Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs GPT-5.6 Luna

GPT-5.6 Luna leads GPT-5.4 Nano on coding, 58.0 to 44.8 on the Vibe Coding Index, at about the same output price ($1.20 vs $1.25 per million). Updated October 22, 2026; 78 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace GPT-5.6 Luna
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
1
GPT-5.6 LunaOpenAI
Coding
58.0
Overall
61.6
Output $/M
$1.20
77
vs boards won of 78 shared

GPT-5.4 Nano or GPT-5.6 Luna: which to pick

Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano.

Pick GPT-5.4 Nano for work measured by Chess puzzles, where it leads.

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel BGPT-5.6 LunaOpenAI58.0/1006 independent benchmarks$0.04 per solved task
Shared results
78
GPT-5.4 Nano only
7
GPT-5.6 Luna only
42
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-5.6 Luna 58.0 from 6 benchmarks.
Widest category
Math, 28.4 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: GPT-5.4 Nano 5.0% against GPT-5.6 Luna 60.0%, 55.0 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against GPT-5.6 Luna $1.20 per million output tokens, 1.0x apart.
Context window
GPT-5.4 Nano takes 400K tokens, GPT-5.6 Luna 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-5.6 LunaTies
Coding010
Intelligence02
Agentic work05
Reasoning114
Math06
Knowledge011
General029
All shared boards177
CodingLike-for-likeSix of these boards feed the Vibe Coding Index010
Coding benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
LiveBench codingNot measured73.6%Only GPT-5.6 Luna measured
LMArena WebDevNot measured1518Only GPT-5.6 Luna measured
AA Coding Index56.171.4GPT-5.6 Luna
LiveCodeBench (Vals AI)84.0%Not measuredOnly GPT-5.4 Nano measured
SWE-bench Verified (Vals AI)69.8%93.0%GPT-5.6 Luna
Terminal-Bench 4 (Vals AI)Not measured11.6%Only GPT-5.6 Luna measured
Vibe Code Bench (Vals AI)26.1%77.1%GPT-5.6 Luna
Code migration (Vals AI)14.5%44.5%GPT-5.6 Luna
ProgramBench (Vals AI)Not measured0.0%Only GPT-5.6 Luna measured
IOI (Vals AI)Not measured61.8%Only GPT-5.6 Luna measured
Terminal-Bench 2.1 (Vals AI)41.6%79.0%GPT-5.6 Luna
Vibe Code Bench 1-100 (Vals AI)Not measured22.6%Only GPT-5.6 Luna measured
SkillsBench (Vals AI)Not measured60.5%Only GPT-5.6 Luna measured
CyberBench (Vals AI)Not measured73.6%Only GPT-5.6 Luna measured
SciCode47.2%53.6%GPT-5.6 Luna
Terminal-Bench Hard (Artificial Analysis run)42.4%Not measuredOnly GPT-5.4 Nano measured
FrontierCodeNot measured39.8%Only GPT-5.6 Luna measured
WeirdML49.2%60.9%GPT-5.6 Luna
ALE-Bench1004.51667.4GPT-5.6 Luna
LMArena Text: coding14041466GPT-5.6 Luna
LMArena Text: software and IT14021463GPT-5.6 Luna
LMArena WebDev: ReactNot measured1508Only GPT-5.6 Luna measured
LMArena WebDev: HTMLNot measured1520Only GPT-5.6 Luna measured
LMArena WebDev: from an imageNot measured1517Only GPT-5.6 Luna measured
SciCodeNot measured6.2%Only GPT-5.6 Luna measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
AA Intelligence Index20.737.3GPT-5.6 Luna
Epoch Capabilities Index146.0156.5GPT-5.6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
AA Agentic Index16.042.1GPT-5.6 Luna
LiveBench researchNot measured51.0%Only GPT-5.6 Luna measured
LiveBench browserNot measured68.0%Only GPT-5.6 Luna measured
LiveBench long agenticNot measured30.4%Only GPT-5.6 Luna measured
SREBench (Vals AI)Not measured1.5%Only GPT-5.6 Luna measured
Finance Agent (Vals AI)38.2%55.0%GPT-5.6 Luna
Tax Agent Bench (Vals AI)5.0%24.8%GPT-5.6 Luna
Legal Research Bench (Vals AI)6.3%36.5%GPT-5.6 Luna
Excel Modeling Benchmark (Vals AI)44.8%67.1%GPT-5.6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-5.6 Luna measured
Terminal-Bench-Science (Vals AI)Not measured0.0%Only GPT-5.6 Luna measured
Vals Science IndexNot measured25.3%Only GPT-5.6 Luna measured
τ²-Bench Telecom76.0%Not measuredOnly GPT-5.4 Nano measured
APEX-AgentsNot measured43.0%Only GPT-5.6 Luna measured
BALROGNot measured45.6%Only GPT-5.6 Luna measured
Vending-Bench 2Not measured$4,095Only GPT-5.6 Luna measured
Neither model has a result on the other 26 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index114
Reasoning benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
GPQA Diamond77.5%91.7%GPT-5.6 Luna
LiveBench reasoningNot measured85.6%Only GPT-5.6 Luna measured
MysteryMechanism (Vals AI)Not measured14.4%Only GPT-5.6 Luna measured
MMMU Pro (Vals AI)73.6%85.0%GPT-5.6 Luna
GPQA Diamond (Artificial Analysis run)81.7%91.1%GPT-5.6 Luna
Humanity's Last Exam (Artificial Analysis run)28.3%39.5%GPT-5.6 Luna
GPQA Diamond (Epoch AI run)78.5%91.6%GPT-5.6 Luna
ARC-AGI51.5%88.0%GPT-5.6 Luna
ARC-AGI-25.7%59.5%GPT-5.6 Luna
SimpleBenchNot measured46.8%Only GPT-5.6 Luna measured
Chess puzzles45.0%43.0%GPT-5.4 Nano
Mystery game puzzles9.0%21.0%GPT-5.6 Luna
LMArena Text: hard prompts13811451GPT-5.6 Luna
LMArena Text: expert13961478GPT-5.6 Luna
LMArena Text: hard prompts in English13871460GPT-5.6 Luna
LMArena Vision: diagrams12101273GPT-5.6 Luna
LMArena Vision: homework12251282GPT-5.6 Luna
Kagi LLM Benchmark39.7%49.1%GPT-5.6 Luna
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
AIME88.8%Not measuredOnly GPT-5.4 Nano measured
OTIS Mock AIME87.8%98.3%GPT-5.6 Luna
FrontierMath, tiers 1 to 344.9%82.1%GPT-5.6 Luna
FrontierMath, tier 412.2%61.0%GPT-5.6 Luna
ProofBench5.0%60.0%GPT-5.6 Luna
LMArena Text: math14051459GPT-5.6 Luna
LMArena Text: mathematical work14091470GPT-5.6 Luna
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index011
Knowledge benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
MMLU Pro77.2%86.0%GPT-5.6 Luna
LegalBench (Vals AI)77.9%84.0%GPT-5.6 Luna
CaseLaw (Vals AI)51.9%Not measuredOnly GPT-5.4 Nano measured
CorpFin (Vals AI)61.2%64.2%GPT-5.6 Luna
TaxEval (Vals AI)67.4%76.2%GPT-5.6 Luna
MortgageTax (Vals AI)59.1%67.3%GPT-5.6 Luna
MedCode (Vals AI)41.0%42.4%GPT-5.6 Luna
SimpleQA Verified11.7%41.0%GPT-5.6 Luna
LMArena Text: science13741433GPT-5.6 Luna
LMArena Text: medicine and healthcare13691399GPT-5.6 Luna
LMArena Text: legal and government13681446GPT-5.6 Luna
LMArena Text: business and finance13661439GPT-5.6 Luna
FACTS Benchmark SuiteNot measured35.0%Only GPT-5.6 Luna measured
Neither model has a result on the other 7 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-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
Design Arena: websitesNot measured1255Only GPT-5.6 Luna measured
Design Arena: UI componentsNot measured1248Only GPT-5.6 Luna measured
Design Arena: game devNot measured1195Only GPT-5.6 Luna measured
Design Arena: data vizNot measured1212Only GPT-5.6 Luna measured
Design Arena: 3DNot measured1121Only GPT-5.6 Luna measured
Design Arena: all code categoriesNot measured1230Only GPT-5.6 Luna measured
Design Arena: SVGNot measured1193Only GPT-5.6 Luna measured
Design Arena: ASCII artNot measured1142Only GPT-5.6 Luna measured
LiveBench designNot measured76.0%Only GPT-5.6 Luna measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index029
General benchmarks for GPT-5.4 Nano and GPT-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
LiveBench data analysisNot measured78.0%Only GPT-5.6 Luna measured
Public Benefits Bench (Vals AI)Not measured61.2%Only GPT-5.6 Luna measured
SAGE (Vals AI)38.1%44.2%GPT-5.6 Luna
MedScribe (Vals AI)77.1%84.4%GPT-5.6 Luna
Vals Multimodal Index47.6%69.1%GPT-5.6 Luna
IFBench75.9%Not measuredOnly GPT-5.4 Nano measured
Long context reasoning (AA-LCR)76.7%83.7%GPT-5.6 Luna
DTBench80.3%89.1%GPT-5.6 Luna
LMCA36.9%48.5%GPT-5.6 Luna
Surface Evolver BenchNot measured61.9%Only GPT-5.6 Luna measured
Furniture assemblyNot measured42.5%Only GPT-5.6 Luna measured
LMArena Text13721431GPT-5.6 Luna
LMArena Text: instruction following13621437GPT-5.6 Luna
LMArena Text: creative writing13151396GPT-5.6 Luna
LMArena Vision11961257GPT-5.6 Luna
LMArena Text: English13811441GPT-5.6 Luna
LMArena Text: non-English13591417GPT-5.6 Luna
LMArena Text: Chinese13911470GPT-5.6 Luna
LMArena Text: German13681455GPT-5.6 Luna
LMArena Text: Japanese13431415GPT-5.6 Luna
LMArena Text: Korean13211415GPT-5.6 Luna
LMArena Text: French13951458GPT-5.6 Luna
LMArena Text: Spanish13711446GPT-5.6 Luna
LMArena Text: Russian13631427GPT-5.6 Luna
LMArena Text: Polish13661405GPT-5.6 Luna
LMArena Text: multi-turn13821434GPT-5.6 Luna
LMArena Text: longer queries13651436GPT-5.6 Luna
LMArena Text: writing and language13381419GPT-5.6 Luna
LMArena Text: entertainment and media13251402GPT-5.6 Luna
LMArena Vision: English12021263GPT-5.6 Luna
LMArena Vision: Chinese12321294GPT-5.6 Luna
LMArena Vision: reading text12041264GPT-5.6 Luna
LMArena Vision: humor11611190GPT-5.6 Luna
LMArena Vision: recognizing things1141Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: creative writing11591257GPT-5.6 Luna
LMArena DocumentNot measured1457Only GPT-5.6 Luna measured
EQ-Bench 4Not measured1156Only GPT-5.6 Luna measured
Neither model has a result on the other 11 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-5.6 Luna
BenchmarkGPT-5.4 NanoGPT-5.6 LunaLeader
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-5.6 Luna$0.0008Fits in one request

GPT-5.6 Luna costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Nano$0.014Fits in one request
GPT-5.6 Luna$0.014Fits in one request

GPT-5.6 Luna costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Nano$0.052Fits in one request
GPT-5.6 Luna$0.052Fits in one request

GPT-5.6 Luna 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-5.6 Luna
SpecificationOpenAI GPT-5.4 NanoOpenAI GPT-5.6 Luna
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 17, 2026July 9, 2026
Context window400K1.05M
Input $/Mtok$0.20$0.20
Output $/Mtok$1.25$1.20
Coding index44.858.0
Independent measurements behind it26
Cost per solved task$0.14$0.04
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Nano better than GPT-5.6 Luna for coding?

Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano. Pick GPT-5.4 Nano for work measured by Chess puzzles, where it leads.

Which is cheaper, GPT-5.4 Nano or GPT-5.6 Luna?

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. Per solved SWE-bench Verified task, GPT-5.4 Nano costs $0.14 and GPT-5.6 Luna $0.04.

Which has the bigger context window, GPT-5.4 Nano or GPT-5.6 Luna?

GPT-5.6 Luna, with 1.05M tokens against 400K.

How many benchmarks is the GPT-5.4 Nano vs GPT-5.6 Luna comparison based on?

78 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-5.6 Luna'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-5-4-nano-vs-gpt-5-6-luna" title="GPT-5.4 Nano vs GPT-5.6 Luna, 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-5-6-luna">LLMBenchmark.ai, GPT-5.4 Nano vs GPT-5.6 Luna</a></p>