Enter opens the highlighted result. Esc closes.

Claude Fable 5.2 vs Inkling

Claude Fable 5.2 leads Inkling on coding, 87.8 to 29.2 on the Vibe Coding Index, and Inkling costs 9.9x less per output token ($4.05 vs $40.00 per million). Updated November 14, 2026; 50 benchmarks have a result for both.

Replace Claude Fable 5.2 Replace Inkling
Claude Fable 5.2Anthropic
Coding
87.8
Overall
91.7
Output $/M
$40.00
50
T InklingThinking Machines
Coding
29.2
Overall
43.1
Output $/M
$4.05
0
vs boards won of 50 shared

Claude Fable 5.2 or Inkling: which to pick

Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 29.2 for Inkling, though on 4 benchmarks against 6.

Pick Inkling for output tokens 9.9x cheaper ($4.05 vs $40.00 per million).

Model AClaude Fable 5.2Anthropic87.8/1004 independent benchmarksNo cost per solved taskModel BInklingThinking Machines29.2/1006 independent benchmarks$0.76 per solved task
Shared results
50
Claude Fable 5.2 only
18
Inkling only
65
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, Inkling 29.2 from 6 benchmarks.
Widest category
Math, 66.9 points apart on average over 4 shared benchmarks.
Widest single gap
ProofBench: Claude Fable 5.2 100.0% against Inkling 0.0%, 100.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5.2 $40.00 against Inkling $4.05 per million output tokens, 9.9x apart.
Context window
Claude Fable 5.2 takes 1M tokens, Inkling 524K.

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 5.2BarsInklingTies
Coding130
Intelligence20
Agentic work70
Reasoning100
Math40
Knowledge20
Web design60
General60
All shared boards500
CodingLike-for-likeSix of these boards feed the Vibe Coding Index130
Coding benchmarks for Claude Fable 5.2 and Inkling
BenchmarkClaude Fable 5.2InklingLeader
LiveBench coding79.2%48.7%Claude Fable 5.2
LMArena WebDev18381414Claude Fable 5.2
AA Coding IndexNot measured52.1Only Inkling measured
LiveCodeBench (Vals AI)Not measured85.5%Only Inkling measured
SWE-bench Verified (Vals AI)Not measured77.6%Only Inkling measured
Terminal-Bench 4 (Vals AI)65.2%0.5%Claude Fable 5.2
Vibe Code Bench (Vals AI)93.8%19.2%Claude Fable 5.2
Code migration (Vals AI)Not measured11.8%Only Inkling measured
ProgramBench (Vals AI)19.0%0.0%Claude Fable 5.2
IOI (Vals AI)Not measured14.9%Only Inkling measured
Terminal-Bench 2.1 (Vals AI)Not measured47.6%Only Inkling measured
SWE-bench Multimodal (Vals AI)62.3%Not measuredOnly Claude Fable 5.2 measured
Vibe Code Bench 1-100 (Vals AI)Not measured7.3%Only Inkling measured
SkillsBench (Vals AI)Not measured26.1%Only Inkling measured
CyberBench (Vals AI)Not measured66.8%Only Inkling measured
SciCode67.7%47.0%Claude Fable 5.2
Terminal-Bench 4.0 (Artificial Analysis run)61.6%1.0%Claude Fable 5.2
FrontierCode 2.049.1%3.9%Claude Fable 5.2
FrontierCodeNot measured14.0%Only Inkling measured
FrontierSWE69.9%4.1%Claude Fable 5.2
WeirdMLNot measured32.3%Only Inkling measured
ALE-Bench2509.8946.0Claude Fable 5.2
LMArena Text: codingNot measured1467Only Inkling measured
LMArena Text: software and ITNot measured1467Only Inkling measured
LMArena WebDev: React19151404Claude Fable 5.2
LMArena WebDev: HTML17381404Claude Fable 5.2
SWE-Bench Pro V2Not measured89.9%Only Inkling measured
GameBench 299.131.3Claude Fable 5.2
Terminal-Bench 4.0Not measured0.0%Only Inkling measured
CursorBench 4.060.0%Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5.2 and Inkling
BenchmarkClaude Fable 5.2InklingLeader
AA Intelligence Index64.612.5Claude Fable 5.2
Epoch Capabilities Index173.4148.4Claude Fable 5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
Agentic work benchmarks for Claude Fable 5.2 and Inkling
BenchmarkClaude Fable 5.2InklingLeader
AA Agentic IndexNot measured22.5Only Inkling measured
Design Arena: agents building web appsNot measured1172Only Inkling measured
Design Arena: agents building full-stack apps1402Not measuredOnly Claude Fable 5.2 measured
Design Arena: agents building mobile apps1325Not measuredOnly Claude Fable 5.2 measured
Design Arena: spreadsheets1434Not measuredOnly Claude Fable 5.2 measured
LiveBench research94.5%60.3%Claude Fable 5.2
LiveBench browser86.9%12.0%Claude Fable 5.2
LiveBench long agentic82.9%9.8%Claude Fable 5.2
SREBench (Vals AI)Not measured0.0%Only Inkling measured
Finance Agent (Vals AI)Not measured46.6%Only Inkling measured
Tax Agent Bench (Vals AI)32.1%15.3%Claude Fable 5.2
Legal Research Bench (Vals AI)46.1%28.4%Claude Fable 5.2
Harvey's Legal Agent Benchmark (Vals AI)5.0%3.8%Claude Fable 5.2
Excel Modeling Benchmark (Vals AI)Not measured38.4%Only Inkling measured
BioMysteryBench (Vals AI)83.7%Not measuredOnly Claude Fable 5.2 measured
Terminal-Bench-Science (Vals AI)55.7%Not measuredOnly Claude Fable 5.2 measured
Vals Science Index63.7%Not measuredOnly Claude Fable 5.2 measured
APEX-Agents80.1%33.8%Claude Fable 5.2
Remote Labor Index41.3%Not measuredOnly Claude Fable 5.2 measured
SpireClimb15.5%Not measuredOnly Claude Fable 5.2 measured
MCP AtlasNot measured76.0%Only Inkling measured
Toolathlon-VerifiedNot measured45.5%Only Inkling measured
τ³-BankingNot measured25.0%Only Inkling measured
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for Claude Fable 5.2 and Inkling
BenchmarkClaude Fable 5.2InklingLeader
GPQA DiamondNot measured87.1%Only Inkling measured
LiveBench reasoning88.8%78.3%Claude Fable 5.2
MysteryMechanism (Vals AI)51.8%Not measuredOnly Claude Fable 5.2 measured
MMMU Pro (Vals AI)Not measured78.5%Only Inkling measured
GPQA Diamond (Artificial Analysis run)Not measured87.2%Only Inkling measured
Humanity's Last Exam (Artificial Analysis run)74.3%31.9%Claude Fable 5.2
HLE-Diamond (Artificial Analysis run)80.2%10.6%Claude Fable 5.2
CritPt v2, hard subset (Artificial Analysis run)76.5%18.0%Claude Fable 5.2
GPQA Diamond (Epoch AI run)93.9%88.3%Claude Fable 5.2
ARC-AGI98.5%79.5%Claude Fable 5.2
ARC-AGI-293.8%36.5%Claude Fable 5.2
SimpleBench94.9%50.0%Claude Fable 5.2
Chess puzzles79.0%21.0%Claude Fable 5.2
Mystery game puzzles90.0%Not measuredOnly Claude Fable 5.2 measured
EBR-bench90.5%Not measuredOnly Claude Fable 5.2 measured
LMArena Text: hard promptsNot measured1453Only Inkling measured
LMArena Text: expertNot measured1469Only Inkling measured
LMArena Text: hard prompts in EnglishNot measured1449Only Inkling measured
Humanity's Last Exam (Scale run)72.4%11.2%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 index40
Math benchmarks for Claude Fable 5.2 and Inkling
BenchmarkClaude Fable 5.2InklingLeader
OTIS Mock AIME99.7%88.9%Claude Fable 5.2
FrontierMath, tiers 1 to 395.1%33.3%Claude Fable 5.2
FrontierMath, tier 4100.0%4.9%Claude Fable 5.2
ProofBench100.0%0.0%Claude Fable 5.2
LMArena Text: mathNot measured1481Only Inkling measured
LMArena Text: mathematical workNot measured1466Only Inkling measured
MathArena82.8%Not measuredOnly Claude Fable 5.2 measured
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 Inkling
BenchmarkClaude Fable 5.2InklingLeader
MMLU ProNot measured86.3%Only Inkling measured
LegalBench (Vals AI)Not measured83.0%Only Inkling measured
CorpFin (Vals AI)Not measured68.6%Only Inkling measured
TaxEval (Vals AI)Not measured75.3%Only Inkling measured
MortgageTax (Vals AI)Not measured64.0%Only Inkling measured
MedCode (Vals AI)Not measured41.2%Only Inkling measured
AA-Omniscience66.8-1.5Claude Fable 5.2
SimpleQA Verified94.0%40.3%Claude Fable 5.2
LMArena Text: scienceNot measured1459Only Inkling measured
LMArena Text: medicine and healthcareNot measured1450Only Inkling measured
LMArena Text: legal and governmentNot measured1448Only Inkling measured
LMArena Text: business and financeNot measured1439Only Inkling 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 Inkling
BenchmarkClaude Fable 5.2InklingLeader
Design Arena: websites13511215Claude Fable 5.2
Design Arena: UI components13711189Claude Fable 5.2
Design Arena: game dev13961152Claude Fable 5.2
Design Arena: data vizNot measured1158Only Inkling measured
Design Arena: 3D15171141Claude Fable 5.2
Design Arena: all code categories13731194Claude Fable 5.2
Design Arena: SVGNot measured1101Only Inkling measured
Design Arena: ASCII artNot measured1088Only Inkling measured
LiveBench design85.1%55.2%Claude Fable 5.2
GeneralLike-for-likePublic boards, shown as published, kept out of the index60
General benchmarks for Claude Fable 5.2 and Inkling
BenchmarkClaude Fable 5.2InklingLeader
Vals Index71.3%29.0%Claude Fable 5.2
LiveBench data analysis81.5%72.8%Claude Fable 5.2
Public Benefits Bench (Vals AI)Not measured58.5%Only Inkling measured
MedScribe (Vals AI)Not measured85.4%Only Inkling measured
Vals Multimodal IndexNot measured49.4%Only Inkling measured
Long context reasoning (AA-LCR)83.3%77.3%Claude Fable 5.2
GDPval-AA18311080Claude Fable 5.2
DTBench99.2%87.5%Claude Fable 5.2
LMCA70.6%37.6%Claude Fable 5.2
Furniture assembly90.0%Not measuredOnly Claude Fable 5.2 measured
LMArena TextNot measured1443Only Inkling measured
LMArena Text: instruction followingNot measured1427Only Inkling measured
LMArena Text: creative writingNot measured1395Only Inkling measured
LMArena Text: EnglishNot measured1443Only Inkling measured
LMArena Text: non-EnglishNot measured1436Only Inkling measured
LMArena Text: ChineseNot measured1494Only Inkling measured
LMArena Text: GermanNot measured1440Only Inkling measured
LMArena Text: JapaneseNot measured1438Only Inkling measured
LMArena Text: KoreanNot measured1413Only Inkling measured
LMArena Text: FrenchNot measured1463Only Inkling measured
LMArena Text: SpanishNot measured1451Only Inkling measured
LMArena Text: RussianNot measured1435Only Inkling measured
LMArena Text: PolishNot measured1451Only Inkling measured
LMArena Text: multi-turnNot measured1442Only Inkling measured
LMArena Text: longer queriesNot measured1437Only Inkling measured
LMArena Text: writing and languageNot measured1410Only Inkling measured
LMArena Text: entertainment and mediaNot measured1398Only Inkling measured
EQ-Bench 4Not measured1212Only Inkling measured
Neither model has a result on the other 21 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 Inkling
BenchmarkClaude Fable 5.2InklingLeader
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
Inkling$0.0030Fits in one request

Inkling costs less

Repository review

50K input + 3K output tokens

Claude Fable 5.2$0.520Fits in one request
Inkling$0.062Fits in one request

Inkling costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5.2$2.00Fits in one request
Inkling$0.240Fits in one request

Inkling 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 Inkling
SpecificationAnthropic Claude Fable 5.2Thinking Machines Inkling
MakerAnthropicThinking Machines
WeightsNo public weights listedOpen weights
ReleasedNovember 9, 2026July 17, 2026
Context window1M524K
Input $/Mtok$8.00$1.00
Output $/Mtok$40.00$4.05
Coding index87.829.2
Independent measurements behind it46
Cost per solved taskNot computable$0.76
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5.2 better than Inkling for coding?

Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 29.2 for Inkling, though on 4 benchmarks against 6. Pick Inkling for output tokens 9.9x cheaper ($4.05 vs $40.00 per million).

Which is cheaper, Claude Fable 5.2 or Inkling?

Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; Inkling costs $1.00 and $4.05. Cost per solved task is known for Inkling only.

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

Claude Fable 5.2, with 1M tokens against 524K.

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

50 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 Inkling'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-thinkingmachines-inkling" title="Claude Fable 5.2 vs Inkling, 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-thinkingmachines-inkling">LLMBenchmark.ai, Claude Fable 5.2 vs Inkling</a></p>