Enter opens the highlighted result. Esc closes.

GPT-5.3-Codex vs Inkling

GPT-5.3-Codex leads Inkling on coding, 60.0 to 31.5 on the Vibe Coding Index, and Inkling costs 3.5x less per output token ($4.05 vs $14.00 per million). Updated October 22, 2026; 23 benchmarks have a result for both.

Replace GPT-5.3-Codex Replace Inkling
GPT-5.3-CodexOpenAI
Coding
60.0
Overall
No data
Output $/M
$14.00
15
T InklingThinking Machines
Coding
31.5
Overall
46.5
Output $/M
$4.05
8
vs boards won of 23 shared

GPT-5.3-Codex or Inkling: which to pick

Pick GPT-5.3-Codex for coding: it scores 60.0 on the Vibe Coding Index against 31.5 for Inkling, though on 3 benchmarks against 6.

Pick Inkling for output tokens 3.5x cheaper ($4.05 vs $14.00 per million) and a larger context window (524K against 400K tokens).

Model AGPT-5.3-CodexOpenAI60.0/1003 independent benchmarks$0.59 per solved taskModel BInklingThinking Machines31.5/1006 independent benchmarks$0.76 per solved task
Shared results
23
GPT-5.3-Codex only
11
Inkling only
83
Like-for-like categories
6 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-5.3-Codex 60.0 from 3 benchmarks, Inkling 31.5 from 6 benchmarks.
Widest category
Agentic work, 20.5 points apart on average over 1 shared benchmark.
Widest single gap
WeirdML: GPT-5.3-Codex 79.3% against Inkling 32.3%, 47.0 points apart on a 0 to 100 scale.
Output price
GPT-5.3-Codex $14.00 against Inkling $4.05 per million output tokens, 3.5x apart.
Context window
GPT-5.3-Codex takes 400K 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
CategoryGPT-5.3-CodexBarsInklingTies
Coding72
Intelligence20
Agentic work01
Reasoning20
Web design35
General10
All shared boards158
CodingLike-for-likeSix of these boards feed the Vibe Coding Index72
Coding benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
LiveBench codingNot measured64.0%Only Inkling measured
LMArena WebDev14071414Inkling
AA Coding IndexNot measured52.1Only Inkling measured
LiveCodeBench (Vals AI)87.3%85.5%GPT-5.3-Codex
SWE-bench Verified (Vals AI)78.0%77.6%GPT-5.3-Codex
Terminal-Bench 4 (Vals AI)Not measured0.5%Only Inkling measured
Vibe Code Bench (Vals AI)61.8%19.2%GPT-5.3-Codex
Code migration (Vals AI)Not measured11.8%Only Inkling measured
ProgramBench (Vals AI)Not measured0.0%Only Inkling measured
IOI (Vals AI)53.8%14.9%GPT-5.3-Codex
Terminal-Bench 2.1 (Vals AI)Not measured47.6%Only Inkling 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
SciCodeNot measured47.0%Only Inkling measured
Terminal-Bench Hard (Artificial Analysis run)53.0%Not measuredOnly GPT-5.3-Codex measured
Terminal-Bench78.4%Not measuredOnly GPT-5.3-Codex measured
FrontierCodeNot measured14.0%Only Inkling measured
FrontierSWENot measured4.1%Only Inkling measured
WeirdML79.3%32.3%GPT-5.3-Codex
ALE-Bench1655.2946.0GPT-5.3-Codex
LMArena Text: codingNot measured1466Only Inkling measured
LMArena Text: software and ITNot measured1465Only Inkling measured
LMArena WebDev: React13951404Inkling
LMArena WebDev: HTML14221399GPT-5.3-Codex
LMArena WebDev: from an image1443Not measuredOnly GPT-5.3-Codex measured
SWE-Bench Pro V2Not measured89.9%Only Inkling measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
AA Intelligence Index32.525.0GPT-5.3-Codex
Epoch Capabilities Index157.1148.4GPT-5.3-Codex
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
AA Agentic IndexNot measured22.5Only Inkling measured
Design Arena: agents building web apps10321196Inkling
Design Arena: agents building full-stack apps983Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building mobile apps1053Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building Android apps1084Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building Godot games1124Not measuredOnly GPT-5.3-Codex measured
LiveBench researchNot measured59.9%Only Inkling measured
LiveBench browserNot measured16.0%Only Inkling measured
LiveBench long agenticNot measured14.1%Only Inkling measured
SREBench (Vals AI)Not measured0.0%Only Inkling measured
Finance Agent (Vals AI)Not measured46.6%Only Inkling measured
Tax Agent Bench (Vals AI)Not measured15.3%Only Inkling measured
Legal Research Bench (Vals AI)Not measured28.4%Only Inkling measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured3.8%Only Inkling measured
Excel Modeling Benchmark (Vals AI)Not measured38.4%Only Inkling measured
τ²-Bench Telecom86.0%Not measuredOnly GPT-5.3-Codex measured
APEX-AgentsNot measured33.8%Only Inkling measured
METR time horizons74.5%Not measuredOnly GPT-5.3-Codex measured
Vending-Bench 2$5,940Not measuredOnly GPT-5.3-Codex measured
MCP AtlasNot measured76.0%Only Inkling measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
GPQA DiamondNot measured87.1%Only Inkling measured
LiveBench reasoningNot measured78.3%Only Inkling measured
MMMU Pro (Vals AI)Not measured78.5%Only Inkling measured
GPQA Diamond (Artificial Analysis run)91.5%87.2%GPT-5.3-Codex
Humanity's Last Exam (Artificial Analysis run)42.5%31.9%GPT-5.3-Codex
GPQA Diamond (Epoch AI run)Not measured88.3%Only Inkling measured
ARC-AGINot measured79.5%Only Inkling measured
ARC-AGI-2Not measured36.5%Only Inkling measured
SimpleBenchNot measured50.0%Only Inkling measured
Chess puzzlesNot measured21.0%Only Inkling measured
LMArena Text: hard promptsNot measured1451Only Inkling measured
LMArena Text: expertNot measured1466Only Inkling measured
LMArena Text: hard prompts in EnglishNot measured1448Only Inkling measured
Humanity's Last Exam (Scale run)Not measured11.2%Only Inkling measured
Neither model has a result on the other 9 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Math benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
OTIS Mock AIMENot measured88.9%Only Inkling measured
FrontierMath, tiers 1 to 3Not measured33.3%Only Inkling measured
FrontierMath, tier 4Not measured4.9%Only Inkling measured
ProofBenchNot measured0.0%Only Inkling measured
LMArena Text: mathNot measured1479Only Inkling measured
LMArena Text: mathematical workNot measured1460Only Inkling measured
Neither model has a result on the other 8 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Knowledge benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
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
SimpleQA VerifiedNot measured40.3%Only Inkling measured
LMArena Text: scienceNot measured1455Only Inkling measured
LMArena Text: medicine and healthcareNot measured1447Only Inkling measured
LMArena Text: legal and governmentNot measured1448Only Inkling measured
LMArena Text: business and financeNot measured1438Only Inkling measured
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index35
Web design benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
Design Arena: websites11621224Inkling
Design Arena: UI components11351199Inkling
Design Arena: game dev11611165Inkling
Design Arena: data viz11641157GPT-5.3-Codex
Design Arena: 3D10071160Inkling
Design Arena: all code categories11441205Inkling
Design Arena: SVG11281108GPT-5.3-Codex
Design Arena: ASCII art11511089GPT-5.3-Codex
LiveBench designNot measured58.3%Only Inkling measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
General benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
Vals IndexNot measured29.0%Only Inkling measured
LiveBench data analysisNot measured72.8%Only Inkling measured
Public Benefits Bench (Vals AI)Not measured58.5%Only Inkling measured
SAGE (Vals AI)Not measured36.5%Only Inkling measured
MedScribe (Vals AI)Not measured85.4%Only Inkling measured
Vals Multimodal IndexNot measured49.4%Only Inkling measured
IFBench75.4%Not measuredOnly GPT-5.3-Codex measured
Long context reasoning (AA-LCR)83.3%77.3%GPT-5.3-Codex
DTBenchNot measured87.5%Only Inkling measured
LMCANot measured37.6%Only Inkling measured
LMArena TextNot measured1442Only Inkling measured
LMArena Text: instruction followingNot measured1425Only Inkling measured
LMArena Text: creative writingNot measured1390Only Inkling measured
LMArena Text: EnglishNot measured1442Only Inkling measured
LMArena Text: non-EnglishNot measured1434Only Inkling measured
LMArena Text: ChineseNot measured1493Only Inkling measured
LMArena Text: GermanNot measured1445Only Inkling measured
LMArena Text: JapaneseNot measured1429Only Inkling measured
LMArena Text: KoreanNot measured1403Only Inkling measured
LMArena Text: FrenchNot measured1455Only Inkling measured
LMArena Text: SpanishNot measured1449Only Inkling measured
LMArena Text: RussianNot measured1430Only Inkling measured
LMArena Text: PolishNot measured1450Only Inkling measured
LMArena Text: multi-turnNot measured1437Only Inkling measured
LMArena Text: longer queriesNot measured1435Only Inkling measured
LMArena Text: writing and languageNot measured1404Only Inkling measured
LMArena Text: entertainment and mediaNot measured1394Only Inkling measured
EQ-Bench 4Not measured1226Only Inkling measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.3-Codex and Inkling
BenchmarkGPT-5.3-CodexInklingLeader
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-5.3-Codex$0.0088Fits in one request
Inkling$0.0030Fits in one request

Inkling costs less

Repository review

50K input + 3K output tokens

GPT-5.3-Codex$0.130Fits in one request
Inkling$0.062Fits in one request

Inkling costs less

Agent loop

200K input + 10K output tokens

GPT-5.3-Codex$0.490Fits 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 GPT-5.3-Codex and Inkling
SpecificationOpenAI GPT-5.3-CodexThinking Machines Inkling
MakerOpenAIThinking Machines
WeightsNo public weights listedOpen weights
ReleasedFebruary 24, 2026July 17, 2026
Context window400K524K
Input $/Mtok$1.75$1.00
Output $/Mtok$14.00$4.05
Coding index60.031.5
Independent measurements behind it36
Cost per solved task$0.59$0.76
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.3-Codex better than Inkling for coding?

Pick GPT-5.3-Codex for coding: it scores 60.0 on the Vibe Coding Index against 31.5 for Inkling, though on 3 benchmarks against 6. Pick Inkling for output tokens 3.5x cheaper ($4.05 vs $14.00 per million) and a larger context window (524K against 400K tokens).

Which is cheaper, GPT-5.3-Codex or Inkling?

GPT-5.3-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; Inkling costs $1.00 and $4.05. Per solved SWE-bench Verified task, GPT-5.3-Codex costs $0.59 and Inkling $0.76.

Which has the bigger context window, GPT-5.3-Codex or Inkling?

Inkling, with 524K tokens against 400K.

How many benchmarks is the GPT-5.3-Codex vs Inkling comparison based on?

23 benchmarks have a result for both models as of October 22, 2026. GPT-5.3-Codex's coding index rests on 3 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/gpt-5-3-codex-vs-thinkingmachines-inkling" title="GPT-5.3-Codex 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/gpt-5-3-codex-vs-thinkingmachines-inkling">LLMBenchmark.ai, GPT-5.3-Codex vs Inkling</a></p>