Enter opens the highlighted result. Esc closes.

GPT-4.1 Nano vs GPT-4o-mini

GPT-4.1 Nano leads GPT-4o-mini on the Artificial Analysis Intelligence Index, 7.8 to 6.7, and GPT-4.1 Nano costs 1.5x less per output token ($0.40 vs $0.60 per million). Updated October 22, 2026; 25 benchmarks have a result for both.

Replace GPT-4.1 Nano Replace GPT-4o-mini
GPT-4.1 NanoOpenAI
Coding
No data
Overall
24.7
Output $/M
$0.40
15
GPT-4o-miniOpenAI
Coding
No data
Overall
No data
Output $/M
$0.60
9
vs boards won of 25 shared, 1 tied

GPT-4.1 Nano or GPT-4o-mini: which to pick

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

Pick GPT-4.1 Nano for output tokens 1.5x cheaper ($0.40 vs $0.60 per million) and a larger context window (1.05M against 128K tokens).

Model AGPT-4.1 NanoOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4o-miniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
25
GPT-4.1 Nano only
46
GPT-4o-mini only
4
Like-for-like categories
6 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-4o-mini not benchmarked.
Widest category
Math, 11.6 points apart on average over 5 shared benchmarks.
Widest single gap
MGSM (Vals AI): GPT-4.1 Nano 69.3% against GPT-4o-mini 86.2%, 16.9 points apart on a 0 to 100 scale.
Output price
GPT-4.1 Nano $0.40 against GPT-4o-mini $0.60 per million output tokens, 1.5x apart.
Context window
GPT-4.1 Nano takes 1.05M tokens, GPT-4o-mini 128K.

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-4o-miniTies
Coding21
Intelligence20
Reasoning321 tie
Math41
Knowledge33
General12
All shared boards1591 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
Coding benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
Aider polyglot8.9%Not measuredOnly GPT-4.1 Nano measured
AA Coding Index11.111.4GPT-4o-mini
LiveCodeBench (Vals AI)42.7%26.4%GPT-4.1 Nano
LiveCodeBench (Artificial Analysis run)32.6%23.4%GPT-4.1 Nano
Terminal-Bench Hard (Artificial Analysis run)3.8%Not measuredOnly GPT-4.1 Nano measured
WeirdML19.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text: coding1306Not measuredOnly GPT-4.1 Nano measured
LMArena Text: software and IT1305Not measuredOnly GPT-4.1 Nano measured
SciCodeNot measured1.5%Only GPT-4o-mini measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
AA Intelligence Index7.86.7GPT-4.1 Nano
Epoch Capabilities Index129.5126.5GPT-4.1 Nano
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
τ²-Bench Telecom17.3%Not measuredOnly GPT-4.1 Nano measured
Berkeley Function Calling Leaderboard (BFCL)33.1%Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
Reasoning benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
GPQA Diamond50.8%44.2%GPT-4.1 Nano
MMMU Pro (Vals AI)55.0%56.6%GPT-4o-mini
GPQA Diamond (Artificial Analysis run)51.2%42.6%GPT-4.1 Nano
Humanity's Last Exam (Artificial Analysis run)3.8%4.2%GPT-4o-mini
GPQA Diamond (Epoch AI run)48.9%Not measuredOnly GPT-4.1 Nano measured
ARC-AGI0.0%Not measuredOnly GPT-4.1 Nano measured
ARC-AGI-20.0%0.0%Tie
Chess puzzles0.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text: hard prompts1286Not measuredOnly GPT-4.1 Nano measured
LMArena Text: expert1271Not measuredOnly GPT-4.1 Nano measured
LMArena Text: hard prompts in English1293Not measuredOnly GPT-4.1 Nano measured
Kagi LLM Benchmark33.3%28.8%GPT-4.1 Nano
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index41
Math benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
AIME26.5%11.5%GPT-4.1 Nano
MATH 500 (Vals AI)80.2%72.6%GPT-4.1 Nano
MGSM (Vals AI)69.3%86.2%GPT-4o-mini
AA Math Index24.014.7GPT-4.1 Nano
AIME 2025 (Artificial Analysis run)24.0%14.7%GPT-4.1 Nano
OTIS Mock AIME28.9%Not measuredOnly GPT-4.1 Nano measured
MATH level 570.0%Not measuredOnly GPT-4.1 Nano measured
GSM8KNot measured91.3%Only GPT-4o-mini measured
LMArena Text: math1274Not measuredOnly GPT-4.1 Nano measured
LMArena Text: mathematical work1274Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index33
Knowledge benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
MMLU Pro63.5%62.7%GPT-4.1 Nano
LegalBench (Vals AI)61.1%Not measuredOnly GPT-4.1 Nano measured
CorpFin (Vals AI)42.1%45.5%GPT-4o-mini
TaxEval (Vals AI)60.8%60.5%GPT-4.1 Nano
MortgageTax (Vals AI)52.8%54.5%GPT-4o-mini
MedQA (Vals AI)68.2%72.4%GPT-4o-mini
MMLU Pro (Artificial Analysis run)65.7%64.8%GPT-4.1 Nano
SimpleQA Verified6.0%Not measuredOnly GPT-4.1 Nano measured
MMLUNot measured81.8%Only GPT-4o-mini measured
LMArena Text: science1297Not measuredOnly GPT-4.1 Nano measured
LMArena Text: medicine and healthcare1276Not measuredOnly GPT-4.1 Nano measured
LMArena Text: legal and government1300Not measuredOnly GPT-4.1 Nano measured
LMArena Text: business and finance1267Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
Design Arena: websites972Not measuredOnly GPT-4.1 Nano measured
Design Arena: UI components913Not measuredOnly GPT-4.1 Nano measured
Design Arena: game dev970Not measuredOnly GPT-4.1 Nano measured
Design Arena: data viz891Not measuredOnly GPT-4.1 Nano measured
Design Arena: 3D924Not measuredOnly GPT-4.1 Nano measured
Design Arena: all code categories962Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index12
General benchmarks for GPT-4.1 Nano and GPT-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
IFBench32.0%31.0%GPT-4.1 Nano
Long context reasoning (AA-LCR)20.3%Not measuredOnly GPT-4.1 Nano measured
DTBench52.5%54.4%GPT-4o-mini
LMCA5.5%10.4%GPT-4o-mini
Fiction.LiveBench25.0%Not measuredOnly GPT-4.1 Nano measured
PIQANot measured88.7%Only GPT-4o-mini measured
LMArena Text1285Not measuredOnly GPT-4.1 Nano measured
LMArena Text: instruction following1266Not measuredOnly GPT-4.1 Nano measured
LMArena Text: creative writing1260Not measuredOnly GPT-4.1 Nano measured
LMArena Vision1063Not measuredOnly GPT-4.1 Nano measured
LMArena Text: English1303Not measuredOnly GPT-4.1 Nano measured
LMArena Text: non-English1260Not measuredOnly GPT-4.1 Nano measured
LMArena Text: Chinese1270Not measuredOnly GPT-4.1 Nano measured
LMArena Text: German1288Not measuredOnly GPT-4.1 Nano measured
LMArena Text: Japanese1198Not measuredOnly GPT-4.1 Nano measured
LMArena Text: Russian1261Not measuredOnly GPT-4.1 Nano measured
LMArena Text: multi-turn1277Not measuredOnly GPT-4.1 Nano measured
LMArena Text: longer queries1283Not measuredOnly GPT-4.1 Nano measured
LMArena Text: writing and language1261Not measuredOnly GPT-4.1 Nano measured
LMArena Text: entertainment and media1243Not measuredOnly GPT-4.1 Nano measured
LMArena Vision: English1101Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 25 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-4o-mini
BenchmarkGPT-4.1 NanoGPT-4o-miniLeader
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-4o-mini$0.0004Fits in one request

GPT-4.1 Nano costs less

Repository review

50K input + 3K output tokens

GPT-4.1 Nano$0.0062Fits in one request
GPT-4o-mini$0.0093Fits in one request

GPT-4.1 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-4.1 Nano$0.024Fits in one request
GPT-4o-mini$0.036Exceeds the context window

GPT-4.1 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-4o-mini
SpecificationOpenAI GPT-4.1 NanoOpenAI GPT-4o-mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025July 18, 2024
Context window1.05M128K
Input $/Mtok$0.10$0.15
Output $/Mtok$0.40$0.60
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Nano better than GPT-4o-mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 Nano for output tokens 1.5x cheaper ($0.40 vs $0.60 per million) and a larger context window (1.05M against 128K tokens).

Which is cheaper, GPT-4.1 Nano or GPT-4o-mini?

GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens; GPT-4o-mini costs $0.15 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4.1 Nano or GPT-4o-mini?

GPT-4.1 Nano, with 1.05M tokens against 128K.

How many benchmarks is the GPT-4.1 Nano vs GPT-4o-mini comparison based on?

25 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-4o-mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next