Enter opens the highlighted result. Esc closes.

GPT-5.4 vs Inkling Small

Updated October 21, 2026. 70 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.4 Replace Inkling Small
GPT-5.4OpenAI
Coding
37.7
Overall
39.0
Output $/M
$15.00
64
T Inkling SmallThinking Machines
Coding
29.9
Overall
25.7
Output $/M
$1.20
5
vs boards won of 70 shared, 1 tied

Decision reading

Pick GPT-5.4 for coding: it scores 37.7 on the Vibe Coding Index against 29.9 for Inkling Small.

Pick Inkling Small when output tokens cost 12.5x less, or when a solved task costs $0.16 against $1.02.

Model AGPT-5.4OpenAI37.7/1001 independent benchmark$1.02 per solved taskModel BInkling SmallThinking Machines29.9/1001 independent benchmark$0.16 per solved task
Shared results
70
GPT-5.4 only
39
Inkling Small only
14
Like-for-like categories
6 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
GPT-5.4 37.7 from 1 benchmark, Inkling Small 29.9 from 1 benchmark.
Widest category
Math, 22.7 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: GPT-5.4 56.0% against Inkling Small 6.0%, 50.0 points apart on a 0 to 100 scale.
Output price
GPT-5.4 $15.00 against Inkling Small $1.20 per million output tokens, 12.5x apart.
Context window
GPT-5.4 takes 1.05M tokens, Inkling Small 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
CategoryGPT-5.4BarsInkling SmallTies
Coding1021 tie
Intelligence20
Reasoning120
Math60
Knowledge92
General251
All shared boards6451 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index102
Coding benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
LMArena WebDev14641409GPT-5.4
AA Coding Index71.152.9GPT-5.4
LiveCodeBench (Vals AI)84.1%85.9%Inkling Small
SWE-bench Verified (Vals AI)78.2%82.2%Inkling Small
Terminal-Bench 4 (Vals AI)Not measured0.0%Only Inkling Small measured
Vibe Code Bench (Vals AI)67.4%19.1%GPT-5.4
Code migration (Vals AI)35.0%13.7%GPT-5.4
ProgramBench (Vals AI)0.5%0.5%Tie
IOI (Vals AI)Not measured9.3%Only Inkling Small measured
Terminal-Bench 2.1 (Vals AI)Not measured55.1%Only Inkling Small measured
SkillsBench (Vals AI)51.7%33.6%GPT-5.4
CyberBench (Vals AI)Not measured64.1%Only Inkling Small measured
SciCodeNot measured49.7%Only Inkling Small measured
Terminal-Bench Hard (Artificial Analysis run)57.6%Not measuredOnly GPT-5.4 measured
Terminal-Bench81.8%Not measuredOnly GPT-5.4 measured
GSO-Bench31.4%Not measuredOnly GPT-5.4 measured
WeirdML77.7%Not measuredOnly GPT-5.4 measured
MirrorCode15.6%Not measuredOnly GPT-5.4 measured
ALE-Bench1607.0Not measuredOnly GPT-5.4 measured
LMArena Text: coding14961450GPT-5.4
LMArena Text: software and IT14911447GPT-5.4
LMArena WebDev: React14541399GPT-5.4
LMArena WebDev: HTML14781398GPT-5.4
LMArena WebDev: from an image14361410GPT-5.4
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
AA Intelligence Index39.025.7GPT-5.4
Epoch Capabilities Index157.3150.3GPT-5.4
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
Agentic work benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
AA Agentic IndexNot measured23.5Only Inkling Small measured
Design Arena: agents building web apps1059Not measuredOnly GPT-5.4 measured
Design Arena: agents building full-stack apps1017Not measuredOnly GPT-5.4 measured
Design Arena: agents building mobile apps1087Not measuredOnly GPT-5.4 measured
Design Arena: agents building Android apps1037Not measuredOnly GPT-5.4 measured
Design Arena: agents building Godot games1135Not measuredOnly GPT-5.4 measured
Finance Agent (Vals AI)Not measured41.3%Only Inkling Small measured
Tax Agent Bench (Vals AI)Not measured15.4%Only Inkling Small measured
Legal Research Bench (Vals AI)Not measured25.5%Only Inkling Small measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured2.9%Only Inkling Small measured
Excel Modeling Benchmark (Vals AI)Not measured31.8%Only Inkling Small measured
τ²-Bench Telecom87.1%Not measuredOnly GPT-5.4 measured
APEX-Agents52.4%Not measuredOnly GPT-5.4 measured
METR time horizons74.3%Not measuredOnly GPT-5.4 measured
DeepResearch Bench35.1%Not measuredOnly GPT-5.4 measured
PostTrainBench19.0%Not measuredOnly GPT-5.4 measured
Vending-Bench 2$6,144Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
GPQA Diamond91.7%83.6%GPT-5.4
MMMU Pro (Vals AI)87.5%Not measuredOnly GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)92.0%89.5%GPT-5.4
Humanity's Last Exam (Artificial Analysis run)43.7%33.3%GPT-5.4
GPQA Diamond (Epoch AI run)93.3%88.5%GPT-5.4
ARC-AGI93.7%84.0%GPT-5.4
ARC-AGI-274.0%40.1%GPT-5.4
Chess puzzles48.0%Not measuredOnly GPT-5.4 measured
Mystery game puzzles37.0%6.0%GPT-5.4
EBR-bench25.4%Not measuredOnly GPT-5.4 measured
LMArena Text: hard prompts14851423GPT-5.4
LMArena Text: expert15071441GPT-5.4
LMArena Text: hard prompts in English14791429GPT-5.4
LMArena Vision: diagrams13271251GPT-5.4
LMArena Vision: homework13361257GPT-5.4
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
AIME96.7%Not measuredOnly GPT-5.4 measured
OTIS Mock AIME97.8%90.0%GPT-5.4
FrontierMath, tiers 1 to 378.6%46.3%GPT-5.4
FrontierMath, tier 449.0%17.1%GPT-5.4
ProofBench56.0%6.0%GPT-5.4
LMArena Text: math14881459GPT-5.4
LMArena Text: mathematical work14971441GPT-5.4
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
Knowledge benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
MMLU Pro87.5%85.6%GPT-5.4
LegalBench (Vals AI)86.0%83.0%GPT-5.4
CaseLaw (Vals AI)63.8%Not measuredOnly GPT-5.4 measured
CorpFin (Vals AI)65.3%69.6%Inkling Small
TaxEval (Vals AI)74.0%75.5%Inkling Small
MortgageTax (Vals AI)68.3%62.3%GPT-5.4
MedQA (Vals AI)96.1%Not measuredOnly GPT-5.4 measured
MedCode (Vals AI)41.3%37.9%GPT-5.4
SimpleQA Verified45.1%19.1%GPT-5.4
LMArena Text: science14791428GPT-5.4
LMArena Text: medicine and healthcare14581413GPT-5.4
LMArena Text: legal and government14861415GPT-5.4
LMArena Text: business and finance14741413GPT-5.4
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
Design Arena: websites1199Not measuredOnly GPT-5.4 measured
Design Arena: UI components1215Not measuredOnly GPT-5.4 measured
Design Arena: game dev1195Not measuredOnly GPT-5.4 measured
Design Arena: data viz1196Not measuredOnly GPT-5.4 measured
Design Arena: 3D1065Not measuredOnly GPT-5.4 measured
Design Arena: all code categories1180Not measuredOnly GPT-5.4 measured
Design Arena: SVG1141Not measuredOnly GPT-5.4 measured
Design Arena: ASCII art1188Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index251
General benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling SmallLeader
Vals IndexNot measured27.6%Only Inkling Small measured
Public Benefits Bench (Vals AI)Not measured59.4%Only Inkling Small measured
SAGE (Vals AI)43.3%32.7%GPT-5.4
MedScribe (Vals AI)77.5%84.1%Inkling Small
Vals Multimodal IndexNot measured50.0%Only Inkling Small measured
IFBench73.9%Not measuredOnly GPT-5.4 measured
Long context reasoning (AA-LCR)82.0%75.7%GPT-5.4
DTBench94.4%Not measuredOnly GPT-5.4 measured
LMCA52.0%Not measuredOnly GPT-5.4 measured
CL-bench27.9%Not measuredOnly GPT-5.4 measured
Furniture assembly37.5%Not measuredOnly GPT-5.4 measured
CL-bench Life21.7%Not measuredOnly GPT-5.4 measured
LMArena Text14691413GPT-5.4
LMArena Text: instruction following14691399GPT-5.4
LMArena Text: creative writing14391334GPT-5.4
LMArena Vision13031237GPT-5.4
LMArena Text: English14671421GPT-5.4
LMArena Text: non-English14651401GPT-5.4
LMArena Text: Chinese15201464GPT-5.4
LMArena Text: German14721408GPT-5.4
LMArena Text: Japanese14851401GPT-5.4
LMArena Text: Korean14491367GPT-5.4
LMArena Text: French14931435GPT-5.4
LMArena Text: Spanish14521422GPT-5.4
LMArena Text: Russian14801394GPT-5.4
LMArena Text: Polish14721428GPT-5.4
LMArena Text: multi-turn14821416GPT-5.4
LMArena Text: longer queries14731402GPT-5.4
LMArena Text: writing and language14581357GPT-5.4
LMArena Text: entertainment and media14381352GPT-5.4
LMArena Vision: English13011243GPT-5.4
LMArena Vision: Chinese13541292GPT-5.4
LMArena Vision: reading text13121243GPT-5.4
LMArena Vision: humor12841207GPT-5.4
LMArena Vision: recognizing things1251Not measuredOnly GPT-5.4 measured
LMArena Vision: creative writing12831205GPT-5.4
LMArena Document1471Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 and Inkling Small
BenchmarkGPT-5.4Inkling 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

GPT-5.4$0.010Fits in one request
Inkling Small$0.0010Fits in one request

Inkling Small costs less

Repository review

50K input + 3K output tokens

GPT-5.4$0.170Fits in one request
Inkling Small$0.026Fits in one request

Inkling Small costs less

Agent loop

200K input + 10K output tokens

GPT-5.4$0.650Fits 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 GPT-5.4 and Inkling Small
SpecificationOpenAI GPT-5.4Thinking Machines Inkling Small
MakerOpenAIThinking Machines
WeightsNo public weights listedOpen weights
ReleasedMarch 5, 2026July 30, 2026
Context window1.05M524K
Input $/Mtok$2.50$0.45
Output $/Mtok$15.00$1.20
Coding index37.729.9
Independent measurements behind it11
Cost per solved task$1.02$0.16
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 better than Inkling Small for coding?

Pick GPT-5.4 for coding: it scores 37.7 on the Vibe Coding Index against 29.9 for Inkling Small. Pick Inkling Small when output tokens cost 12.5x less, or when a solved task costs $0.16 against $1.02.

Which is cheaper, GPT-5.4 or Inkling Small?

GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, GPT-5.4 costs $1.02 and Inkling Small $0.16.

Which has the bigger context window, GPT-5.4 or Inkling Small?

GPT-5.4, with 1.05M tokens against 524K.

How many benchmarks is the GPT-5.4 vs Inkling Small comparison based on?

70 benchmarks have a result for both models as of October 21, 2026. GPT-5.4's coding index rests on 1 independent benchmark and Inkling Small's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next