Enter opens the highlighted result. Esc closes.

Claude Fable 5.2 vs Kimi K3

Claude Fable 5.2 leads Kimi K3 on coding, 87.8 to 61.4 on the Vibe Coding Index, and Kimi K3 costs 2.7x less per output token ($15.00 vs $40.00 per million). Updated November 14, 2026; 59 benchmarks have a result for both.

Replace Claude Fable 5.2 Replace Kimi K3
Claude Fable 5.2Anthropic
Coding
87.8
Overall
91.7
Output $/M
$40.00
54
Kimi K3Moonshot AI
Coding
61.4
Overall
61.2
Output $/M
$15.00
4
vs boards won of 59 shared, 1 tied

Claude Fable 5.2 or Kimi K3: which to pick

Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 61.4 for Kimi K3, though on 4 benchmarks against 6.

Pick Kimi K3 for output tokens 2.7x cheaper ($15.00 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).

Model AClaude Fable 5.2Anthropic87.8/1004 independent benchmarksNo cost per solved taskModel BKimi K3Moonshot AI61.4/1006 independent benchmarks$0.81 per solved task
Shared results
59
Claude Fable 5.2 only
9
Kimi K3 only
74
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Fable 5.2 87.8 from 4 benchmarks, Kimi K3 61.4 from 6 benchmarks.
Widest category
Knowledge, 38.8 points apart on average over 2 shared benchmarks.
Widest single gap
Mystery game puzzles: Claude Fable 5.2 90.0% against Kimi K3 26.0%, 64.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5.2 $40.00 against Kimi K3 $15.00 per million output tokens, 2.7x apart.
Context window
Claude Fable 5.2 takes 1M tokens, Kimi K3 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Fable 5.2BarsKimi K3Ties
Coding140
Intelligence20
Agentic work921 tie
Reasoning101
Math50
Knowledge20
Web design60
General61
All shared boards5441 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index140
Coding benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
LiveBench coding79.2%53.1%Claude Fable 5.2
LMArena WebDev18381658Claude Fable 5.2
AA Coding IndexNot measured72.0Only Kimi K3 measured
LiveCodeBench (Vals AI)Not measured87.2%Only Kimi K3 measured
SWE-bench Verified (Vals AI)Not measured93.4%Only Kimi K3 measured
Terminal-Bench 4 (Vals AI)65.2%17.2%Claude Fable 5.2
Vibe Code Bench (Vals AI)93.8%85.0%Claude Fable 5.2
Code migration (Vals AI)Not measured16.1%Only Kimi K3 measured
ProgramBench (Vals AI)19.0%2.0%Claude Fable 5.2
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)Not measured80.9%Only Kimi K3 measured
SWE-bench Multimodal (Vals AI)62.3%44.2%Claude Fable 5.2
Vibe Code Bench 1-100 (Vals AI)Not measured18.2%Only Kimi K3 measured
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCode67.7%59.5%Claude Fable 5.2
Terminal-Bench 4.0 (Artificial Analysis run)61.6%12.6%Claude Fable 5.2
FrontierCode 2.049.1%10.9%Claude Fable 5.2
FrontierCodeNot measured44.2%Only Kimi K3 measured
FrontierSWE69.9%25.9%Claude Fable 5.2
WeirdMLNot measured82.6%Only Kimi K3 measured
MirrorCodeNot measured54.4%Only Kimi K3 measured
ALE-Bench2509.81524.5Claude Fable 5.2
LMArena Text: codingNot measured1506Only Kimi K3 measured
LMArena Text: software and ITNot measured1497Only Kimi K3 measured
LMArena WebDev: React19151672Claude Fable 5.2
LMArena WebDev: HTML17381640Claude Fable 5.2
LMArena WebDev: from an imageNot measured1586Only Kimi K3 measured
SWE-Bench Pro V2Not measured97.7%Only Kimi K3 measured
GameBench 299.149.8Claude Fable 5.2
Terminal-Bench 4.0Not measured22.4%Only Kimi K3 measured
CursorBench 4.060.0%Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
AA Intelligence Index64.617.4Claude Fable 5.2
Epoch Capabilities Index173.4158.6Claude Fable 5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index92
Agentic work benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
AA Agentic IndexNot measured29.3Only Kimi K3 measured
Design Arena: agents building web appsNot measured1273Only Kimi K3 measured
Design Arena: agents building full-stack apps14021290Claude Fable 5.2
Design Arena: agents building mobile apps13251253Claude Fable 5.2
Design Arena: agents building Android appsNot measured1256Only Kimi K3 measured
Design Arena: agents building Godot gamesNot measured1200Only Kimi K3 measured
Design Arena: agents building gamesNot measured1198Only Kimi K3 measured
Design Arena: HTML slidesNot measured1151Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1223Only Kimi K3 measured
Design Arena: spreadsheets14341068Claude Fable 5.2
LiveBench research94.5%79.8%Claude Fable 5.2
LiveBench browser86.9%75.2%Claude Fable 5.2
LiveBench long agentic82.9%36.0%Claude Fable 5.2
Finance Agent (Vals AI)Not measured53.1%Only Kimi K3 measured
Tax Agent Bench (Vals AI)32.1%33.4%Kimi K3
Legal Research Bench (Vals AI)46.1%46.1%Tie
Harvey's Legal Agent Benchmark (Vals AI)5.0%12.9%Kimi K3
Excel Modeling Benchmark (Vals AI)Not measured66.7%Only Kimi K3 measured
BioMysteryBench (Vals AI)83.7%72.6%Claude Fable 5.2
Terminal-Bench-Science (Vals AI)55.7%1.4%Claude Fable 5.2
Vals Science Index63.7%Not measuredOnly Claude Fable 5.2 measured
Time Horizon Index (Vals AI)Not measured10.5%Only Kimi K3 measured
APEX-Agents80.1%47.8%Claude Fable 5.2
Remote Labor Index41.3%Not measuredOnly Claude Fable 5.2 measured
PostTrainBenchNot measured31.5%Only Kimi K3 measured
SpireClimb15.5%Not measuredOnly Claude Fable 5.2 measured
Vending-Bench 2Not measured$5,165Only Kimi K3 measured
MCP AtlasNot measured82.3%Only Kimi K3 measured
Toolathlon-VerifiedNot measured76.5%Only Kimi K3 measured
τ³-BankingNot measured37.1%Only Kimi K3 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index101
Reasoning benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
GPQA DiamondNot measured92.9%Only Kimi K3 measured
LiveBench reasoning88.8%90.7%Kimi K3
MysteryMechanism (Vals AI)51.8%Not measuredOnly Claude Fable 5.2 measured
MMMU Pro (Vals AI)Not measured88.2%Only Kimi K3 measured
GPQA Diamond (Artificial Analysis run)Not measured93.5%Only Kimi K3 measured
Humanity's Last Exam (Artificial Analysis run)74.3%46.9%Claude Fable 5.2
HLE-Diamond (Artificial Analysis run)80.2%26.9%Claude Fable 5.2
CritPt v2, hard subset (Artificial Analysis run)76.5%40.5%Claude Fable 5.2
GPQA Diamond (Epoch AI run)93.9%93.1%Claude Fable 5.2
ARC-AGI98.5%94.5%Claude Fable 5.2
ARC-AGI-293.8%60.4%Claude Fable 5.2
SimpleBench94.9%60.7%Claude Fable 5.2
Chess puzzles79.0%37.0%Claude Fable 5.2
Mystery game puzzles90.0%26.0%Claude Fable 5.2
EBR-bench90.5%Not measuredOnly Claude Fable 5.2 measured
LMArena Text: hard promptsNot measured1494Only Kimi K3 measured
LMArena Text: expertNot measured1515Only Kimi K3 measured
LMArena Text: hard prompts in EnglishNot measured1493Only Kimi K3 measured
Humanity's Last Exam (Scale run)72.4%22.2%Claude Fable 5.2
GoBench2566Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
OTIS Mock AIME99.7%97.2%Claude Fable 5.2
FrontierMath, tiers 1 to 395.1%72.2%Claude Fable 5.2
FrontierMath, tier 4100.0%39.0%Claude Fable 5.2
ProofBench100.0%87.0%Claude Fable 5.2
LMArena Text: mathNot measured1496Only Kimi K3 measured
LMArena Text: mathematical workNot measured1507Only Kimi K3 measured
MathArena82.8%42.9%Claude Fable 5.2
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
Knowledge benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
MMLU ProNot measured88.0%Only Kimi K3 measured
LegalBench (Vals AI)Not measured86.2%Only Kimi K3 measured
CorpFin (Vals AI)Not measured71.6%Only Kimi K3 measured
TaxEval (Vals AI)Not measured75.7%Only Kimi K3 measured
MortgageTax (Vals AI)Not measured66.3%Only Kimi K3 measured
MedCode (Vals AI)Not measured49.4%Only Kimi K3 measured
AA-Omniscience66.8-1.7Claude Fable 5.2
SimpleQA Verified94.0%50.6%Claude Fable 5.2
LMArena Text: scienceNot measured1502Only Kimi K3 measured
LMArena Text: medicine and healthcareNot measured1488Only Kimi K3 measured
LMArena Text: legal and governmentNot measured1498Only Kimi K3 measured
LMArena Text: business and financeNot measured1469Only Kimi K3 measured
PRBench Finance47.1%Not measuredOnly Claude Fable 5.2 measured
PRBench Legal49.0%Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
Design Arena: websites13511336Claude Fable 5.2
Design Arena: UI components13711340Claude Fable 5.2
Design Arena: game dev13961353Claude Fable 5.2
Design Arena: data vizNot measured1350Only Kimi K3 measured
Design Arena: 3D15171364Claude Fable 5.2
Design Arena: all code categories13731351Claude Fable 5.2
Design Arena: SVGNot measured1296Only Kimi K3 measured
LiveBench design85.1%72.5%Claude Fable 5.2
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index61
General benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
Vals Index71.3%53.0%Claude Fable 5.2
LiveBench data analysis81.5%78.7%Claude Fable 5.2
Public Benefits Bench (Vals AI)Not measured68.2%Only Kimi K3 measured
SAGE (Vals AI)Not measured86.8%Only Kimi K3 measured
MedScribe (Vals AI)Not measured88.0%Only Kimi K3 measured
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
Long context reasoning (AA-LCR)83.3%88.7%Kimi K3
GDPval-AA18311542Claude Fable 5.2
DTBench99.2%91.2%Claude Fable 5.2
LMCA70.6%52.7%Claude Fable 5.2
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assembly90.0%34.2%Claude Fable 5.2
LMArena TextNot measured1475Only Kimi K3 measured
LMArena Text: instruction followingNot measured1484Only Kimi K3 measured
LMArena Text: creative writingNot measured1453Only Kimi K3 measured
LMArena Text: EnglishNot measured1479Only Kimi K3 measured
LMArena Text: non-EnglishNot measured1465Only Kimi K3 measured
LMArena Text: ChineseNot measured1527Only Kimi K3 measured
LMArena Text: GermanNot measured1483Only Kimi K3 measured
LMArena Text: JapaneseNot measured1495Only Kimi K3 measured
LMArena Text: KoreanNot measured1444Only Kimi K3 measured
LMArena Text: FrenchNot measured1482Only Kimi K3 measured
LMArena Text: SpanishNot measured1477Only Kimi K3 measured
LMArena Text: RussianNot measured1481Only Kimi K3 measured
LMArena Text: PolishNot measured1472Only Kimi K3 measured
LMArena Text: multi-turnNot measured1489Only Kimi K3 measured
LMArena Text: longer queriesNot measured1490Only Kimi K3 measured
LMArena Text: writing and languageNot measured1468Only Kimi K3 measured
LMArena Text: entertainment and mediaNot measured1450Only Kimi K3 measured
EQ-Bench 4Not measured1319Only Kimi K3 measured
Neither model has a result on the other 19 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5.2 and Kimi K3
BenchmarkClaude Fable 5.2Kimi K3Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Fable 5.2$0.028Fits in one request
Kimi K3$0.011Fits in one request

Kimi K3 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5.2$0.520Fits in one request
Kimi K3$0.195Fits in one request

Kimi K3 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5.2$2.00Fits in one request
Kimi K3$0.750Fits in one request

Kimi K3 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Fable 5.2 and Kimi K3
SpecificationAnthropic Claude Fable 5.2MoonshotAI Kimi K3
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedNovember 9, 2026July 16, 2026
Context window1M1.05M
Input $/Mtok$8.00$3.00
Output $/Mtok$40.00$15.00
Coding index87.861.4
Independent measurements behind it46
Cost per solved taskNot computable$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5.2 better than Kimi K3 for coding?

Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 61.4 for Kimi K3, though on 4 benchmarks against 6. Pick Kimi K3 for output tokens 2.7x cheaper ($15.00 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Claude Fable 5.2 or Kimi K3?

Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. Cost per solved task is known for Kimi K3 only.

Which has the bigger context window, Claude Fable 5.2 or Kimi K3?

Kimi K3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Fable 5.2 vs Kimi K3 comparison based on?

59 benchmarks have a result for both models as of November 14, 2026. Claude Fable 5.2's coding index rests on 4 independent benchmarks and Kimi K3's on 6. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-fable-5-2-vs-kimi-k3" title="Claude Fable 5.2 vs Kimi K3, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-fable-5-2-vs-kimi-k3">LLMBenchmark.ai, Claude Fable 5.2 vs Kimi K3</a></p>