BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Fable 5.2 vs Muse Spark Open 816B A42B

Full profiles: Claude Fable 5.2 (Anthropic) and Muse Spark Open 816B A42B (Meta): every benchmark, price and rank.

Updated · Data from 5 sources

As of 9 Nov 2026, Claude Fable 5.2 is ahead of Muse Spark Open 816B A42B on quality (69.4 vs 58.5 on the BenchLeader Index), but Muse Spark Open 816B A42B is 8.0× cheaper at $2.00 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in.

Key facts (as of 9 Nov 2026)

  • Claude Fable 5.2 scores 69.4 on the BenchLeader Index and Muse Spark Open 816B A42B scores 58.5 (BenchLeader, 9 Nov 2026).
  • Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Muse Spark Open 816B A42B costs $2.00 per 1M tokens blended (list price, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic Muse Spark Open 816B A42B benchmarks xhigh 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
CodingClaude Fable 5.280 vs 66 category scoreHigh
ReasoningClaude Fable 5.278 vs 63 category scoreHigh
KnowledgeClaude Fable 5.282 vs 63 category scoreHigh
Lowest costMuse Spark Open 816B A42B$2.00 vs $16.00 per 1M blended; agentic coding session $0.092 vs $0.640–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Fable 5.2 (max) leads on quality: 69.4 vs 58.5.
  • Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
  • Muse Spark Open 816B A42B (xhigh) is stronger in maths.
  • Muse Spark Open 816B A42B (xhigh) is 8.0× cheaper ($2.00 vs $16.00 per 1M blended).

At a glance

SpecClaude Fable 5.2Muse Spark Open 816B A42B
DeveloperAnthropicMeta
Released9 Nov 202615 Oct 2026
Context window (tokens)1,000,0001,048,576
Compared atClaude Fable 5.2 (max)Muse Spark Open 816B A42B (xhigh)
Open weightsNoYes
Price in / out / cached input per 1M$8.00 / $40.00 / $0.200$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 Fable 5.2 (max)Muse Spark Open 816B A42B (xhigh)Leader
Reasoning78.463.3Claude Fable 5.2
Coding80.265.6Claude Fable 5.2
Maths–59.2not comparable
Knowledge81.762.8Claude Fable 5.2
Long context66.4–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 avg75ReasoningCodingKnowledgeClaude Fable 5.2, Reasoning: 78.4Claude Fable 5.2, Coding: 80.2Claude Fable 5.2, Knowledge: 81.7Muse Spark Open 816B A42B, Reasoning: 63.3Muse Spark Open 816B A42B, Coding: 65.6Muse Spark Open 816B A42B, Knowledge: 62.8

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

ModelIndex

Where sources disagree

Across the 0 benchmarks both have, Claude Fable 5.2 leads 0, Muse Spark Open 816B A42B leads 0. Every overall index that rates both puts Claude Fable 5.2 ahead.

Overall indexClaude Fable 5.2 (max)Muse Spark Open 816B A42B (xhigh)Leader
BenchLeader Index69.458.5Claude Fable 5.2

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.

MeasureClaude Fable 5.2 (max)Muse Spark Open 816B A42B (xhigh)
Blended price per 1M tokens$16.00$2.00
Input / output per 1M$8.00 / $40.00$1.25 / $4.25
Cached input per 1M$0.200$0.150
Price per task: chat reply$0.015$0.0018
Price per task: summarize a 30-page report$0.120$0.018
Price per task: code edit$0.108$0.014
Price per task: agentic coding session$0.640$0.092
Price per task: structured extraction$0.024$0.0034
Agentic coding session, input mostly cached$0.289$0.043
Cost per benchmark task (AA Index)$26.54–
Output tokens per task (AA Index)274k–
Of which reasoning193k–
Output speed72 tok/s–
Time to first answer3.0 s–

Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.2 (max) scores 69.4 and takes 3 s to its first answer token; Claude Fable 5.2 (high) scores 68.9 in 3 s, Claude Fable 5.2 (xhigh) scores 68.7 in 3 s. Muse Spark Open 816B A42B (xhigh) scores 58.5. 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

56 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 Fable 5.2 (max)Muse Spark Open 816B A42B (xhigh)
BenchLeader IndexBenchLeader69.458.5
Coding scoreBenchLeader80.265.6
Knowledge scoreBenchLeader81.762.8
Long context scoreBenchLeader66.4–
Reasoning scoreBenchLeader78.463.3
Maths scoreBenchLeader–59.2
Blended price $/MBenchLeader$16.00$2.00
Output speedBenchLeader72 tok/s–
Time to first answerBenchLeader3.0 s–
Context windowBenchLeader1,000,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–88.6%
LiveBench 2.0 ReasoningLiveBench88.8%†–
Humanity's Last Exam (AA)Artificial Analysis74.3%–
HLE-Diamond (AA)Artificial Analysis80.2%–
ARC-AGI-1ARC Prize97.5%–
ARC-AGI-2ARC Prize92.5%–
ARC-AGI-3ARC Prize94.9%–
CritPtArtificial Analysis35.4%–
CritPt v2 hard subset (AA)Artificial Analysis76.5%–
MysteryMechanismVals AI51.8%†–
Coding
SciCodeSciCode–58.5%
LiveBench 2.0 CodingLiveBench79.2%†–
SciCode (AA)Artificial Analysis67.7%–
Code Migration v1.1Vals AI83.3%†–
ProgramBenchVals AI19.0%†–
SWE-bench MultimodalVals AI62.3%†–
Vibe Code Bench v1.1Vals AI93.8%†–
ALE-BenchEpoch AI Benchmarking Hub–1590.1
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%–
FrontierCode 1.1 (AA)Artificial Analysis56.2%–
FrontierCode 2.0 (AA)Artificial Analysis48.8%–
Agents & tools
APEX-AgentsMercor–33.4%†
LiveBench Long AgenticLiveBench82.9%†–
LiveBench BrowserLiveBench86.9%†–
GDPval-AA v2.1Artificial Analysis1831–
Show all 56 benchmarks
MetricPublisherClaude Fable 5.2 (max)Muse Spark Open 816B A42B (xhigh)
Agents & tools
Finance Agent v2.1Vals AI69.5%†–
Harvey's Legal Agent Benchmark v1.1Vals AI5.0%†–
Legal Research BenchVals AI46.1%†–
Tax Agent BenchVals AI32.1%†–
Terminal-Bench 4.0 (Vals)Vals AI65.2%†–
Terminal-Bench ScienceVals AI55.7%†–
AutomationBenchArtificial Analysis76.4%–
GDP.pdf (AA)Artificial Analysis24.2%–
Harvey LAB-AA v1.1Harvey7.2%–
AA-Briefcase v1.1Artificial Analysis1785–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis73.3%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–69.8%
FrontierMath Tier 4Epoch AI Benchmarking Hub–31.7%
OTIS Mock AIMEEpoch AI Benchmarking Hub–98.1%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–56.6%
LiveBench 2.0 Data AnalysisLiveBench81.5%†–
LiveBench ResearchLiveBench94.5%†–
AA-Omniscience v1.1Artificial Analysis66.8–
BioMysteryBenchVals AI83.7%†–
Excel Modeling Benchmark v1.1Vals AI77.4%†–
AA-Omniscience v1.1: accuracyArtificial Analysis79.1%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.7%–
HealthBench Professional (AA)OpenAI67.7%–
Multimodal
LiveBench DesignLiveBench85.1%†–
AA-3DArtificial Analysis1271–
Long context
AA-LCR v1.1Artificial Analysis83.3%–
Composite
LiveBench 2.0LiveBench84.9%†–
AA Intelligence Index v5.0Artificial Analysis64.6–
Vals IndexVals AI71.3†–
Vals Finance IndexVals AI63.6%†–
Vals Science IndexVals AI63.7%†–

Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Muse Spark Open 816B A42B (xhigh): BenchLeader Index 57.4 → 58.6.
  • Muse Spark Open 816B A42B (xhigh): 2 new results (SciCode, ALE-Bench).
  • Muse Spark Open 816B A42B (xhigh): first results.

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

Claude Fable 5.2 vs Muse Spark Open 816B A42B: questions

Is Claude Fable 5.2 better than Muse Spark Open 816B A42B?
Claude Fable 5.2 (max) leads on quality: 69.4 vs 58.5. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.2 (max) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
Claude Fable 5.2 vs Muse Spark Open 816B A42B: which is cheaper, and will that change?
Muse Spark Open 816B A42B is cheaper today: $2.00 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Fable 5.2 or Muse Spark Open 816B A42B better for coding?
Claude Fable 5.2 scores higher in coding (80 vs 66 on the category index, where 50 is average).
Which is better for long documents?
Both take about 1M tokens: Claude Fable 5.2 1,000,000, Muse Spark Open 816B A42B 1,048,576.
When was Claude Fable 5.2 released?
Claude Fable 5.2 was released on 9 Nov 2026.