoreBenchLeader61.353.1
Knowledge scoreBenchLeader81.256.9
Maths scoreBenchLeader56.357.6
Reasoning scoreBenchLeader71.062.9
Coding scoreBenchLeader–50.8
Human preference scoreBenchLeader–62.4
Instruction following scoreBenchLeader–73.4
Long context scoreBenchLeader–63.8
Multimodal scoreBenchLeader–60.3
Blended price $/MBenchLeader$2.00$1.13
Output speedBenchLeader163 tok/s52 tok/s
Time to first answerBenchLeader2.6 s44.4 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–88.4%
SimpleBenchSimpleBench81.8%–
Arena Hard PromptsArena (LMArena)1517†1467
LiveBench 2.0 ReasoningLiveBench89.7%†–
LiveBench 1.0 ReasoningLiveBench89.7%†75.8%
GPQA Diamond (AA)Artificial Analysis93.5%†88.2%
Humanity's Last Exam (AA)Artificial Analysis48.7%†27.9%
HLE-Diamond (AA)Artificial Analysis33.7%†–
GPQA Diamond (Vals)Vals AI–87.4%
CritPtArtificial Analysis24.9%†2.9%
CritPt v2 hard subset (AA)Artificial Analysis48.0%†–
MysteryMechanismVals AI36.0%†–
HLE-Diamond (Scale)Scale AI SEAL25.4%–
Arena ExpertArena (LMArena)1521†1475
Chess PuzzlesEpoch AI Benchmarking Hub37.0%†16.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub25.0%†12.0%†
CL-benchEpoch AI Benchmarking Hub–20.3%
LMCAEpoch AI Benchmarking Hub53.9%33.1%
DTBenchEpoch AI Benchmarking Hub96.5%81.9%
ForecastBenchForecastBench65.5%†–
BTF-3Epoch AI Benchmarking Hub14.1%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–57.9%
SciCodeSciCode58.8%†40.7%
Arena CodingArena (LMArena)1534†1496
Arena WebDevArena (LMArena)1655†1461
Show all 144 benchmarks
MetricPublisherMuse Spark 1.3Qwen3.6 Plus
Coding
LiveBench 2.0 CodingLiveBench84.4%†–
LiveBench 1.0 CodingLiveBench81.1%†78.2%
SciCode (AA)Artificial Analysis58.8%†–
LiveCodeBenchVals AI–86.0%
IOIVals AI56.6%†–
SWE-bench (Vals)Vals AI–73.4%
Code MigrationVals AI47.4%†11.1%
ProgramBenchVals AI2.5%†0.0%
SWE-bench MultimodalVals AI43.1%†–
Vibe Code Bench 1-100Vals AI20.5%†–
Vibe Code Bench v1.1Vals AI85.9%†25.6%
MirrorCodeEpoch AI Benchmarking Hub54.4%†–
CursorBenchCursor41.6%†–
ALE-BenchEpoch AI Benchmarking Hub1688.3†670.1
FrontierSWEEpoch AI Benchmarking Hub25.8%†–
WeirdML v3WeirdML6.7%†–
Terminal-Bench 4.0 (AA)Artificial Analysis33.3%†–
Terminal-Bench 2.1 (AA)Artificial Analysis84.3%†61.4%
Startrise FrontendStartrise74.7%–
GameBench 2 OverallDuelLab GameBench 257.7–
GameBench 2 by reasoning settingDuelLab GameBench 268.5†–
Design Arena WebsiteDesign Arena1353†1234
FrontierCode 1.1 (AA)Artificial Analysis40.6%†–
FrontierCode 2.0 (AA)Artificial Analysis23.1%†–
Agents & tools
Terminal-BenchTerminal-Bench14.8%†–
APEX-AgentsMercor58.6%–
Arena AgentArena (LMArena)2.2†–
LiveBench Long AgenticLiveBench47.9%†–
LiveBench BrowserLiveBench30.9%†–
LiveBench Agentic CodingLiveBench64.1%†41.4%
Terminal-Bench HardArtificial Analysis–43.9%
τ²-Bench Telecom (AA)Artificial Analysis–97.7%
Terminal-Bench 2.1 (Vals)Vals AI79.0%†53.2%
HiL-BenchScale AI SEAL66.9%–
GDPval-AA v2.1Artificial Analysis1681†997
τ³-Banking (AA)Artificial Analysis50.5%†20.8%
ITBench SRE (AA)Artificial Analysis33.2%†–
Analyst Agent (AA)Artificial Analysis37.5%†–
CUA-benchVals AI5.8%†–
CyberBenchVals AI72.7%†–
Finance Agent v2Vals AI60.0%†40.9%
Harvey's Legal Agent Benchmark v1Vals AI23.8%†1.3%
Legal Research BenchVals AI55.3%†14.9%
SREBenchVals AI3.8%†–
Tax Agent BenchVals AI42.4%†7.7%
Terminal-Bench 2.0 (Vals)Vals AI–44.9%
Terminal-Bench 4.0 (Vals)Vals AI24.8%†–
Terminal-Bench ScienceVals AI10.0%†–
Arena Agent Task CompletionArena (LMArena)3.7†–
Vending-Bench 2Andon Labs–5114.9
AutomationBenchArtificial Analysis57.9%†–
GDP.pdf (AA)Artificial Analysis26.6%†–
Harvey LAB-AA v1.1Harvey8.9%†–
AA-Briefcase v1.1Artificial Analysis1581†–
Design Arena AgenticDesign Arena1283†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis10.9%†–
CWE-Bench (AA)Artificial Analysis60.8%†–
DeepSec-Bench (AA)Artificial Analysis12.5%†–
CyberGym end-to-end (AA)Artificial Analysis59.5%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub74.0%†38.3%
FrontierMath Tier 4Epoch AI Benchmarking Hub46.3%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub99.2%†93.3%
ProofBenchVals AI55.0%–
LiveBench MathematicsLiveBench96.0%†83.7%
AIME (Vals)Vals AI–94.6%
Arena MathsArena (LMArena)1506†1451
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–44.1%
LiveBench 2.0 Data AnalysisLiveBench79.6%†–
LiveBench ResearchLiveBench82.5%†–
LiveBench 1.0 Data AnalysisLiveBench79.6%†69.9%
AA-Omniscience v1.1Artificial Analysis22.4†–
MMLU-ProVals AI–87.7%
LegalBenchVals AI–84.2%
CorpFinVals AI–61.9%
TaxEvalVals AI–74.7%
PRBench FinanceScale AI SEAL59.5%–
PRBench LegalScale AI SEAL61.6%–
CaseLaw v2Vals AI–51.5%
Excel Modeling BenchmarkVals AI67.4%†32.9%
MedCodeVals AI–36.9%
MedScribeVals AI–77.0%
Access to Justice BenchmarkVals AI72.2%†–
Financial Coaching BenchVals AI70.3%†–
Immigration BenchVals AI64.9%†–
DrugDiscoveryBenchScale AI SEAL62.2%†–
GDP.pdfEpoch AI Benchmarking Hub27.6%–
AA-Omniscience v1.1: accuracyArtificial Analysis38.0%†–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis74.8%†–
Instruction following
LiveBench LanguageLiveBench82.8%†75.0%
LiveBench Instruction FollowingLiveBench78.0%†58.3%
IFBenchArtificial Analysis–75.2%
Arena Instruction FollowingArena (LMArena)1485†1435
Human preference
Arena TextArena (LMArena)1497†1443
EQ-Bench Creative Writing v3EQ-Bench1907–
Arena Creative WritingArena (LMArena)1468†1407
Arena Multi-turnArena (LMArena)1493†1445
Arena Longer QueriesArena (LMArena)1498†1455
Multimodal
Arena VisionArena (LMArena)1310†–
LiveBench DesignLiveBench74.8%†–
MMMU-ProArtificial Analysis82.0%†78.0%
MMMU-Pro (Vals)Vals AI–84.2%
MortgageTaxVals AI–68.0%
Humanity's Sixth SenseScale AI SEAL37.4%†–
GeoBenchGeoBench86.0%–
Code2Video-AAArtificial Analysis1019†–
AA-3DArtificial Analysis1032†–
Long context
AA-LCR v1.1Artificial Analysis83.0%†78.3%
Arena DocumentArena (LMArena)1474†–
MLCRArtificial Analysis13.9%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub158.2148.9
LiveBench 2.0LiveBench68.6%†–
LiveBench 1.0LiveBench81.6%†68.9%
AA Intelligence Index v5.0.1Artificial Analysis36.6†–
AA Intelligence Index v4.3.2Artificial Analysis48.1†27.0
AA Progress Index v1Artificial Analysis324.5†283.4
Vals RSI IndexVals AI19.6%†–
Vals Multimodal IndexVals AI–51.5%
AA Cyber IndexArtificial Analysis44.3†–
Safety & honesty
DistressBenchScale AI SEAL84.9%–

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

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Muse Spark 1.3: BenchLeader Index 60.2 → 61.6.
  • Qwen3.6 Plus: 1 new result (GDPval-AA v2.1).
  • Muse Spark 1.3: 1 score revision.
  • Muse Spark 1.3: BenchLeader Index 59.2 → 60.2.
  • Muse Spark 1.3: 2 new results (SimpleBench, GeoBench).
  • Muse Spark 1.3: BenchLeader Index 57.7 → 59.2.
  • Muse Spark 1.3: 4 score revisions.
  • Muse Spark 1.3: BenchLeader Index 58.2 → 57.7.
  • Muse Spark 1.3: 1 score revision.
  • Qwen3.6 Plus: 2 score revisions.

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

Muse Spark 1.3 vs Qwen3.6 Plus: questions

Is Muse Spark 1.3 better than Qwen3.6 Plus?
Muse Spark 1.3 and Qwen3.6 Plus are neck and neck on quality (61.6 vs 59.0, within the ±9.2 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Muse Spark 1.3 vs Qwen3.6 Plus: which is cheaper, and will that change?
Qwen3.6 Plus is cheaper today: $1.13 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Which is faster, Muse Spark 1.3 or Qwen3.6 Plus?
Muse Spark 1.3 streams ~1.5× faster (163 vs 52 output tokens per second, Artificial Analysis 7-day median).
Is Muse Spark 1.3 or Qwen3.6 Plus better for agents and tool use?
Muse Spark 1.3 scores higher in agentic tasks (61 vs 53 on the category index, where 50 is average).
Which is better for long documents?
Both take about 1M tokens: Muse Spark 1.3 1,048,576, Qwen3.6 Plus 1,000,000.
More questions (3)
Which has lower latency?
Muse Spark 1.3 answers first: 2.6 s against 44.4 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 Muse Spark 1.3 vs Qwen3.6 Plus?
Across the 3 benchmarks both have, Muse Spark 1.3 leads 3, Qwen3.6 Plus leads 0. 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.