Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs GPT-5 Nano

GPT-5.4 Nano leads GPT-5 Nano on the Artificial Analysis Intelligence Index, 20.7 to 13.0, and GPT-5 Nano costs 3.1x less per output token ($0.40 vs $1.25 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace GPT-5 Nano
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
63
GPT-5 NanoOpenAI
Coding
No data
Overall
35.6
Output $/M
$0.40
3
vs boards won of 68 shared, 2 tied

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

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; GPT-5 Nano has none, so the two cannot be ranked on coding.

Pick GPT-5 Nano for output tokens 3.1x cheaper ($0.40 vs $1.25 per million) and a lower cost per solved task ($0.109 against $0.14).

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel BGPT-5 NanoOpenAINot benchmarkedNo coding benchmark$0.109 per solved task
Shared results
68
GPT-5.4 Nano only
17
GPT-5 Nano only
19
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 Nano 44.8 from 2 benchmarks, GPT-5 Nano not benchmarked.
Widest category
Agentic work, 39.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GPT-5.4 Nano 76.0% against GPT-5 Nano 36.5%, 39.5 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against GPT-5 Nano $0.40 per million output tokens, 3.1x 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-5.4 NanoBarsGPT-5 NanoTies
Coding50
Intelligence20
Agentic work10
Reasoning1311 tie
Math61
Knowledge911 tie
General270
All shared boards6332 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
SWE-bench VerifiedNot measured34.8%Only GPT-5 Nano measured
AA Coding Index56.1Not measuredOnly GPT-5.4 Nano measured
LiveCodeBench (Vals AI)84.0%70.2%GPT-5.4 Nano
SWE-bench Verified (Vals AI)69.8%Not measuredOnly GPT-5.4 Nano measured
Vibe Code Bench (Vals AI)26.1%Not measuredOnly GPT-5.4 Nano measured
Code migration (Vals AI)14.5%Not measuredOnly GPT-5.4 Nano measured
Terminal-Bench 2.1 (Vals AI)41.6%Not measuredOnly GPT-5.4 Nano measured
LiveCodeBench (Artificial Analysis run)Not measured78.9%Only GPT-5 Nano measured
SciCode47.2%Not measuredOnly GPT-5.4 Nano measured
Terminal-Bench Hard (Artificial Analysis run)42.4%17.4%GPT-5.4 Nano
Terminal-BenchNot measured21.8%Only GPT-5 Nano measured
WeirdML49.2%38.1%GPT-5.4 Nano
ALE-Bench1004.5Not measuredOnly GPT-5.4 Nano measured
LMArena Text: coding14041351GPT-5.4 Nano
LMArena Text: software and IT14021345GPT-5.4 Nano
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
AA Intelligence Index20.713.0GPT-5.4 Nano
Epoch Capabilities Index146.0139.2GPT-5.4 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
AA Agentic Index16.0Not measuredOnly GPT-5.4 Nano measured
Finance Agent (Vals AI)38.2%Not measuredOnly GPT-5.4 Nano measured
Tax Agent Bench (Vals AI)5.0%Not measuredOnly GPT-5.4 Nano measured
Legal Research Bench (Vals AI)6.3%Not measuredOnly GPT-5.4 Nano measured
Excel Modeling Benchmark (Vals AI)44.8%Not measuredOnly GPT-5.4 Nano measured
τ²-Bench Telecom76.0%36.5%GPT-5.4 Nano
Berkeley Function Calling Leaderboard (BFCL)Not measured51.4%Only GPT-5 Nano measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index131
Reasoning benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
GPQA Diamond77.5%63.4%GPT-5.4 Nano
MMMU Pro (Vals AI)73.6%70.9%GPT-5.4 Nano
GPQA Diamond (Artificial Analysis run)81.7%67.6%GPT-5.4 Nano
Humanity's Last Exam (Artificial Analysis run)28.3%9.5%GPT-5.4 Nano
GPQA Diamond (Epoch AI run)78.5%69.4%GPT-5.4 Nano
ARC-AGI51.5%20.7%GPT-5.4 Nano
ARC-AGI-25.7%2.6%GPT-5.4 Nano
Chess puzzles45.0%22.0%GPT-5.4 Nano
Mystery game puzzles9.0%9.0%Tie
VPCTNot measured37.2%Only GPT-5 Nano measured
LMArena Text: hard prompts13811328GPT-5.4 Nano
LMArena Text: expert13961321GPT-5.4 Nano
LMArena Text: hard prompts in English13871338GPT-5.4 Nano
LMArena Vision: diagrams12101141GPT-5.4 Nano
LMArena Vision: homework12251157GPT-5.4 Nano
Kagi LLM Benchmark39.7%62.2%GPT-5 Nano
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index61
Math benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
AIME88.8%81.2%GPT-5.4 Nano
MATH 500 (Vals AI)Not measured93.8%Only GPT-5 Nano measured
MGSM (Vals AI)Not measured89.3%Only GPT-5 Nano measured
AA Math IndexNot measured83.7Only GPT-5 Nano measured
AIME 2025 (Artificial Analysis run)Not measured83.7%Only GPT-5 Nano measured
OTIS Mock AIME87.8%81.1%GPT-5.4 Nano
FrontierMath, tiers 1 to 344.9%20.0%GPT-5.4 Nano
FrontierMath, tier 412.2%2.4%GPT-5.4 Nano
ProofBench5.0%12.0%GPT-5 Nano
MATH level 5Not measured95.2%Only GPT-5 Nano measured
LMArena Text: math14051317GPT-5.4 Nano
LMArena Text: mathematical work14091326GPT-5.4 Nano
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
Knowledge benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
MMLU Pro77.2%76.1%GPT-5.4 Nano
LegalBench (Vals AI)77.9%50.1%GPT-5.4 Nano
CaseLaw (Vals AI)51.9%52.6%GPT-5 Nano
CorpFin (Vals AI)61.2%Not measuredOnly GPT-5.4 Nano measured
TaxEval (Vals AI)67.4%67.4%GPT-5.4 Nano
MortgageTax (Vals AI)59.1%53.6%GPT-5.4 Nano
MedQA (Vals AI)Not measured93.3%Only GPT-5 Nano measured
MedCode (Vals AI)41.0%30.4%GPT-5.4 Nano
MMLU Pro (Artificial Analysis run)Not measured78.0%Only GPT-5 Nano measured
SimpleQA Verified11.7%11.7%Tie
LMArena Text: science13741318GPT-5.4 Nano
LMArena Text: medicine and healthcare13691335GPT-5.4 Nano
LMArena Text: legal and government13681298GPT-5.4 Nano
LMArena Text: business and finance13661311GPT-5.4 Nano
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
Design Arena: websitesNot measured1101Only GPT-5 Nano measured
Design Arena: UI componentsNot measured1064Only GPT-5 Nano measured
Design Arena: game devNot measured1044Only GPT-5 Nano measured
Design Arena: data vizNot measured1056Only GPT-5 Nano measured
Design Arena: 3DNot measured965Only GPT-5 Nano measured
Design Arena: all code categoriesNot measured1084Only GPT-5 Nano measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index270
General benchmarks for GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 NanoLeader
SAGE (Vals AI)38.1%30.4%GPT-5.4 Nano
MedScribe (Vals AI)77.1%72.9%GPT-5.4 Nano
Vals Multimodal Index47.6%Not measuredOnly GPT-5.4 Nano measured
IFBench75.9%67.6%GPT-5.4 Nano
Long context reasoning (AA-LCR)76.7%45.0%GPT-5.4 Nano
DTBench80.3%62.7%GPT-5.4 Nano
LMCA36.9%7.9%GPT-5.4 Nano
Fiction.LiveBenchNot measured44.4%Only GPT-5 Nano measured
LMArena Text13721320GPT-5.4 Nano
LMArena Text: instruction following13621306GPT-5.4 Nano
LMArena Text: creative writing13151249GPT-5.4 Nano
LMArena Vision11961159GPT-5.4 Nano
LMArena Text: English13811321GPT-5.4 Nano
LMArena Text: non-English13591313GPT-5.4 Nano
LMArena Text: Chinese13911356GPT-5.4 Nano
LMArena Text: German13681327GPT-5.4 Nano
LMArena Text: Japanese13431227GPT-5.4 Nano
LMArena Text: Korean13211269GPT-5.4 Nano
LMArena Text: French1395Not measuredOnly GPT-5.4 Nano measured
LMArena Text: Spanish13711360GPT-5.4 Nano
LMArena Text: Russian13631296GPT-5.4 Nano
LMArena Text: Polish13661314GPT-5.4 Nano
LMArena Text: multi-turn13821311GPT-5.4 Nano
LMArena Text: longer queries13651312GPT-5.4 Nano
LMArena Text: writing and language13381283GPT-5.4 Nano
LMArena Text: entertainment and media13251268GPT-5.4 Nano
LMArena Vision: English12021170GPT-5.4 Nano
LMArena Vision: Chinese12321176GPT-5.4 Nano
LMArena Vision: reading text12041152GPT-5.4 Nano
LMArena Vision: humor11611110GPT-5.4 Nano
LMArena Vision: recognizing things1141Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: creative writing1159Not measuredOnly GPT-5.4 Nano 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 GPT-5.4 Nano and GPT-5 Nano
BenchmarkGPT-5.4 NanoGPT-5 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-5.4 Nano$0.0008Fits in one request
GPT-5 Nano$0.0003Fits in one request

GPT-5 Nano costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Nano$0.014Fits in one request
GPT-5 Nano$0.0037Fits in one request

GPT-5 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Nano$0.052Fits in one request
GPT-5 Nano$0.014Fits in one request

GPT-5 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-5.4 Nano and GPT-5 Nano
SpecificationOpenAI GPT-5.4 NanoOpenAI GPT-5 Nano
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 17, 2026August 7, 2025
Context window400K400K
Input $/Mtok$0.20$0.05
Output $/Mtok$1.25$0.40
Coding index44.8Not benchmarked
Independent measurements behind it20
Cost per solved task$0.14$0.109
SourceOpenRouter listingOpenRouter listing

Questions

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

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; GPT-5 Nano has none, so the two cannot be ranked on coding. Pick GPT-5 Nano for output tokens 3.1x cheaper ($0.40 vs $1.25 per million) and a lower cost per solved task ($0.109 against $0.14).

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

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; GPT-5 Nano costs $0.05 and $0.40. Per solved SWE-bench Verified task, GPT-5.4 Nano costs $0.14 and GPT-5 Nano $0.109.

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

Neither: both take 400K tokens.

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

68 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Nano's coding index rests on 2 independent benchmarks and GPT-5 Nano's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next