BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Fable 5.2 vs Kimi K2.6

Full profiles: Claude Fable 5.2 (Anthropic) and Kimi K2.6 (Moonshot AI): every benchmark, price and rank.

Updated · Data from 6 sources

As of 9 Nov 2026, Claude Fable 5.2 is ahead of Kimi K2.6 on quality (69.4 vs 59.8 on the BenchLeader Index), but Kimi K2.6 is 9.3× cheaper at $1.71 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in. Claude Fable 5.2 streams ~1.5× faster.

Key facts (as of 9 Nov 2026)

  • Claude Fable 5.2 scores 69.4 on the BenchLeader Index and Kimi K2.6 scores 59.8 (BenchLeader, 9 Nov 2026).
  • Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Kimi K2.6 costs $1.71 per 1M tokens blended (list price, 9 Nov 2026).
  • Claude Fable 5.2 streams ~1.5× faster than Kimi K2.6 (Artificial Analysis, 7-day median, 9 Nov 2026).
  • Of the 7 benchmarks both models have, Claude Fable 5.2 leads 7 (BenchLeader, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic Kimi K2.6 benchmarks thinking Moonshot AIAdd 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
Long documentsClaude Fable 5.266 vs 65 category score; AA-LCR v1.1 83.3% vs 81.0%Medium
Lowest costKimi K2.6$1.71 vs $16.00 per 1M blended; agentic coding session $0.073 vs $0.640–
Fastest first answerClaude Fable 5.23.0 s (Claude Fable 5.2 (max)) vs 75.2 s (Kimi K2.6 (thinking)) 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

  • Claude Fable 5.2 (max) leads on quality: 69.4 vs 59.8.
  • Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
  • Kimi K2.6 (thinking) is stronger in agents & tools, instruction following, maths, multimodal.
  • Kimi K2.6 (thinking) is 9.3× cheaper ($1.71 vs $16.00 per 1M blended).
  • Claude Fable 5.2 (max) streams 2.0× faster (72 vs 37 tokens per second).

At a glance

SpecClaude Fable 5.2Kimi K2.6
DeveloperAnthropicMoonshot AI
Released9 Nov 202620 Apr 2026
Context window (tokens)1,000,000262,144
Compared atClaude Fable 5.2 (max)Kimi K2.6 (thinking)
Open weightsNoYes
Price in / out / cached input per 1M$8.00 / $40.00 / $0.200$0.950 / $4.00 / $0.160

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)Kimi K2.6 (thinking)Leader
Reasoning78.4–not comparable
Coding80.2–not comparable
Agents & tools–58.4not comparable
Maths–57.6not comparable
Knowledge81.7–not comparable
Instruction following–74.1not comparable
Multimodal–61.8not comparable
Long context66.465.2Claude Fable 5.2

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 & toolsMathsKnowledgeInstructionfollowingLong contextMultimodalClaude Fable 5.2, Reasoning: 78.4Claude Fable 5.2, Coding: 80.2Claude Fable 5.2, Knowledge: 81.7Claude Fable 5.2, Long context: 66.4Kimi K2.6, Agents & tools: 58.4Kimi K2.6, Maths: 57.6Kimi K2.6, Instruction following: 74.1Kimi K2.6, Long context: 65.2Kimi K2.6, Multimodal: 61.8

Dashed: that model has no result on the axis it crosses; the line only joins its neighbours.

Not drawn, no result for these models: Human preference.

ModelIndex

Where sources disagree

Across the 7 benchmarks both have, Claude Fable 5.2 leads 7, Kimi K2.6 leads 0. Every overall index that rates both puts Claude Fable 5.2 ahead.

Overall indexClaude Fable 5.2 (max)Kimi K2.6 (thinking)Leader
BenchLeader Index69.459.8Claude 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)Kimi K2.6 (thinking)
Blended price per 1M tokens$16.00$1.71
Input / output per 1M$8.00 / $40.00$0.950 / $4.00
Cached input per 1M$0.200$0.160
Price per task: chat reply$0.015$0.0016
Price per task: summarize a 30-page report$0.120$0.014
Price per task: code edit$0.108$0.012
Price per task: agentic coding session$0.640$0.073
Price per task: structured extraction$0.024$0.0027
Agentic coding session, input mostly cached$0.289$0.037
Cost per benchmark task (AA Index)$26.54–
Output tokens per task (AA Index)274k–
Of which reasoning193k–
Output speed72 tok/s37 tok/s
Time to first answer3.0 s75.2 s
Time to a complete answer–196.2 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. Kimi K2.6 (thinking) scores 59.8 and takes 75 s to its first answer token; Kimi K2.6 scores 55.2 in 1 s. 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

130 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)Kimi K2.6 (thinking)
BenchLeader IndexBenchLeader69.459.8
Coding scoreBenchLeader80.2–
Knowledge scoreBenchLeader81.7–
Long context scoreBenchLeader66.465.2
Reasoning scoreBenchLeader78.4–
Agents & tools scoreBenchLeader–58.4
Instruction following scoreBenchLeader–74.1
Maths scoreBenchLeader–57.6
Multimodal scoreBenchLeader–61.8
Blended price $/MBenchLeader$16.00$1.71
Output speedBenchLeader72 tok/s37 tok/s
Time to first answerBenchLeader3.0 s75.2 s
Context windowBenchLeader1,000,000 tokens262,144 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–90.8%†
Arena Hard PromptsArena (LMArena)–1485†
LiveBench 2.0 ReasoningLiveBench88.8%†–
LiveBench 1.0 ReasoningLiveBench–79.4%
GPQA Diamond (AA)Artificial Analysis–91.1%
Humanity's Last Exam (AA)Artificial Analysis74.3%37.5%
HLE-Diamond (AA)Artificial Analysis80.2%–
GPQA Diamond (Vals)Vals AI–89.1%†
ARC-AGI-1ARC Prize97.5%–
ARC-AGI-2ARC Prize92.5%–
ARC-AGI-3ARC Prize94.9%–
CritPtArtificial Analysis35.4%8.0%
CritPt v2 hard subset (AA)Artificial Analysis76.5%–
MysteryMechanismVals AI51.8%†–
Chess PuzzlesEpoch AI Benchmarking Hub–20.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub–18.0%†
LMCAEpoch AI Benchmarking Hub–37.3%†
DTBenchEpoch AI Benchmarking Hub–90.9%†
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–76.7%†
SciCodeSciCode–53.5%†
WeirdMLWeirdML–55.9%†
Arena CodingArena (LMArena)–1516†
Arena WebDevArena (LMArena)–1509†
LiveBench 2.0 CodingLiveBench79.2%†–
LiveBench 1.0 CodingLiveBench–78.6%
Show all 130 benchmarks
MetricPublisherClaude Fable 5.2 (max)Kimi K2.6 (thinking)
Coding
SciCode (AA)Artificial Analysis67.7%51.5%
LiveCodeBenchVals AI–86.8%†
SWE-bench (Vals)Vals AI–76.2%†
Code MigrationVals AI–27.8%†
Code Migration v1.1Vals AI83.3%†–
ProgramBenchVals AI19.0%†0.0%†
SWE-bench MultimodalVals AI62.3%†–
Vibe Code Bench v1.1Vals AI93.8%†37.9%†
ALE-BenchEpoch AI Benchmarking Hub–1092.7†
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%0.5%
Terminal-Bench 2.1 (AA)Artificial Analysis–65.9%
Design Arena WebsiteDesign Arena–1265†
FrontierCode 1.1 (AA)Artificial Analysis56.2%–
FrontierCode 2.0 (AA)Artificial Analysis48.8%–
Agents & tools
OSWorld-Verified 2.0OSWorld–4.6%†
LiveBench Long AgenticLiveBench82.9%†–
LiveBench BrowserLiveBench86.9%†–
LiveBench Agentic CodingLiveBench–46.9%
Terminal-Bench HardArtificial Analysis–43.9%
τ²-Bench Telecom (AA)Artificial Analysis–95.9%
Terminal-Bench 2.1 (Vals)Vals AI–53.6%†
HiL-BenchScale AI SEAL–18.7%†
GDPval-AA v2.1Artificial Analysis1831–
τ³-Banking (AA)Artificial Analysis–23.3%
ITBench SRE (AA)Artificial Analysis–31.2%
APEX-Agents (AA)Artificial Analysis–28.5%
Finance Agent v2Vals AI–44.9%†
Finance Agent v2.1Vals AI69.5%†–
Harvey's Legal Agent Benchmark v1.1Vals AI5.0%†–
Harvey's Legal Agent Benchmark v1Vals AI–1.7%†
Legal Research BenchVals AI46.1%†15.9%†
Tax Agent BenchVals AI32.1%†12.4%†
Terminal-Bench 2.0 (Vals)Vals AI–57.3%†
Terminal-Bench 4.0 (Vals)Vals AI65.2%†–
Terminal-Bench ScienceVals AI55.7%†–
ExploitBenchEpoch AI Benchmarking Hub–18.4%†
GBAEvalEpoch AI Benchmarking Hub–0.9%†
Vending-Bench 2Andon Labs–6204.6†
AutomationBenchArtificial Analysis76.4%13.0%
GDP.pdf (AA)Artificial Analysis24.2%13.0%
Harvey LAB-AA v1.1Harvey7.2%–
EnterpriseOps-GymArtificial Analysis–38.5%
AA-Briefcase v1.1Artificial Analysis1785–
Design Arena AgenticDesign Arena–1153†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis73.3%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–57.2%†
FrontierMath Tier 4Epoch AI Benchmarking Hub–25.6%†
OTIS Mock AIMEEpoch AI Benchmarking Hub–96.1%†
ProofBenchVals AI–16.0%†
LiveBench MathematicsLiveBench–84.3%
AIME 2026MathArena–95.8%
HMMT February 2026MathArena–94.7%
USAMO 2026MathArena–51.2%
MathArena ApexMathArena–24.0%
Arena MathsArena (LMArena)–1479†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–34.9%†
LiveBench 2.0 Data AnalysisLiveBench81.5%†–
LiveBench ResearchLiveBench94.5%†–
LiveBench 1.0 Data AnalysisLiveBench–65.1%
AA-Omniscience v1.1Artificial Analysis66.8–
MMLU-ProVals AI–87.6%†
LegalBenchVals AI–84.7%†
CorpFinVals AI–66.7%†
TaxEvalVals AI–74.7%†
BioMysteryBenchVals AI83.7%†–
CaseLaw v2Vals AI–61.2%†
Excel Modeling BenchmarkVals AI–57.9%†
Excel Modeling Benchmark v1.1Vals AI77.4%†–
MedCodeVals AI–40.1%†
MedScribeVals AI–78.2%†
Public Benefits Bench v1.1Vals AI–56.6%†
EBR-benchEpoch AI Benchmarking Hub–2.4%†
GDP.pdfEpoch AI Benchmarking Hub–12.0%†
AA-Omniscience v1.1: accuracyArtificial Analysis79.1%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.7%–
HealthBench Professional (AA)OpenAI67.7%–
Instruction following
LiveBench LanguageLiveBench–75.1%
LiveBench Instruction FollowingLiveBench–64.4%
IFBenchArtificial Analysis–76.0%
Arena Instruction FollowingArena (LMArena)–1456†
Human preference
Arena TextArena (LMArena)–1461†
EQ-Bench 4EQ-Bench–1191†
Arena Creative WritingArena (LMArena)–1432†
Arena Multi-turnArena (LMArena)–1462†
Arena Longer QueriesArena (LMArena)–1478†
Multimodal
Arena VisionArena (LMArena)–1282†
LiveBench DesignLiveBench85.1%†–
MMMU-ProArtificial Analysis–79.4%
MMMU-Pro (Vals)Vals AI–86.3%†
MortgageTaxVals AI–65.8%†
Blueprint-Bench 2Epoch AI Benchmarking Hub–3.9%†
AA-3DArtificial Analysis1271–
Long context
AA-LCR v1.1Artificial Analysis83.3%81.0%
Arena DocumentArena (LMArena)–1450†
MLCRArtificial Analysis–11.1%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–151.6†
LiveBench 2.0LiveBench84.9%†–
LiveBench 1.0LiveBench–70.5%
AA Intelligence Index v5.0Artificial Analysis64.6–
AA Intelligence Index v4.3.2Artificial Analysis–27.0
AA Progress Index v1Artificial Analysis–284.4
Vals IndexVals AI71.3†–
Vals Finance IndexVals AI63.6%†–
Vals Science IndexVals AI63.7%†–
Vals Multimodal IndexVals AI–56.4%†

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

What changed

  • Kimi K2.6 (thinking): BenchLeader Index 60.3 → 59.8.
  • Kimi K2.6 (thinking): 1 new result (AA Progress Index v1).
  • Kimi K2.6 (thinking): cost per task moved from $0.80/M to $0.71/M (12% down).
  • Kimi K2.6 (thinking): 1 new result (MLCR).
  • Kimi K2.6 (thinking): 4 new results (USAMO 2026, AutomationBench, GDP.pdf (AA)…).

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

Claude Fable 5.2 vs Kimi K2.6: questions

Is Claude Fable 5.2 better than Kimi K2.6?
Claude Fable 5.2 (max) leads on quality: 69.4 vs 59.8. 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 Kimi K2.6: which is cheaper, and will that change?
Kimi K2.6 is cheaper today: $1.71 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Which is faster, Claude Fable 5.2 or Kimi K2.6?
Claude Fable 5.2 streams ~1.5× faster (72 vs 37 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Claude Fable 5.2 scores higher on long-context benchmarks (66 vs 65). Claude Fable 5.2 accepts more context: 1,000,000 against 262,144 tokens for Kimi K2.6.
Which has lower latency?
Claude Fable 5.2 answers first: 3.0 s against 75.2 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.
More questions (2)
Do independent benchmarks agree on Claude Fable 5.2 vs Kimi K2.6?
Across the 7 benchmarks both have, Claude Fable 5.2 leads 7, Kimi K2.6 leads 0. Every overall index that rates both puts Claude Fable 5.2 ahead.
When was Claude Fable 5.2 released?
Claude Fable 5.2 was released on 9 Nov 2026.