BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases4

Muse Spark 1.2 vs Qwen3.6 Max

Full profiles: Muse Spark 1.2 (Meta) and Qwen3.6 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 8 sources

As of 2 Nov 2026, Muse Spark 1.2 and Qwen3.6 Max are neck and neck on quality (61.6 vs 62.4 on the BenchLeader Index, inside the ±5.8 margin), and Muse Spark 1.2 is 1.5× cheaper at $2.00 vs $2.92 per 1M tokens blended. Choose Muse Spark 1.2 for reasoning (68 vs 63), knowledge (65 vs 60), and human preference (69 vs 65); choose Qwen3.6 Max for agents & tools (72 vs 55) and coding (56 vs 55).

Key facts (as of 2 Nov 2026)

  • Muse Spark 1.2 scores 61.6 on the BenchLeader Index and Qwen3.6 Max scores 62.4 (BenchLeader, 2 Nov 2026).
  • Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 2 Nov 2026).
  • Qwen3.6 Max costs $2.92 per 1M tokens blended (list price, 2 Nov 2026).
  • Of the 18 benchmarks both models have, Muse Spark 1.2 leads 17 (BenchLeader, 2 Nov 2026).
  • On Arena WebDev, Muse Spark 1.2 is rated 1534 and Qwen3.6 Max 1482 (LMArena, as published by 2 Nov 2026).
Muse Spark 1.2 benchmarks xhigh Meta Qwen3.6 Max benchmarks max AlibabaAdd 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
CodingQwen3.6 Max56 vs 55 category score; Arena WebDev 1482 vs 1534Medium
Agents & tool useQwen3.6 Max72 vs 55 category scoreHigh
MathsMuse Spark 1.267 vs 65 category score; Arena Maths 1492 vs 1476Medium
ReasoningMuse Spark 1.268 vs 63 category score; Arena Hard Prompts 1513 vs 1482Medium
KnowledgeMuse Spark 1.265 vs 60 category score; SimpleQA Verified 60.3% vs 52.0%Medium
Long documentsEither64 vs 65 category score; AA-LCR v1.1 79.0% vs 80.7%Either
Chat quality (human preference)Muse Spark 1.269 vs 65 on Arena votesMedium
Lowest costMuse Spark 1.2$2.00 vs $2.96 per 1M blended; agentic coding session $0.092 vs $0.111–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Muse Spark 1.2 (xhigh) and Qwen3.6 Max (max) are neck and neck on quality (61.6 vs 62.4, within the ±5.8 margin).
  • Muse Spark 1.2 (xhigh) is stronger in human preference, knowledge, maths, multimodal, reasoning.
  • Qwen3.6 Max (max) is stronger in agents & tools, coding, long context, instruction following.
  • Muse Spark 1.2 (xhigh) is 1.5× cheaper ($2.00 vs $2.96 per 1M blended).

At a glance

SpecMuse Spark 1.2Qwen3.6 Max
DeveloperMetaAlibaba
Released5 Aug 202620 Apr 2026
Context window (tokens)1,048,576245,800
Compared atMuse Spark 1.2 (xhigh)Qwen3.6 Max (max)
Open weightsNoNo
Price in / out / cached input per 1M$1.25 / $4.25 / $0.150$1.32 / $7.90 / $0.132

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 1.2 (xhigh)Qwen3.6 Max (max)Leader
Reasoning68.162.7Muse Spark 1.2
Coding55.056.3Qwen3.6 Max
Agents & tools55.472.1Qwen3.6 Max
Maths67.364.7Muse Spark 1.2
Knowledge64.760.0Muse Spark 1.2
Instruction following–74.6not comparable
Human preference68.564.6Muse Spark 1.2
Multimodal65.2–not comparable
Long context64.365.2level

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 contextHumanpreferenceMuse Spark 1.2, Reasoning: 68.1Muse Spark 1.2, Coding: 55.0Muse Spark 1.2, Agents & tools: 55.4Muse Spark 1.2, Maths: 67.3Muse Spark 1.2, Knowledge: 64.7Muse Spark 1.2, Long context: 64.3Muse Spark 1.2, Human preference: 68.5Qwen3.6 Max, Reasoning: 62.7Qwen3.6 Max, Coding: 56.3Qwen3.6 Max, Agents & tools: 72.1Qwen3.6 Max, Maths: 64.7Qwen3.6 Max, Knowledge: 60.0Qwen3.6 Max, Long context: 65.2Qwen3.6 Max, Human preference: 64.6

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

ModelIndex

Where sources disagree

Across the 18 benchmarks both have, Muse Spark 1.2 leads 17, Qwen3.6 Max leads 1. Every overall index that rates both puts Muse Spark 1.2 ahead.

Overall indexMuse Spark 1.2 (xhigh)Qwen3.6 Max (max)Leader
BenchLeader Index61.662.4neck and neck
Arena Text14921460Muse 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.

MeasureMuse Spark 1.2 (xhigh)Qwen3.6 Max (max)
Blended price per 1M tokens$2.00$2.96
Input / output per 1M$1.25 / $4.25$1.32 / $7.90
Cached input per 1M$0.150$0.132
Price per task: chat reply$0.0018$0.0029
Price per task: summarize a 30-page report$0.018$0.021
Price per task: code edit$0.014$0.020
Price per task: agentic coding session$0.092$0.111
Price per task: structured extraction$0.0034$0.0042
Agentic coding session, input mostly cached$0.043$0.057
Output speed296 tok/s–
Time to first answer17.5 s–
Time to a complete answer19.2 s–

Each model is compared at its best-ranked reasoning-effort setting. Muse Spark 1.2 (xhigh) scores 61.6 and takes 18 s to its first answer token. Qwen3.6 Max (max) scores 62.4. 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

85 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 1.2 (xhigh)Qwen3.6 Max (max)
BenchLeader IndexBenchLeader61.662.4
Agents & tools scoreBenchLeader55.472.1
Coding scoreBenchLeader55.056.3
Human preference scoreBenchLeader68.564.6
Knowledge scoreBenchLeader64.760.0
Long context scoreBenchLeader64.365.2
Maths scoreBenchLeader67.364.7
Multimodal scoreBenchLeader65.2–
Reasoning scoreBenchLeader68.162.7
Instruction following scoreBenchLeader–74.6
Blended price $/MBenchLeader$2.00$2.96
Output speedBenchLeader296 tok/s–
Time to first answerBenchLeader17.5 s–
Context windowBenchLeader1,048,576 tokens245,800 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–87.4%
SimpleBenchSimpleBench74.5%†63.0%
Arena Hard PromptsArena (LMArena)15131482
LiveBench 1.0 ReasoningLiveBench90.0%–
GPQA Diamond (AA)Artificial Analysis90.4%88.8%
Humanity's Last Exam (AA)Artificial Analysis45.5%30.8%
CritPtArtificial Analysis17.7%3.7%
Chess PuzzlesEpoch AI Benchmarking Hub27.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub–19.0%†
LMCAEpoch AI Benchmarking Hub48.4%42.5%
DTBenchEpoch AI Benchmarking Hub94.7%87.2%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–76.7%
SciCodeSciCode57.4%–
WeirdMLWeirdML60.3%–
Arena CodingArena (LMArena)15431511
Arena WebDevArena (LMArena)15341482
LiveBench 1.0 CodingLiveBench77.5%–
IOIVals AI21.8%–
SWE-bench (Vals)Vals AI86.6%72.8%
Code MigrationVals AI29.9%–
ProgramBenchVals AI0.5%–
Vibe Code Bench v1.1Vals AI79.1%–
DeepSWE v1.1Epoch AI Benchmarking Hub54.9%–
FrontierSWEEpoch AI Benchmarking Hub12.0%–
Terminal-Bench 4.0 (AA)Artificial Analysis7.1%–
Show all 85 benchmarks
MetricPublisherMuse Spark 1.2 (xhigh)Qwen3.6 Max (max)
Coding
Terminal-Bench 2.1 (AA)Artificial Analysis80.2%–
Startrise FrontendStartrise70.3%†–
GameBench 2 OverallDuelLab GameBench 253.7†–
GameBench 2 by reasoning settingDuelLab GameBench 259.7–
Agents & tools
APEX-AgentsMercor45.4%†–
Arena AgentArena (LMArena)-7.5–
LiveBench Agentic CodingLiveBench57.6%–
Terminal-Bench HardArtificial Analysis–43.9%
τ²-Bench Telecom (AA)Artificial Analysis–95.9%
Terminal-Bench 2.1 (Vals)Vals AI69.7%–
τ³-Banking (AA)Artificial Analysis34.9%–
CyberBenchVals AI69.5%–
Finance Agent v2Vals AI60.6%–
Harvey's Legal Agent Benchmark v1Vals AI25.4%–
Legal Research BenchVals AI43.8%–
SkillsBenchVals AI53.0%–
SREBenchVals AI0.0%–
Tax Agent BenchVals AI32.8%–
Terminal-Bench 2.0 (Vals)Vals AI–51.7%
Terminal-Bench 4.0 (Vals)Vals AI6.1%–
Vending-Bench 2Andon Labs–4254.2
AutomationBenchArtificial Analysis40.6%–
GDP.pdf (AA)Artificial Analysis17.4%–
EnterpriseOps-GymArtificial Analysis47.3%–
AA-Briefcase v1.1Artificial Analysis1325–
Maths
OTIS Mock AIMEEpoch AI Benchmarking Hub–91.1%
ProofBenchVals AI43.0%†–
LiveBench MathematicsLiveBench91.2%–
Arena MathsArena (LMArena)14921476
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub60.3%52.0%
LiveBench 1.0 Data AnalysisLiveBench76.5%–
MMLU-ProVals AI88.3%–
LegalBenchVals AI85.3%–
CorpFinVals AI70.9%66.5%
TaxEvalVals AI80.4%–
BioMysteryBenchVals AI64.8%–
CaseLaw v2Vals AI–47.9%
Excel Modeling BenchmarkVals AI57.0%–
MedCodeVals AI49.4%–
MedScribeVals AI90.1%–
Public Benefits Bench v1.1Vals AI68.5%–
GDP.pdfEpoch AI Benchmarking Hub16.0%–
Instruction following
LiveBench LanguageLiveBench78.6%–
LiveBench Instruction FollowingLiveBench74.3%–
IFBenchArtificial Analysis–76.6%
Arena Instruction FollowingArena (LMArena)14751451
Human preference
Arena TextArena (LMArena)14921460
Arena Creative WritingArena (LMArena)14411437
Arena Multi-turnArena (LMArena)15081467
Arena Longer QueriesArena (LMArena)14891473
Multimodal
Arena VisionArena (LMArena)1304–
MMMU-Pro (Vals)Vals AI86.1%–
MortgageTaxVals AI65.4%–
Long context
AA-LCR v1.1Artificial Analysis79.0%80.7%
MLCRArtificial Analysis7.2%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub155.2†149.4
LiveBench 1.0LiveBench78.0%–
AA Intelligence Index v4.3.2Artificial Analysis39.628.4
AA Progress Index v1Artificial Analysis309.1297.1
Vals Multimodal IndexVals AI69.8%†–

Data as of 2026-11-02. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261026-cb69502a12d9 (https://benchmarks.duellab.org/releases/gb2-20261026-cb69502a12d9/), 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 1.2 (xhigh): 1 score revision.
  • Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.
  • Muse Spark 1.2 (xhigh): 1 new result (AA Progress Index v1).
  • Qwen3.6 Max (max): 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).
  • Muse Spark 1.2 (xhigh): cost per task moved from $0.97/M to $1.29/M (32% up).
  • Muse Spark 1.2 (xhigh): 1 new result (AA-Briefcase v1.1).
  • Muse Spark 1.2 (xhigh): 1 new result (Harvey's Legal Agent Benchmark v1).
  • Qwen3.6 Max (max): BenchLeader Index 63.3 → 62.8.
  • Muse Spark 1.2 (xhigh): 2 score revisions.

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

Muse Spark 1.2 vs Qwen3.6 Max: questions

Is Muse Spark 1.2 better than Qwen3.6 Max?
Muse Spark 1.2 (xhigh) and Qwen3.6 Max (max) are neck and neck on quality (61.6 vs 62.4, within the ±5.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2 Nov 2026, so check the category scores for your use.
Muse Spark 1.2 vs Qwen3.6 Max: which is cheaper, and will that change?
Muse Spark 1.2 is cheaper today: $2.00 against $2.92 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Muse Spark 1.2 or Qwen3.6 Max better for coding?
Qwen3.6 Max scores higher in coding (56 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1534 for Muse Spark 1.2 against 1482 for Qwen3.6 Max.
Is Muse Spark 1.2 or Qwen3.6 Max better for agents and tool use?
Qwen3.6 Max scores higher in agentic tasks (72 vs 55 on the category index, where 50 is average).
Which is better for long documents?
They are level on long-context benchmarks (64 vs 65). Muse Spark 1.2 accepts more context: 1,048,576 against 245,800 tokens for Qwen3.6 Max.
More questions (2)
Do independent benchmarks agree on Muse Spark 1.2 vs Qwen3.6 Max?
Across the 18 benchmarks both have, Muse Spark 1.2 leads 17, Qwen3.6 Max leads 1. 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.