Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs GPT-5.5

GPT-5.5 leads GPT-5.4 Nano on coding, 71.3 to 44.8 on the Vibe Coding Index, and GPT-5.4 Nano costs 24.0x less per output token ($1.25 vs $30.00 per million). Updated October 22, 2026; 84 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace GPT-5.5
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
2
GPT-5.5OpenAI
Coding
71.3
Overall
69.2
Output $/M
$30.00
82
vs boards won of 84 shared

GPT-5.4 Nano or GPT-5.5: which to pick

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano.

Pick GPT-5.4 Nano for output tokens 24.0x cheaper ($1.25 vs $30.00 per million) and a lower cost per solved task ($0.14 against $1.65).

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel BGPT-5.5OpenAI71.3/1005 independent benchmarks$1.65 per solved task
Shared results
84
GPT-5.4 Nano only
1
GPT-5.5 only
50
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-5.5 71.3 from 5 benchmarks.
Widest category
Math, 29.5 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI-2: GPT-5.4 Nano 5.7% against GPT-5.5 85.0%, 79.3 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against GPT-5.5 $30.00 per million output tokens, 24.0x apart.
Context window
GPT-5.4 Nano takes 400K tokens, GPT-5.5 1.05M.

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-5.5Ties
Coding012
Intelligence02
Agentic work06
Reasoning015
Math15
Knowledge012
General130
All shared boards282
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
LiveBench codingNot measured85.1%Only GPT-5.5 measured
LMArena WebDevNot measured1513Only GPT-5.5 measured
AA Coding Index56.174.9GPT-5.5
LiveCodeBench (Vals AI)84.0%85.3%GPT-5.5
SWE-bench Verified (Vals AI)69.8%82.6%GPT-5.5
Vibe Code Bench (Vals AI)26.1%69.8%GPT-5.5
Code migration (Vals AI)14.5%45.2%GPT-5.5
ProgramBench (Vals AI)Not measured0.5%Only GPT-5.5 measured
Terminal-Bench 2.1 (Vals AI)41.6%76.4%GPT-5.5
SkillsBench (Vals AI)Not measured62.5%Only GPT-5.5 measured
SciCode47.2%56.1%GPT-5.5
Terminal-Bench Hard (Artificial Analysis run)42.4%60.6%GPT-5.5
Terminal-BenchNot measured84.7%Only GPT-5.5 measured
FrontierCodeNot measured43.0%Only GPT-5.5 measured
GSO-BenchNot measured40.2%Only GPT-5.5 measured
WeirdML49.2%84.9%GPT-5.5
MirrorCodeNot measured10.0%Only GPT-5.5 measured
ALE-Bench1004.51943.0GPT-5.5
LMArena Text: coding14041494GPT-5.5
LMArena Text: software and IT14021493GPT-5.5
LMArena WebDev: ReactNot measured1506Only GPT-5.5 measured
LMArena WebDev: HTMLNot measured1543Only GPT-5.5 measured
LMArena WebDev: from an imageNot measured1532Only GPT-5.5 measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
AA Intelligence Index20.738.4GPT-5.5
Epoch Capabilities Index146.0159.7GPT-5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
Agentic work benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
AA Agentic Index16.036.4GPT-5.5
Design Arena: agents building web appsNot measured1117Only GPT-5.5 measured
Design Arena: agents building full-stack appsNot measured1089Only GPT-5.5 measured
Design Arena: agents building mobile appsNot measured1142Only GPT-5.5 measured
Design Arena: agents building Android appsNot measured1164Only GPT-5.5 measured
Design Arena: agents building Godot gamesNot measured1173Only GPT-5.5 measured
Design Arena: agents building gamesNot measured1179Only GPT-5.5 measured
Design Arena: HTML slidesNot measured1017Only GPT-5.5 measured
Design Arena: PowerPoint slidesNot measured1084Only GPT-5.5 measured
LiveBench researchNot measured61.6%Only GPT-5.5 measured
LiveBench browserNot measured48.0%Only GPT-5.5 measured
LiveBench long agenticNot measured44.6%Only GPT-5.5 measured
SREBench (Vals AI)Not measured3.8%Only GPT-5.5 measured
Finance Agent (Vals AI)38.2%51.8%GPT-5.5
Tax Agent Bench (Vals AI)5.0%21.8%GPT-5.5
Legal Research Bench (Vals AI)6.3%40.4%GPT-5.5
Excel Modeling Benchmark (Vals AI)44.8%64.5%GPT-5.5
Time Horizon Index (Vals AI)Not measured8.3%Only GPT-5.5 measured
τ²-Bench Telecom76.0%93.9%GPT-5.5
APEX-AgentsNot measured55.1%Only GPT-5.5 measured
Remote Labor IndexNot measured6.3%Only GPT-5.5 measured
OSWorld 2.0Not measured13.0%Only GPT-5.5 measured
DeepResearch BenchNot measured54.0%Only GPT-5.5 measured
PostTrainBenchNot measured27.2%Only GPT-5.5 measured
Vending-Bench 2Not measured$7,524Only GPT-5.5 measured
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index015
Reasoning benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
GPQA Diamond77.5%93.2%GPT-5.5
LiveBench reasoningNot measured89.7%Only GPT-5.5 measured
MMMU Pro (Vals AI)73.6%88.3%GPT-5.5
GPQA Diamond (Artificial Analysis run)81.7%93.5%GPT-5.5
Humanity's Last Exam (Artificial Analysis run)28.3%45.8%GPT-5.5
GPQA Diamond (Epoch AI run)78.5%90.7%GPT-5.5
ARC-AGI51.5%95.0%GPT-5.5
ARC-AGI-25.7%85.0%GPT-5.5
SimpleBenchNot measured69.0%Only GPT-5.5 measured
Chess puzzles45.0%63.0%GPT-5.5
Mystery game puzzles9.0%56.0%GPT-5.5
EBR-benchNot measured34.3%Only GPT-5.5 measured
LMArena Text: hard prompts13811489GPT-5.5
LMArena Text: expert13961507GPT-5.5
LMArena Text: hard prompts in English13871483GPT-5.5
LMArena Vision: diagrams12101325GPT-5.5
LMArena Vision: homework12251332GPT-5.5
Kagi LLM Benchmark39.7%88.8%GPT-5.5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
AIME88.8%Not measuredOnly GPT-5.4 Nano measured
OTIS Mock AIME87.8%84.4%GPT-5.4 Nano
FrontierMath, tiers 1 to 344.9%85.3%GPT-5.5
FrontierMath, tier 412.2%72.5%GPT-5.5
ProofBench5.0%50.0%GPT-5.5
LMArena Text: math14051487GPT-5.5
LMArena Text: mathematical work14091496GPT-5.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index012
Knowledge benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
MMLU Pro77.2%88.1%GPT-5.5
LegalBench (Vals AI)77.9%86.5%GPT-5.5
CaseLaw (Vals AI)51.9%66.2%GPT-5.5
CorpFin (Vals AI)61.2%68.4%GPT-5.5
TaxEval (Vals AI)67.4%75.0%GPT-5.5
MortgageTax (Vals AI)59.1%68.8%GPT-5.5
MedCode (Vals AI)41.0%49.1%GPT-5.5
SimpleQA Verified11.7%63.0%GPT-5.5
LMArena Text: science13741485GPT-5.5
LMArena Text: medicine and healthcare13691465GPT-5.5
LMArena Text: legal and government13681491GPT-5.5
LMArena Text: business and finance13661478GPT-5.5
FACTS Benchmark SuiteNot measured66.7%Only GPT-5.5 measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
Design Arena: websitesNot measured1256Only GPT-5.5 measured
Design Arena: UI componentsNot measured1257Only GPT-5.5 measured
Design Arena: game devNot measured1293Only GPT-5.5 measured
Design Arena: data vizNot measured1264Only GPT-5.5 measured
Design Arena: 3DNot measured1197Only GPT-5.5 measured
Design Arena: all code categoriesNot measured1260Only GPT-5.5 measured
Design Arena: SVGNot measured1234Only GPT-5.5 measured
Design Arena: ASCII artNot measured1255Only GPT-5.5 measured
LiveBench designNot measured70.3%Only GPT-5.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
General benchmarks for GPT-5.4 Nano and GPT-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
LiveBench data analysisNot measured81.6%Only GPT-5.5 measured
Public Benefits Bench (Vals AI)Not measured60.9%Only GPT-5.5 measured
SAGE (Vals AI)38.1%51.5%GPT-5.5
MedScribe (Vals AI)77.1%86.9%GPT-5.5
Vals Multimodal Index47.6%68.1%GPT-5.5
IFBench75.9%75.9%GPT-5.4 Nano
Long context reasoning (AA-LCR)76.7%84.3%GPT-5.5
DTBench80.3%96.0%GPT-5.5
LMCA36.9%54.3%GPT-5.5
Surface Evolver BenchNot measured88.1%Only GPT-5.5 measured
Furniture assemblyNot measured44.2%Only GPT-5.5 measured
ExploitBenchNot measured47.4%Only GPT-5.5 measured
CL-bench LifeNot measured22.2%Only GPT-5.5 measured
LMArena Text13721471GPT-5.5
LMArena Text: instruction following13621478GPT-5.5
LMArena Text: creative writing13151455GPT-5.5
LMArena Vision11961297GPT-5.5
LMArena Text: English13811470GPT-5.5
LMArena Text: non-English13591467GPT-5.5
LMArena Text: Chinese13911534GPT-5.5
LMArena Text: German13681480GPT-5.5
LMArena Text: Japanese13431499GPT-5.5
LMArena Text: Korean13211460GPT-5.5
LMArena Text: French13951485GPT-5.5
LMArena Text: Spanish13711468GPT-5.5
LMArena Text: Russian13631473GPT-5.5
LMArena Text: Polish13661465GPT-5.5
LMArena Text: multi-turn13821476GPT-5.5
LMArena Text: longer queries13651484GPT-5.5
LMArena Text: writing and language13381466GPT-5.5
LMArena Text: entertainment and media13251449GPT-5.5
LMArena Vision: English12021292GPT-5.5
LMArena Vision: Chinese12321360GPT-5.5
LMArena Vision: reading text12041306GPT-5.5
LMArena Vision: humor11611293GPT-5.5
LMArena Vision: recognizing things11411231GPT-5.5
LMArena Vision: creative writing11591301GPT-5.5
LMArena DocumentNot measured1486Only GPT-5.5 measured
Neither model has a result on the other 8 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-5.5
BenchmarkGPT-5.4 NanoGPT-5.5Leader
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-5.5$0.020Fits in one request

GPT-5.4 Nano costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Nano$0.014Fits in one request
GPT-5.5$0.340Fits in one request

GPT-5.4 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Nano$0.052Fits in one request
GPT-5.5$1.30Fits 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-5.4 Nano and GPT-5.5
SpecificationOpenAI GPT-5.4 NanoOpenAI GPT-5.5
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 17, 2026April 24, 2026
Context window400K1.05M
Input $/Mtok$0.20$5.00
Output $/Mtok$1.25$30.00
Coding index44.871.3
Independent measurements behind it25
Cost per solved task$0.14$1.65
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Nano better than GPT-5.5 for coding?

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano. Pick GPT-5.4 Nano for output tokens 24.0x cheaper ($1.25 vs $30.00 per million) and a lower cost per solved task ($0.14 against $1.65).

Which is cheaper, GPT-5.4 Nano or GPT-5.5?

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; GPT-5.5 costs $5.00 and $30.00. Per solved SWE-bench Verified task, GPT-5.4 Nano costs $0.14 and GPT-5.5 $1.65.

Which has the bigger context window, GPT-5.4 Nano or GPT-5.5?

GPT-5.5, with 1.05M tokens against 400K.

How many benchmarks is the GPT-5.4 Nano vs GPT-5.5 comparison based on?

84 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-5.5's on 5. 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-nano-vs-gpt-5-5" title="GPT-5.4 Nano vs GPT-5.5, 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-nano-vs-gpt-5-5">LLMBenchmark.ai, GPT-5.4 Nano vs GPT-5.5</a></p>