Enter opens the highlighted result. Esc closes.

GPT-4.1 Nano vs GPT-5 Nano

GPT-5 Nano leads GPT-4.1 Nano on the Artificial Analysis Intelligence Index, 13.0 to 7.8, at about the same output price ($0.40 vs $0.40 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace GPT-4.1 Nano Replace GPT-5 Nano
GPT-4.1 NanoOpenAI
Coding
No data
Overall
24.7
Output $/M
$0.40
3
GPT-5 NanoOpenAI
Coding
No data
Overall
35.6
Output $/M
$0.40
65
vs boards won of 68 shared

GPT-4.1 Nano or GPT-5 Nano: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-4.1 Nano for a larger context window (1.05M against 400K tokens) and work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Model AGPT-4.1 NanoOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-5 NanoOpenAINot benchmarkedNo coding benchmark$0.109 per solved task
Shared results
68
GPT-4.1 Nano only
3
GPT-5 Nano only
19
Like-for-like categories
8 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-4.1 Nano not benchmarked, GPT-5 Nano not benchmarked.
Widest category
Math, 33.4 points apart on average over 9 shared benchmarks.
Widest single gap
AA Math Index: GPT-4.1 Nano 24.0 against GPT-5 Nano 83.7, 59.7 points apart on a 0 to 100 scale.
Output price
Both cost $0.40 per million output tokens.
Context window
GPT-4.1 Nano takes 1.05M tokens, GPT-5 Nano 400K.

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-4.1 NanoBarsGPT-5 NanoTies
Coding06
Intelligence02
Agentic work02
Reasoning012
Math09
Knowledge29
Web design06
General119
All shared boards365
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
Aider polyglot8.9%Not measuredOnly GPT-4.1 Nano measured
SWE-bench VerifiedNot measured34.8%Only GPT-5 Nano measured
AA Coding Index11.1Not measuredOnly GPT-4.1 Nano measured
LiveCodeBench (Vals AI)42.7%70.2%GPT-5 Nano
LiveCodeBench (Artificial Analysis run)32.6%78.9%GPT-5 Nano
Terminal-Bench Hard (Artificial Analysis run)3.8%17.4%GPT-5 Nano
Terminal-BenchNot measured21.8%Only GPT-5 Nano measured
WeirdML19.0%38.1%GPT-5 Nano
LMArena Text: coding13061351GPT-5 Nano
LMArena Text: software and IT13051345GPT-5 Nano
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
AA Intelligence Index7.813.0GPT-5 Nano
Epoch Capabilities Index129.5139.2GPT-5 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
τ²-Bench Telecom17.3%36.5%GPT-5 Nano
Berkeley Function Calling Leaderboard (BFCL)33.1%51.4%GPT-5 Nano
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index012
Reasoning benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
GPQA Diamond50.8%63.4%GPT-5 Nano
MMMU Pro (Vals AI)55.0%70.9%GPT-5 Nano
GPQA Diamond (Artificial Analysis run)51.2%67.6%GPT-5 Nano
Humanity's Last Exam (Artificial Analysis run)3.8%9.5%GPT-5 Nano
GPQA Diamond (Epoch AI run)48.9%69.4%GPT-5 Nano
ARC-AGI0.0%20.7%GPT-5 Nano
ARC-AGI-20.0%2.6%GPT-5 Nano
Chess puzzles0.0%22.0%GPT-5 Nano
Mystery game puzzlesNot measured9.0%Only GPT-5 Nano measured
VPCTNot measured37.2%Only GPT-5 Nano measured
LMArena Text: hard prompts12861328GPT-5 Nano
LMArena Text: expert12711321GPT-5 Nano
LMArena Text: hard prompts in English12931338GPT-5 Nano
LMArena Vision: diagramsNot measured1141Only GPT-5 Nano measured
LMArena Vision: homeworkNot measured1157Only GPT-5 Nano measured
Kagi LLM Benchmark33.3%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 index09
Math benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
AIME26.5%81.2%GPT-5 Nano
MATH 500 (Vals AI)80.2%93.8%GPT-5 Nano
MGSM (Vals AI)69.3%89.3%GPT-5 Nano
AA Math Index24.083.7GPT-5 Nano
AIME 2025 (Artificial Analysis run)24.0%83.7%GPT-5 Nano
OTIS Mock AIME28.9%81.1%GPT-5 Nano
FrontierMath, tiers 1 to 3Not measured20.0%Only GPT-5 Nano measured
FrontierMath, tier 4Not measured2.4%Only GPT-5 Nano measured
ProofBenchNot measured12.0%Only GPT-5 Nano measured
MATH level 570.0%95.2%GPT-5 Nano
LMArena Text: math12741317GPT-5 Nano
LMArena Text: mathematical work12741326GPT-5 Nano
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index29
Knowledge benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
MMLU Pro63.5%76.1%GPT-5 Nano
LegalBench (Vals AI)61.1%50.1%GPT-4.1 Nano
CaseLaw (Vals AI)Not measured52.6%Only GPT-5 Nano measured
CorpFin (Vals AI)42.1%Not measuredOnly GPT-4.1 Nano measured
TaxEval (Vals AI)60.8%67.4%GPT-5 Nano
MortgageTax (Vals AI)52.8%53.6%GPT-5 Nano
MedQA (Vals AI)68.2%93.3%GPT-5 Nano
MedCode (Vals AI)Not measured30.4%Only GPT-5 Nano measured
MMLU Pro (Artificial Analysis run)65.7%78.0%GPT-5 Nano
SimpleQA Verified6.0%11.7%GPT-5 Nano
LMArena Text: science12971318GPT-5 Nano
LMArena Text: medicine and healthcare12761335GPT-5 Nano
LMArena Text: legal and government13001298GPT-4.1 Nano
LMArena Text: business and finance12671311GPT-5 Nano
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
Design Arena: websites9731101GPT-5 Nano
Design Arena: UI components9131064GPT-5 Nano
Design Arena: game dev9701044GPT-5 Nano
Design Arena: data viz8911056GPT-5 Nano
Design Arena: 3D924965GPT-5 Nano
Design Arena: all code categories9621084GPT-5 Nano
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index119
General benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 NanoGPT-5 NanoLeader
SAGE (Vals AI)Not measured30.4%Only GPT-5 Nano measured
MedScribe (Vals AI)Not measured72.9%Only GPT-5 Nano measured
IFBench32.0%67.6%GPT-5 Nano
Long context reasoning (AA-LCR)20.3%45.0%GPT-5 Nano
DTBench52.5%62.7%GPT-5 Nano
LMCA5.5%7.9%GPT-5 Nano
Fiction.LiveBench25.0%44.4%GPT-5 Nano
LMArena Text12851320GPT-5 Nano
LMArena Text: instruction following12661306GPT-5 Nano
LMArena Text: creative writing12601249GPT-4.1 Nano
LMArena Vision10631159GPT-5 Nano
LMArena Text: English13031321GPT-5 Nano
LMArena Text: non-English12601313GPT-5 Nano
LMArena Text: Chinese12701356GPT-5 Nano
LMArena Text: German12881327GPT-5 Nano
LMArena Text: Japanese11981227GPT-5 Nano
LMArena Text: KoreanNot measured1269Only GPT-5 Nano measured
LMArena Text: SpanishNot measured1360Only GPT-5 Nano measured
LMArena Text: Russian12611296GPT-5 Nano
LMArena Text: PolishNot measured1314Only GPT-5 Nano measured
LMArena Text: multi-turn12771311GPT-5 Nano
LMArena Text: longer queries12831312GPT-5 Nano
LMArena Text: writing and language12611283GPT-5 Nano
LMArena Text: entertainment and media12431268GPT-5 Nano
LMArena Vision: English11011170GPT-5 Nano
LMArena Vision: ChineseNot measured1176Only GPT-5 Nano measured
LMArena Vision: reading textNot measured1152Only GPT-5 Nano measured
LMArena Vision: humorNot measured1110Only GPT-5 Nano measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4.1 Nano and GPT-5 Nano
BenchmarkGPT-4.1 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-4.1 Nano$0.0003Fits in one request
GPT-5 Nano$0.0003Fits in one request

GPT-5 Nano costs less

Repository review

50K input + 3K output tokens

GPT-4.1 Nano$0.0062Fits in one request
GPT-5 Nano$0.0037Fits in one request

GPT-5 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-4.1 Nano$0.024Fits 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-4.1 Nano and GPT-5 Nano
SpecificationOpenAI GPT-4.1 NanoOpenAI GPT-5 Nano
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025August 7, 2025
Context window1.05M400K
Input $/Mtok$0.10$0.05
Output $/Mtok$0.40$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computable$0.109
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Nano better than GPT-5 Nano for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 Nano for a larger context window (1.05M against 400K tokens) and work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Which is cheaper, GPT-4.1 Nano or GPT-5 Nano?

GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens; GPT-5 Nano costs $0.05 and $0.40. Cost per solved task is known for GPT-5 Nano only.

Which has the bigger context window, GPT-4.1 Nano or GPT-5 Nano?

GPT-4.1 Nano, with 1.05M tokens against 400K.

How many benchmarks is the GPT-4.1 Nano vs GPT-5 Nano comparison based on?

68 benchmarks have a result for both models as of October 22, 2026. GPT-4.1 Nano's coding index rests on 0 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