Enter opens the highlighted result. Esc closes.

Inkling vs Inkling Small

Inkling leads Inkling Small on coding, 31.5 to 27.3 on the Vibe Coding Index, and Inkling Small costs 3.4x less per output token ($1.20 vs $4.05 per million). Updated October 22, 2026; 74 benchmarks have a result for both.

Replace Inkling Replace Inkling Small
T InklingThinking Machines
Coding
31.5
Overall
46.5
Output $/M
$4.05
48
T Inkling SmallThinking Machines
Coding
27.3
Overall
43.6
Output $/M
$1.20
26
vs boards won of 74 shared

Inkling or Inkling Small: which to pick

Pick Inkling for coding: it scores 31.5 on the Vibe Coding Index against 27.3 for Inkling Small.

Pick Inkling Small for output tokens 3.4x cheaper ($1.20 vs $4.05 per million) and a lower cost per solved task ($0.16 against $0.76).

Model AInklingThinking Machines31.5/1006 independent benchmarks$0.76 per solved taskModel BInkling SmallThinking Machines27.3/1004 independent benchmarks$0.16 per solved task
Shared results
74
Inkling only
28
Inkling Small only
10
Like-for-like categories
7 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
Inkling 31.5 from 6 benchmarks, Inkling Small 27.3 from 4 benchmarks.
Widest category
Math, 6.5 points apart on average over 6 shared benchmarks.
Widest single gap
SimpleQA Verified: Inkling 40.3% against Inkling Small 19.1%, 21.2 points apart on a 0 to 100 scale.
Output price
Inkling $4.05 against Inkling Small $1.20 per million output tokens, 3.4x apart.
Context window
Both take 524K tokens.

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
CategoryInklingBarsInkling SmallTies
Coding98
Intelligence02
Agentic work42
Reasoning45
Math24
Knowledge83
General212
All shared boards4826
CodingLike-for-likeSix of these boards feed the Vibe Coding Index98
Coding benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
LiveBench coding64.0%Not measuredOnly Inkling measured
LMArena WebDev14141409Inkling
AA Coding Index52.152.9Inkling Small
LiveCodeBench (Vals AI)85.5%85.9%Inkling Small
SWE-bench Verified (Vals AI)77.6%82.2%Inkling Small
Terminal-Bench 4 (Vals AI)0.5%0.0%Inkling
Vibe Code Bench (Vals AI)19.2%19.1%Inkling
Code migration (Vals AI)11.8%13.7%Inkling Small
ProgramBench (Vals AI)0.0%0.5%Inkling Small
IOI (Vals AI)14.9%9.3%Inkling
Terminal-Bench 2.1 (Vals AI)47.6%55.1%Inkling Small
Vibe Code Bench 1-100 (Vals AI)7.3%Not measuredOnly Inkling measured
SkillsBench (Vals AI)26.1%33.6%Inkling Small
CyberBench (Vals AI)66.8%64.1%Inkling
SciCode47.0%49.7%Inkling Small
FrontierCode14.0%Not measuredOnly Inkling measured
FrontierSWE4.1%Not measuredOnly Inkling measured
WeirdML32.3%Not measuredOnly Inkling measured
ALE-Bench946.0Not measuredOnly Inkling measured
LMArena Text: coding14661450Inkling
LMArena Text: software and IT14651447Inkling
LMArena WebDev: React14041399Inkling
LMArena WebDev: HTML13991398Inkling
LMArena WebDev: from an imageNot measured1410Only Inkling Small measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
AA Intelligence Index25.025.7Inkling Small
Epoch Capabilities Index148.4150.3Inkling Small
Agentic workLike-for-likePublic boards, shown as published, kept out of the index42
Agentic work benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
AA Agentic Index22.523.5Inkling Small
Design Arena: agents building web apps1196Not measuredOnly Inkling measured
LiveBench research59.9%Not measuredOnly Inkling measured
LiveBench browser16.0%Not measuredOnly Inkling measured
LiveBench long agentic14.1%Not measuredOnly Inkling measured
SREBench (Vals AI)0.0%Not measuredOnly Inkling measured
Finance Agent (Vals AI)46.6%41.3%Inkling
Tax Agent Bench (Vals AI)15.3%15.4%Inkling Small
Legal Research Bench (Vals AI)28.4%25.5%Inkling
Harvey's Legal Agent Benchmark (Vals AI)3.8%2.9%Inkling
Excel Modeling Benchmark (Vals AI)38.4%31.8%Inkling
APEX-Agents33.8%Not measuredOnly Inkling measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index45
Reasoning benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
GPQA Diamond87.1%83.6%Inkling
LiveBench reasoning78.3%Not measuredOnly Inkling measured
MMMU Pro (Vals AI)78.5%Not measuredOnly Inkling measured
GPQA Diamond (Artificial Analysis run)87.2%89.5%Inkling Small
Humanity's Last Exam (Artificial Analysis run)31.9%33.3%Inkling Small
GPQA Diamond (Epoch AI run)88.3%88.5%Inkling Small
ARC-AGI79.5%84.0%Inkling Small
ARC-AGI-236.5%40.1%Inkling Small
SimpleBench50.0%Not measuredOnly Inkling measured
Chess puzzles21.0%Not measuredOnly Inkling measured
Mystery game puzzlesNot measured6.0%Only Inkling Small measured
LMArena Text: hard prompts14511423Inkling
LMArena Text: expert14661441Inkling
LMArena Text: hard prompts in English14481429Inkling
LMArena Vision: diagramsNot measured1251Only Inkling Small measured
LMArena Vision: homeworkNot measured1257Only Inkling Small measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
OTIS Mock AIME88.9%90.0%Inkling Small
FrontierMath, tiers 1 to 333.3%46.3%Inkling Small
FrontierMath, tier 44.9%17.1%Inkling Small
ProofBench0.0%6.0%Inkling Small
LMArena Text: math14791459Inkling
LMArena Text: mathematical work14601441Inkling
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index83
Knowledge benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
MMLU Pro86.3%85.6%Inkling
LegalBench (Vals AI)83.0%83.0%Inkling Small
CorpFin (Vals AI)68.6%69.6%Inkling Small
TaxEval (Vals AI)75.3%75.5%Inkling Small
MortgageTax (Vals AI)64.0%62.3%Inkling
MedCode (Vals AI)41.2%37.9%Inkling
SimpleQA Verified40.3%19.1%Inkling
LMArena Text: science14551428Inkling
LMArena Text: medicine and healthcare14471413Inkling
LMArena Text: legal and government14481415Inkling
LMArena Text: business and finance14381413Inkling
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
Design Arena: websites1224Not measuredOnly Inkling measured
Design Arena: UI components1198Not measuredOnly Inkling measured
Design Arena: game dev1165Not measuredOnly Inkling measured
Design Arena: data viz1156Not measuredOnly Inkling measured
Design Arena: 3D1160Not measuredOnly Inkling measured
Design Arena: all code categories1205Not measuredOnly Inkling measured
Design Arena: SVG1108Not measuredOnly Inkling measured
Design Arena: ASCII art1089Not measuredOnly Inkling measured
LiveBench design58.3%Not measuredOnly Inkling measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index212
General benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
Vals Index29.0%27.6%Inkling
LiveBench data analysis72.8%Not measuredOnly Inkling measured
Public Benefits Bench (Vals AI)58.5%59.4%Inkling Small
SAGE (Vals AI)36.5%32.7%Inkling
MedScribe (Vals AI)85.4%84.1%Inkling
Vals Multimodal Index49.4%50.0%Inkling Small
Long context reasoning (AA-LCR)77.3%75.7%Inkling
DTBench87.5%Not measuredOnly Inkling measured
LMCA37.6%Not measuredOnly Inkling measured
LMArena Text14421413Inkling
LMArena Text: instruction following14251399Inkling
LMArena Text: creative writing13901334Inkling
LMArena VisionNot measured1237Only Inkling Small measured
LMArena Text: English14421421Inkling
LMArena Text: non-English14341401Inkling
LMArena Text: Chinese14931464Inkling
LMArena Text: German14451408Inkling
LMArena Text: Japanese14291401Inkling
LMArena Text: Korean14031367Inkling
LMArena Text: French14551435Inkling
LMArena Text: Spanish14491422Inkling
LMArena Text: Russian14301394Inkling
LMArena Text: Polish14501428Inkling
LMArena Text: multi-turn14371416Inkling
LMArena Text: longer queries14351402Inkling
LMArena Text: writing and language14041357Inkling
LMArena Text: entertainment and media13941352Inkling
LMArena Vision: EnglishNot measured1243Only Inkling Small measured
LMArena Vision: ChineseNot measured1292Only Inkling Small measured
LMArena Vision: reading textNot measured1243Only Inkling Small measured
LMArena Vision: humorNot measured1207Only Inkling Small measured
LMArena Vision: creative writingNot measured1205Only Inkling Small measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Inkling and Inkling Small
BenchmarkInklingInkling SmallLeader
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

Inkling$0.0030Fits in one request
Inkling Small$0.0010Fits in one request

Inkling Small costs less

Repository review

50K input + 3K output tokens

Inkling$0.061Fits in one request
Inkling Small$0.026Fits in one request

Inkling Small costs less

Agent loop

200K input + 10K output tokens

Inkling$0.235Fits in one request
Inkling Small$0.102Fits in one request

Inkling Small 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 Inkling and Inkling Small
SpecificationThinking Machines InklingThinking Machines Inkling Small
MakerThinking MachinesThinking Machines
WeightsOpen weightsOpen weights
ReleasedJuly 17, 2026July 30, 2026
Context window524K524K
Input $/Mtok$0.975$0.45
Output $/Mtok$4.05$1.20
Coding index31.527.3
Independent measurements behind it64
Cost per solved task$0.76$0.16
SourceOpenRouter listingOpenRouter listing

Questions

Is Inkling better than Inkling Small for coding?

Pick Inkling for coding: it scores 31.5 on the Vibe Coding Index against 27.3 for Inkling Small. Pick Inkling Small for output tokens 3.4x cheaper ($1.20 vs $4.05 per million) and a lower cost per solved task ($0.16 against $0.76).

Which is cheaper, Inkling or Inkling Small?

Inkling costs $0.975 per million input tokens and $4.05 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, Inkling costs $0.76 and Inkling Small $0.16.

Which has the bigger context window, Inkling or Inkling Small?

Neither: both take 524K tokens.

How many benchmarks is the Inkling vs Inkling Small comparison based on?

74 benchmarks have a result for both models as of October 22, 2026. Inkling's coding index rests on 6 independent benchmarks and Inkling Small's on 4. 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/thinkingmachines-inkling-vs-thinkingmachines-inkling-small" title="Inkling vs Inkling Small, 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/thinkingmachines-inkling-vs-thinkingmachines-inkling-small">LLMBenchmark.ai, Inkling vs Inkling Small</a></p>