BenchLeader

Claude Sonnet 4.6 vs Muse Spark Open 816B A42B

Full profiles: Claude Sonnet 4.6 (Anthropic) and Muse Spark Open 816B A42B (Meta): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Claude Sonnet 4.6 and Muse Spark Open 816B A42B are neck and neck on quality (57.6 vs 58.1 on the BenchLeader Index, inside the ±7.3 margin), and Muse Spark Open 816B A42B is 3.0× cheaper at $2.00 vs $6.00 per 1M tokens blended. Choose Claude Sonnet 4.6 for maths (63 vs 59); choose Muse Spark Open 816B A42B for coding (65 vs 54) and knowledge (62 vs 58).

Key facts (as of 16 Nov 2026)

  • Claude Sonnet 4.6 scores 57.6 on the BenchLeader Index and Muse Spark Open 816B A42B scores 58.1 (BenchLeader, 16 Nov 2026).
  • Claude Sonnet 4.6 costs $6.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Spark Open 816B A42B costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 2 benchmarks both models have, Muse Spark Open 816B A42B leads 2 (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
CodingMuse Spark Open 816B A42B65 vs 54 category scoreHigh
MathsClaude Sonnet 4.663 vs 59 category score; OTIS Mock AIME 85.8% vs 98.1%Medium
ReasoningEither64 vs 63 category score; GPQA Diamond 87.4% vs 88.6%Either
KnowledgeMuse Spark Open 816B A42B62 vs 58 category scoreMedium
Chat quality (human preference)–Only Claude Sonnet 4.6 has an Arena rating (61 category score)Not comparable
Lowest costMuse Spark Open 816B A42B$2.00 vs $6.00 per 1M blended; agentic coding session $0.092 vs $0.240–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Sonnet 4.6 and Muse Spark Open 816B A42B (xhigh) are neck and neck on quality (57.6 vs 58.1, within the ±7.3 margin).
  • Claude Sonnet 4.6 is stronger in maths, reasoning.
  • Muse Spark Open 816B A42B (xhigh) is stronger in coding, knowledge.
  • Muse Spark Open 816B A42B (xhigh) is 3.0× cheaper ($2.00 vs $6.00 per 1M blended).

At a glance

SpecClaude Sonnet 4.6Muse Spark Open 816B A42B
DeveloperAnthropicMeta
Released17 Feb 202615 Oct 2026
Context window (tokens)1,000,0001,048,576
Compared atClaude Sonnet 4.6Muse Spark Open 816B A42B (xhigh)
Open weightsNoYes
Price in / out / cached input per 1M$3.00 / $15.00 / $0.300$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.

CategoryClaude Sonnet 4.6Muse Spark Open 816B A42B (xhigh)Leader
Reasoning63.963.2level
Coding53.565.1Muse Spark Open 816B A42B
Agents & tools52.6–not comparable
Maths63.158.7Claude Sonnet 4.6
Knowledge58.161.5Muse Spark Open 816B A42B
Human preference60.5–not comparable
Multimodal62.4–not 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 avg75ReasoningCodingMathsKnowledgeClaude Sonnet 4.6, Reasoning: 63.9Claude Sonnet 4.6, Coding: 53.5Claude Sonnet 4.6, Maths: 63.1Claude Sonnet 4.6, Knowledge: 58.1Muse Spark Open 816B A42B, Reasoning: 63.2Muse Spark Open 816B A42B, Coding: 65.1Muse Spark Open 816B A42B, Maths: 58.7Muse Spark Open 816B A42B, Knowledge: 61.5

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

Model, click to add or removeIndex

Where sources disagree

Across the 2 benchmarks both have, Claude Sonnet 4.6 leads 0, Muse Spark Open 816B A42B leads 2.

Overall indexClaude Sonnet 4.6Muse Spark Open 816B A42B (xhigh)Leader
BenchLeader Index57.658.1neck and neck

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.

MeasureClaude Sonnet 4.6Muse Spark Open 816B A42B (xhigh)
Blended price per 1M tokens$6.00$2.00
Input / output per 1M$3.00 / $15.00$1.25 / $4.25
Cached input per 1M$0.300$0.150
Price per task: chat reply$0.0057$0.0018
Price per task: summarize a 30-page report$0.045$0.018
Price per task: code edit$0.041$0.014
Price per task: agentic coding session$0.240$0.092
Price per task: structured extraction$0.0090$0.0034
Agentic coding session, input mostly cached$0.118$0.043
Output speed43 tok/s–
Time to first answer0.6 s–

Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 4.6 scores 57.6 and takes 1 s to its first answer token; Claude Sonnet 4.6 (max) scores 56.1 in 91 s, Claude Sonnet 4.6 (high) scores 50.3 in 1 s. Muse Spark Open 816B A42B (xhigh) scores 58.1. 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

108 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.

MetricPublisherClaude Sonnet 4.6Muse Spark Open 816B A42B (xhigh)
BenchLeader IndexBenchLeader57.658.1
Agents & tools scoreBenchLeader52.6–
Coding scoreBenchLeader53.565.1
Human preference scoreBenchLeader60.5–
Knowledge scoreBenchLeader58.161.5
Maths scoreBenchLeader63.158.7
Multimodal scoreBenchLeader62.4–
Reasoning scoreBenchLeader63.963.2
Blended price $/MBenchLeader$6.00$2.00
Output speedBenchLeader43 tok/s–
Time to first answerBenchLeader0.6 s–
Context windowBenchLeader1,000,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub87.4%88.6%
Arena Hard PromptsArena (LMArena)1503–
LiveBench 1.0 ReasoningLiveBench84.8%†–
GPQA Diamond (AA)Artificial Analysis87.5%†–
Humanity's Last Exam (AA)Artificial Analysis33.6%†–
GPQA Diamond (Vals)Vals AI85.6%†–
ARC-AGI-1ARC Prize86.0%†–
ARC-AGI-2ARC Prize58.3%†–
CritPtArtificial Analysis3.1%†–
Arena ExpertArena (LMArena)1506–
Chess PuzzlesEpoch AI Benchmarking Hub23.0%†–
Mystery Game PuzzlesEpoch AI Benchmarking Hub14.0%–
LMCAEpoch AI Benchmarking Hub46.5%†–
DTBenchEpoch AI Benchmarking Hub89.9%†–
ForecastBenchForecastBench64.0%–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub75.2%–
SciCodeSciCode46.8%†58.5%
WeirdMLWeirdML66.1%†–
FrontierCodeCognition24.3%–
Arena CodingArena (LMArena)1528–
Arena WebDevArena (LMArena)1522–
LiveBench 1.0 CodingLiveBench79.3%†–
SciCode (AA)Artificial Analysis50.1%†–
LiveCodeBenchVals AI82.1%†–
SWE-bench (Vals)Vals AI77.4%†–
Show all 108 benchmarks
MetricPublisherClaude Sonnet 4.6Muse Spark Open 816B A42B (xhigh)
Coding
Code MigrationVals AI39.9%†–
ProgramBenchVals AI0.5%†–
Vibe Code Bench v1.1Vals AI55.8%–
SWE Atlas v1.0: Codebase QnAScale AI SEAL31.2%–
SWE Atlas v1.0: RefactoringScale AI SEAL32.2%–
SWE Atlas v1.0: Test WritingScale AI SEAL31.8%–
DeepSWE v1.1Epoch AI Benchmarking Hub29.9%†–
ALE-BenchEpoch AI Benchmarking Hub1327.3†1590.1
Terminal-Bench 4.0 (AA)Artificial Analysis3.0%†–
Terminal-Bench 2.1 (AA)Artificial Analysis71.2%†–
Design Arena WebsiteDesign Arena1277–
Agents & tools
Terminal-BenchTerminal-Bench53.4%–
OSWorld-Verified 2.0OSWorld8.3%†–
APEX-AgentsMercor43.0%†33.4%†
LiveBench Agentic CodingLiveBench42.6%†–
Terminal-Bench HardArtificial Analysis53.0%†–
τ²-Bench Telecom (AA)Artificial Analysis75.7%†–
Terminal-Bench 2.1 (Vals)Vals AI57.3%†–
MCP AtlasScale AI SEAL69.5%–
GDPval-AA v2.1Artificial Analysis1240†–
τ³-Banking (AA)Artificial Analysis34.4%†–
ITBench SRE (AA)Artificial Analysis39.8%†–
Analyst Agent (AA)Artificial Analysis20.0%†–
APEX-Agents (AA)Artificial Analysis28.0%†–
Finance Agent v2Vals AI51.0%†–
Harvey's Legal Agent Benchmark v1Vals AI5.0%†–
Legal Research BenchVals AI38.5%†–
SkillsBenchVals AI49.0%†–
Tax Agent BenchVals AI25.8%†–
Terminal-Bench 2.0 (Vals)Vals AI59.5%†–
Arena SearchArena (LMArena)1201–
DeepResearch BenchDeepResearch Bench54.9%†–
ExploitBenchEpoch AI Benchmarking Hub23.6%–
GBAEvalEpoch AI Benchmarking Hub48.8%–
Vending-Bench 2Andon Labs7204.1–
AutomationBenchArtificial Analysis20.1%†–
GDP.pdf (AA)Artificial Analysis15.8%†–
AA-Briefcase v1.1Artificial Analysis1062†–
Design Arena AgenticDesign Arena1187–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–69.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub–31.7%
OTIS Mock AIMEEpoch AI Benchmarking Hub85.8%98.1%
ProofBenchVals AI45.0%†–
LiveBench MathematicsLiveBench87.0%†–
AIME (Vals)Vals AI92.3%–
Arena MathsArena (LMArena)1461–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub32.8%†56.6%
LiveBench 1.0 Data AnalysisLiveBench78.0%†–
MMLU-ProVals AI87.3%†–
LegalBenchVals AI82.1%†–
CorpFinVals AI65.3%†–
TaxEvalVals AI77.1%†–
MedQAVals AI92.1%–
CaseLaw v2Vals AI64.0%–
Excel Modeling BenchmarkVals AI60.1%†–
Public Benefits Bench v1.1Vals AI62.5%†–
DrugDiscoveryBenchScale AI SEAL31.3%†–
GDP.pdfEpoch AI Benchmarking Hub18.0%†–
Global-MMLU-Lite (AA)Artificial Analysis90.5%†–
Instruction following
LiveBench LanguageLiveBench76.1%†–
LiveBench Instruction FollowingLiveBench63.2%†–
IFBenchArtificial Analysis56.6%†–
Arena Instruction FollowingArena (LMArena)1475–
Human preference
Arena TextArena (LMArena)1472–
EQ-Bench 4EQ-Bench1197–
EQ-Bench Creative Writing v3EQ-Bench1811–
Arena Creative WritingArena (LMArena)1449–
Arena Multi-turnArena (LMArena)1480–
Arena Longer QueriesArena (LMArena)1492–
Multimodal
Arena VisionArena (LMArena)1283–
MMMU-ProArtificial Analysis73.3%†–
MMMU-Pro (Vals)Vals AI83.6%†–
MortgageTaxVals AI67.7%†–
GeoBenchGeoBench73.0%–
Blueprint-Bench 2Epoch AI Benchmarking Hub6.7%–
Long context
AA-LCR v1.1Artificial Analysis80.0%†–
Arena DocumentArena (LMArena)1478–
MLCRArtificial Analysis7.8%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub152.9–
LiveBench 1.0LiveBench73.0%†–
AA Intelligence Index v4.3.2Artificial Analysis30.1†–
AA Progress Index v1Artificial Analysis293.6†–
Vals Multimodal IndexVals AI60.6%†–

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

What changed

  • Claude Sonnet 4.6: BenchLeader Index 58.3 → 57.6.
  • Claude Sonnet 4.6: 2 score revisions.
  • Muse Spark Open 816B A42B (xhigh): BenchLeader Index 58.6 → 58.1.
  • Claude Sonnet 4.6: 1 new result (GeoBench).
  • Claude Sonnet 4.6: 1 new result (Arena Search).
  • Claude Sonnet 4.6: BenchLeader Index 57.1 → 58.3.
  • Claude Sonnet 4.6: 1 score revision.
  • Claude Sonnet 4.6: 1 new result (Harvey's Legal Agent Benchmark v1).
  • Claude Sonnet 4.6: 1 score revision.
  • Claude Sonnet 4.6: BenchLeader Index 58.9 → 57.1.

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

Claude Sonnet 4.6 vs Muse Spark Open 816B A42B: questions

Is Claude Sonnet 4.6 better than Muse Spark Open 816B A42B?
Claude Sonnet 4.6 and Muse Spark Open 816B A42B (xhigh) are neck and neck on quality (57.6 vs 58.1, within the ±7.3 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.
Claude Sonnet 4.6 vs Muse Spark Open 816B A42B: which is cheaper, and will that change?
Muse Spark Open 816B A42B is cheaper today: $2.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Sonnet 4.6 or Muse Spark Open 816B A42B better for coding?
Muse Spark Open 816B A42B scores higher in coding (65 vs 54 on the category index, where 50 is average).
Which is better for long documents?
Both take about 1M tokens: Claude Sonnet 4.6 1,000,000, Muse Spark Open 816B A42B 1,048,576.
Do independent benchmarks agree on Claude Sonnet 4.6 vs Muse Spark Open 816B A42B?
Across the 2 benchmarks both have, Claude Sonnet 4.6 leads 0, Muse Spark Open 816B A42B leads 2.
More questions (1)
When was Muse Spark Open 816B A42B released?
Muse Spark Open 816B A42B was released on 15 Oct 2026.