Enter opens the highlighted result. Esc closes.

GPT-5 vs GPT-5.4 Nano

GPT-5.4 Nano leads GPT-5 on coding, 44.8 to 38.8 on the Vibe Coding Index, and GPT-5.4 Nano costs 8.0x less per output token ($1.25 vs $10.00 per million). Updated October 23, 2026; 76 benchmarks have a result for both.

Replace GPT-5 Replace GPT-5.4 Nano
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
67
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.8
Output $/M
$1.25
9
vs boards won of 76 shared

GPT-5 or GPT-5.4 Nano: which to pick

Pick GPT-5.4 Nano for coding: it scores 44.8 on the Vibe Coding Index against 38.8 for GPT-5, though on 2 benchmarks against 3.

Pick GPT-5 for work measured by LiveCodeBench (Vals AI) or WeirdML, where it leads.

Model AGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved taskModel BGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved task
Shared results
76
GPT-5 only
41
GPT-5.4 Nano only
9
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 38.8 from 3 benchmarks, GPT-5.4 Nano 44.8 from 2 benchmarks.
Widest category
Agentic work, 10.5 points apart on average over 1 shared benchmark.
Widest single gap
SimpleQA Verified: GPT-5 50.1% against GPT-5.4 Nano 11.7%, 38.4 points apart on a 0 to 100 scale.
Output price
GPT-5 $10.00 against GPT-5.4 Nano $1.25 per million output tokens, 8.0x apart.
Context window
Both take 400K 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
CategoryGPT-5BarsGPT-5.4 NanoTies
Coding45
Intelligence20
Agentic work10
Reasoning141
Math61
Knowledge111
General291
All shared boards679
CodingLike-for-likeSix of these boards feed the Vibe Coding Index45
Coding benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
Aider polyglot88.0%Not measuredOnly GPT-5 measured
SWE-bench Verified74.4%Not measuredOnly GPT-5 measured
LMArena WebDev1418Not measuredOnly GPT-5 measured
AA Coding Index37.856.1GPT-5.4 Nano
LiveCodeBench (Vals AI)85.9%84.0%GPT-5
SWE-bench Verified (Vals AI)69.0%69.8%GPT-5.4 Nano
Vibe Code Bench (Vals AI)20.1%26.1%GPT-5.4 Nano
Code migration (Vals AI)Not measured14.5%Only GPT-5.4 Nano measured
Terminal-Bench 2.1 (Vals AI)Not measured41.6%Only GPT-5.4 Nano measured
LiveCodeBench (Artificial Analysis run)84.6%Not measuredOnly GPT-5 measured
SciCodeNot measured47.2%Only GPT-5.4 Nano measured
Terminal-Bench Hard (Artificial Analysis run)37.9%42.4%GPT-5.4 Nano
Terminal-Bench49.6%Not measuredOnly GPT-5 measured
GSO-Bench6.9%Not measuredOnly GPT-5 measured
WeirdML60.7%49.2%GPT-5
ALE-Bench807.61004.5GPT-5.4 Nano
LMArena Text: coding14361405GPT-5
LMArena Text: software and IT14201403GPT-5
LMArena WebDev: HTML1426Not measuredOnly GPT-5 measured
SciCode0.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
AA Intelligence Index23.020.7GPT-5
Epoch Capabilities Index150.0146.0GPT-5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
AA Agentic IndexNot measured16.0Only GPT-5.4 Nano measured
Finance Agent (Vals AI)Not measured38.2%Only GPT-5.4 Nano measured
Tax Agent Bench (Vals AI)Not measured5.0%Only GPT-5.4 Nano measured
Legal Research Bench (Vals AI)Not measured6.3%Only GPT-5.4 Nano measured
Excel Modeling Benchmark (Vals AI)Not measured44.8%Only GPT-5.4 Nano measured
τ²-Bench Telecom86.5%76.0%GPT-5
METR time horizons69.6%Not measuredOnly GPT-5 measured
Remote Labor Index1.7%Not measuredOnly GPT-5 measured
GDPval34.8%Not measuredOnly GPT-5 measured
BALROG32.8%Not measuredOnly GPT-5 measured
DeepResearch Bench49.6%Not measuredOnly GPT-5 measured
BrowseComp-Plus80.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index141
Reasoning benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
GPQA Diamond85.6%77.5%GPT-5
MMMU Pro (Vals AI)81.5%73.6%GPT-5
GPQA Diamond (Artificial Analysis run)85.4%81.7%GPT-5
Humanity's Last Exam (Artificial Analysis run)28.5%28.3%GPT-5
GPQA Diamond (Epoch AI run)86.2%78.5%GPT-5
ARC-AGI65.7%51.5%GPT-5
ARC-AGI-29.9%5.7%GPT-5
SimpleBench56.7%Not measuredOnly GPT-5 measured
Chess puzzles36.0%45.0%GPT-5.4 Nano
Mystery game puzzles23.0%9.0%GPT-5
EBR-bench12.7%Not measuredOnly GPT-5 measured
VPCT66.0%Not measuredOnly GPT-5 measured
LMArena Text: hard prompts14151381GPT-5
LMArena Text: expert14191396GPT-5
LMArena Text: hard prompts in English14191387GPT-5
LMArena Vision: diagrams12521210GPT-5
LMArena Vision: homework12781225GPT-5
Kagi LLM Benchmark72.7%39.7%GPT-5
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index61
Math benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
AIME93.4%88.8%GPT-5
MATH 500 (Vals AI)96.0%Not measuredOnly GPT-5 measured
MGSM (Vals AI)92.8%Not measuredOnly GPT-5 measured
AA Math Index94.3Not measuredOnly GPT-5 measured
AIME 2025 (Artificial Analysis run)94.3%Not measuredOnly GPT-5 measured
OTIS Mock AIME91.4%87.8%GPT-5
FrontierMath, tiers 1 to 355.4%44.9%GPT-5
FrontierMath, tier 422.0%12.2%GPT-5
ProofBench18.0%5.0%GPT-5
MATH level 598.1%Not measuredOnly GPT-5 measured
LMArena Text: math14071406GPT-5
LMArena Text: mathematical work14051409GPT-5.4 Nano
MathArena17.1%Not measuredOnly GPT-5 measured
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
MMLU Pro86.5%77.2%GPT-5
LegalBench (Vals AI)86.0%77.9%GPT-5
CaseLaw (Vals AI)66.5%51.9%GPT-5
CorpFin (Vals AI)61.1%61.2%GPT-5.4 Nano
TaxEval (Vals AI)73.4%67.4%GPT-5
MortgageTax (Vals AI)65.5%59.1%GPT-5
MedQA (Vals AI)96.3%Not measuredOnly GPT-5 measured
MedCode (Vals AI)49.6%41.0%GPT-5
MMLU Pro (Artificial Analysis run)87.1%Not measuredOnly GPT-5 measured
SimpleQA Verified50.1%11.7%GPT-5
GeoBench81.0%Not measuredOnly GPT-5 measured
LMArena Text: science14161374GPT-5
LMArena Text: medicine and healthcare14131369GPT-5
LMArena Text: legal and government14311368GPT-5
LMArena Text: business and finance13991366GPT-5
FACTS Benchmark Suite56.5%Not measuredOnly GPT-5 measured
PRBench Finance51.3%Not measuredOnly GPT-5 measured
PRBench Legal49.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
Design Arena: websites1184Not measuredOnly GPT-5 measured
Design Arena: UI components1177Not measuredOnly GPT-5 measured
Design Arena: game dev1185Not measuredOnly GPT-5 measured
Design Arena: data viz1222Not measuredOnly GPT-5 measured
Design Arena: 3D1056Not measuredOnly GPT-5 measured
Design Arena: all code categories1167Not measuredOnly GPT-5 measured
Design Arena: SVG1188Not measuredOnly GPT-5 measured
Design Arena: ASCII art1141Not measuredOnly GPT-5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index291
General benchmarks for GPT-5 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
SAGE (Vals AI)43.7%38.1%GPT-5
MedScribe (Vals AI)83.7%77.1%GPT-5
Vals Multimodal IndexNot measured47.6%Only GPT-5.4 Nano measured
IFBench73.1%75.9%GPT-5.4 Nano
Long context reasoning (AA-LCR)78.2%76.7%GPT-5
DTBench90.7%80.3%GPT-5
LMCA40.0%36.9%GPT-5
Fiction.LiveBench97.2%Not measuredOnly GPT-5 measured
Creative writing (Lech Mazur)86.0%Not measuredOnly GPT-5 measured
LMArena Text14061372GPT-5
LMArena Text: instruction following13881362GPT-5
LMArena Text: creative writing13651314GPT-5
LMArena Vision12321196GPT-5
LMArena Text: English14091381GPT-5
LMArena Text: non-English13971360GPT-5
LMArena Text: Chinese14221391GPT-5
LMArena Text: German14161368GPT-5
LMArena Text: Japanese14091343GPT-5
LMArena Text: Korean13601320GPT-5
LMArena Text: French14091395GPT-5
LMArena Text: Spanish13991371GPT-5
LMArena Text: Russian14071362GPT-5
LMArena Text: Polish14311366GPT-5
LMArena Text: multi-turn14261382GPT-5
LMArena Text: longer queries13991366GPT-5
LMArena Text: writing and language13841338GPT-5
LMArena Text: entertainment and media13791324GPT-5
LMArena Vision: English12311202GPT-5
LMArena Vision: Chinese12671232GPT-5
LMArena Vision: reading text12461204GPT-5
LMArena Vision: humor12191161GPT-5
LMArena Vision: captioning1212Not measuredOnly GPT-5 measured
LMArena Vision: recognizing things12631141GPT-5
LMArena Vision: creative writing12101159GPT-5
MultiChallenge63.2%Not measuredOnly GPT-5 measured
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 and GPT-5.4 Nano
BenchmarkGPT-5GPT-5.4 NanoLeader
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$0.0063Fits in one request
GPT-5.4 Nano$0.0008Fits in one request

GPT-5.4 Nano costs less

Repository review

50K input + 3K output tokens

GPT-5$0.092Fits in one request
GPT-5.4 Nano$0.014Fits in one request

GPT-5.4 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-5$0.350Fits in one request
GPT-5.4 Nano$0.052Fits in one request

GPT-5.4 Nano 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 and GPT-5.4 Nano
SpecificationOpenAI GPT-5OpenAI GPT-5.4 Nano
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025March 17, 2026
Context window400K400K
Input $/Mtok$1.25$0.20
Output $/Mtok$10.00$1.25
Coding index38.844.8
Independent measurements behind it32
Cost per solved task$0.39$0.14
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 better than GPT-5.4 Nano for coding?

Pick GPT-5.4 Nano for coding: it scores 44.8 on the Vibe Coding Index against 38.8 for GPT-5, though on 2 benchmarks against 3. Pick GPT-5 for work measured by LiveCodeBench (Vals AI) or WeirdML, where it leads.

Which is cheaper, GPT-5 or GPT-5.4 Nano?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5.4 Nano costs $0.20 and $1.25. Per solved SWE-bench Verified task, GPT-5 costs $0.39 and GPT-5.4 Nano $0.14.

Which has the bigger context window, GPT-5 or GPT-5.4 Nano?

Neither: both take 400K tokens.

How many benchmarks is the GPT-5 vs GPT-5.4 Nano comparison based on?

76 benchmarks have a result for both models as of October 23, 2026. GPT-5's coding index rests on 3 independent benchmarks and GPT-5.4 Nano's on 2. 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-vs-gpt-5-4-nano" title="GPT-5 vs GPT-5.4 Nano, 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-vs-gpt-5-4-nano">LLMBenchmark.ai, GPT-5 vs GPT-5.4 Nano</a></p>