Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs Inkling Small

GPT-5.4 Mini leads Inkling Small on coding, 35.8 to 27.3 on the Vibe Coding Index, and Inkling Small costs 3.8x less per output token ($1.20 vs $4.50 per million). Updated October 21, 2026; 74 benchmarks have a result for both.

Replace GPT-5.4 Mini Replace Inkling Small
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
35
T Inkling SmallThinking Machines
Coding
27.3
Overall
43.6
Output $/M
$1.20
39
vs boards won of 74 shared

GPT-5.4 Mini or Inkling Small: which to pick

Pick GPT-5.4 Mini for coding: it scores 35.8 on the Vibe Coding Index against 27.3 for Inkling Small.

Pick Inkling Small for output tokens 3.8x cheaper ($1.20 vs $4.50 per million) and a lower cost per solved task ($0.16 against $0.70).

Model AGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved taskModel BInkling SmallThinking Machines27.3/1004 independent benchmarks$0.16 per solved task
Shared results
74
GPT-5.4 Mini only
15
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
GPT-5.4 Mini 35.8 from 5 benchmarks, Inkling Small 27.3 from 4 benchmarks.
Widest category
Agentic work, 8.6 points apart on average over 5 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): GPT-5.4 Mini 48.0% against Inkling Small 19.1%, 28.9 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against Inkling Small $1.20 per million output tokens, 3.8x apart.
Context window
GPT-5.4 Mini takes 400K 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-5.4 MiniBarsInkling SmallTies
Coding59
Intelligence02
Agentic work23
Reasoning48
Math24
Knowledge36
General197
All shared boards3539
CodingLike-for-likeSix of these boards feed the Vibe Coding Index59
Coding benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
LMArena WebDev13971409Inkling Small
AA Coding Index56.152.9GPT-5.4 Mini
LiveCodeBench (Vals AI)81.5%85.9%Inkling Small
SWE-bench Verified (Vals AI)73.0%82.2%Inkling Small
Terminal-Bench 4 (Vals AI)2.5%0.0%GPT-5.4 Mini
Vibe Code Bench (Vals AI)48.0%19.1%GPT-5.4 Mini
Code migration (Vals AI)12.9%13.7%Inkling Small
ProgramBench (Vals AI)0.0%0.5%Inkling Small
IOI (Vals AI)Not measured9.3%Only Inkling Small measured
Terminal-Bench 2.1 (Vals AI)54.7%55.1%Inkling Small
SkillsBench (Vals AI)Not measured33.6%Only Inkling Small measured
CyberBench (Vals AI)Not measured64.1%Only Inkling Small measured
SciCode52.1%49.7%GPT-5.4 Mini
Terminal-Bench Hard (Artificial Analysis run)52.3%Not measuredOnly GPT-5.4 Mini measured
FrontierCode27.0%Not measuredOnly GPT-5.4 Mini measured
WeirdML60.3%Not measuredOnly GPT-5.4 Mini measured
ALE-Bench1188.6Not measuredOnly GPT-5.4 Mini measured
LMArena Text: coding14381450Inkling Small
LMArena Text: software and IT14361447Inkling Small
LMArena WebDev: React13861399Inkling Small
LMArena WebDev: HTML14191398GPT-5.4 Mini
LMArena WebDev: from an imageNot measured1410Only Inkling Small measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
AA Intelligence Index24.125.7Inkling Small
Epoch Capabilities Index148.7150.3Inkling Small
Agentic workLike-for-likePublic boards, shown as published, kept out of the index23
Agentic work benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
AA Agentic Index17.923.5Inkling Small
Finance Agent (Vals AI)45.4%41.3%GPT-5.4 Mini
Tax Agent Bench (Vals AI)8.8%15.4%Inkling Small
Legal Research Bench (Vals AI)12.5%25.5%Inkling Small
Harvey's Legal Agent Benchmark (Vals AI)Not measured2.9%Only Inkling Small measured
Excel Modeling Benchmark (Vals AI)45.4%31.8%GPT-5.4 Mini
τ²-Bench Telecom83.3%Not measuredOnly GPT-5.4 Mini measured
DeepResearch Bench36.3%Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index48
Reasoning benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
GPQA Diamond83.1%83.6%Inkling Small
MMMU Pro (Vals AI)79.3%Not measuredOnly GPT-5.4 Mini measured
GPQA Diamond (Artificial Analysis run)87.5%89.5%Inkling Small
Humanity's Last Exam (Artificial Analysis run)28.1%33.3%Inkling Small
GPQA Diamond (Epoch AI run)86.9%88.5%Inkling Small
ARC-AGI63.7%84.0%Inkling Small
ARC-AGI-218.9%40.1%Inkling Small
Chess puzzles23.0%Not measuredOnly GPT-5.4 Mini measured
Mystery game puzzles11.0%6.0%GPT-5.4 Mini
LMArena Text: hard prompts14241423GPT-5.4 Mini
LMArena Text: expert14351441Inkling Small
LMArena Text: hard prompts in English14201429Inkling Small
LMArena Vision: diagrams12661251GPT-5.4 Mini
LMArena Vision: homework12851257GPT-5.4 Mini
Kagi LLM Benchmark37.9%Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
AIME95.6%Not measuredOnly GPT-5.4 Mini measured
OTIS Mock AIME88.9%90.0%Inkling Small
FrontierMath, tiers 1 to 351.2%46.3%GPT-5.4 Mini
FrontierMath, tier 49.8%17.1%Inkling Small
ProofBench21.0%6.0%GPT-5.4 Mini
LMArena Text: math14181459Inkling Small
LMArena Text: mathematical work14291441Inkling Small
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index36
Knowledge benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
MMLU Pro84.5%85.6%Inkling Small
LegalBench (Vals AI)Not measured83.0%Only Inkling Small measured
CaseLaw (Vals AI)51.7%Not measuredOnly GPT-5.4 Mini measured
CorpFin (Vals AI)60.9%69.6%Inkling Small
TaxEval (Vals AI)71.2%75.5%Inkling Small
MortgageTax (Vals AI)63.5%62.3%GPT-5.4 Mini
MedCode (Vals AI)Not measured37.9%Only Inkling Small measured
SimpleQA Verified29.4%19.1%GPT-5.4 Mini
LMArena Text: science14171428Inkling Small
LMArena Text: medicine and healthcare13951413Inkling Small
LMArena Text: legal and government14141415Inkling Small
LMArena Text: business and finance14181413GPT-5.4 Mini
Neither model has a result on the other 6 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index197
General benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling SmallLeader
Vals IndexNot measured27.6%Only Inkling Small measured
Public Benefits Bench (Vals AI)Not measured59.4%Only Inkling Small measured
SAGE (Vals AI)50.8%32.7%GPT-5.4 Mini
MedScribe (Vals AI)Not measured84.1%Only Inkling Small measured
Vals Multimodal Index54.2%50.0%GPT-5.4 Mini
IFBench73.3%Not measuredOnly GPT-5.4 Mini measured
Long context reasoning (AA-LCR)77.0%75.7%GPT-5.4 Mini
DTBench80.0%Not measuredOnly GPT-5.4 Mini measured
LMCA40.8%Not measuredOnly GPT-5.4 Mini measured
LMArena Text14121413Inkling Small
LMArena Text: instruction following14051399GPT-5.4 Mini
LMArena Text: creative writing13701334GPT-5.4 Mini
LMArena Vision12451237GPT-5.4 Mini
LMArena Text: English14121421Inkling Small
LMArena Text: non-English14051401GPT-5.4 Mini
LMArena Text: Chinese14461464Inkling Small
LMArena Text: German14081408GPT-5.4 Mini
LMArena Text: Japanese13751401Inkling Small
LMArena Text: Korean13701367GPT-5.4 Mini
LMArena Text: French14411435GPT-5.4 Mini
LMArena Text: Spanish14051422Inkling Small
LMArena Text: Russian14171394GPT-5.4 Mini
LMArena Text: Polish14151428Inkling Small
LMArena Text: multi-turn14291416GPT-5.4 Mini
LMArena Text: longer queries14081402GPT-5.4 Mini
LMArena Text: writing and language13931357GPT-5.4 Mini
LMArena Text: entertainment and media13731352GPT-5.4 Mini
LMArena Vision: English12441243GPT-5.4 Mini
LMArena Vision: Chinese12861292Inkling Small
LMArena Vision: reading text12531243GPT-5.4 Mini
LMArena Vision: humor12351207GPT-5.4 Mini
LMArena Vision: recognizing things1218Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: creative writing12221205GPT-5.4 Mini
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 Mini and Inkling Small
BenchmarkGPT-5.4 MiniInkling 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 Mini$0.0030Fits in one request
Inkling Small$0.0010Fits in one request

Inkling Small costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Mini$0.051Fits in one request
Inkling Small$0.026Fits in one request

Inkling Small costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Mini$0.195Fits 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 Mini and Inkling Small
SpecificationOpenAI GPT-5.4 MiniThinking Machines Inkling Small
MakerOpenAIThinking Machines
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026July 30, 2026
Context window400K524K
Input $/Mtok$0.75$0.45
Output $/Mtok$4.50$1.20
Coding index35.827.3
Independent measurements behind it54
Cost per solved task$0.70$0.16
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Mini better than Inkling Small for coding?

Pick GPT-5.4 Mini for coding: it scores 35.8 on the Vibe Coding Index against 27.3 for Inkling Small. Pick Inkling Small for output tokens 3.8x cheaper ($1.20 vs $4.50 per million) and a lower cost per solved task ($0.16 against $0.70).

Which is cheaper, GPT-5.4 Mini or Inkling Small?

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and Inkling Small $0.16.

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

Inkling Small, with 524K tokens against 400K.

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

74 benchmarks have a result for both models as of October 21, 2026. GPT-5.4 Mini's coding index rests on 5 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/gpt-5-4-mini-vs-thinkingmachines-inkling-small" title="GPT-5.4 Mini 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/gpt-5-4-mini-vs-thinkingmachines-inkling-small">LLMBenchmark.ai, GPT-5.4 Mini vs Inkling Small</a></p>