LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4.1 Nano vs GPT-4o (2024-08-06)

Updated October 21, 2026. 50 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-4.1 Nano Replace GPT-4o (2024-08-06)
GPT-4.1 NanoOpenAI
Coding
8.9
Overall
7.8
Output $/M
$0.40
22
GPT-4o (2024-08-06)OpenAI
Coding
23.1
Overall
7.7
Output $/M
$10.00
28
vs boards won of 50 shared

Decision reading

Pick GPT-4o (2024-08-06) for coding: it scores 23.1 on the Vibe Coding Index against 8.9 for GPT-4.1 Nano.

Pick GPT-4.1 Nano when output tokens cost 25.0x less, or when the context window is larger, 1.05M against 128K tokens.

Model AGPT-4.1 NanoOpenAI8.9/1001 independent benchmarkNo cost per solved taskModel BGPT-4o (2024-08-06)OpenAI23.1/1001 independent benchmarkNo cost per solved task
Shared results
50
GPT-4.1 Nano only
19
GPT-4o (2024-08-06) only
8
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 8.9 from 1 benchmark, GPT-4o (2024-08-06) 23.1 from 1 benchmark.
Widest category
Agentic work, 11.7 points apart on average over 1 shared benchmark.
Widest single gap
OTIS Mock AIME: GPT-4.1 Nano 28.9% against GPT-4o (2024-08-06) 6.4%, 22.5 points apart on a 0 to 100 scale.
Output price
GPT-4.1 Nano $0.40 against GPT-4o (2024-08-06) $10.00 per million output tokens, 25.0x apart.
Context window
GPT-4.1 Nano takes 1.05M tokens, GPT-4o (2024-08-06) 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 (2024-08-06)Ties
Coding32
Intelligence10
Agentic work01
Reasoning44
Math43
Knowledge56
General512
All shared boards2228
CodingLike-for-likeFour of these boards feed the Vibe Coding Index32
Coding benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
Aider polyglot8.9%23.1%GPT-4o (2024-08-06)
SWE-bench LiteNot measured21.7%Only GPT-4o (2024-08-06) measured
AA Coding Index11.1Not measuredOnly GPT-4.1 Nano measured
LiveCodeBench (Vals AI)42.7%Not measuredOnly GPT-4.1 Nano measured
LiveCodeBench (Artificial Analysis run)32.6%31.7%GPT-4.1 Nano
Terminal-Bench Hard (Artificial Analysis run)3.8%8.3%GPT-4o (2024-08-06)
WeirdML19.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text: coding13061283GPT-4.1 Nano
LMArena Text: software and IT13051278GPT-4.1 Nano
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
AA Intelligence Index7.87.7GPT-4.1 Nano
Epoch Capabilities Index129.5Not measuredOnly GPT-4.1 Nano measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
τ²-Bench Telecom17.3%28.9%GPT-4o (2024-08-06)
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index44
Reasoning benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
GPQA Diamond50.8%Not measuredOnly GPT-4.1 Nano measured
MMMU Pro (Vals AI)55.0%64.0%GPT-4o (2024-08-06)
GPQA Diamond (Artificial Analysis run)51.2%52.1%GPT-4o (2024-08-06)
Humanity's Last Exam (Artificial Analysis run)3.8%2.3%GPT-4.1 Nano
GPQA Diamond (Epoch AI run)48.9%49.2%GPT-4o (2024-08-06)
ARC-AGI0.0%Not measuredOnly GPT-4.1 Nano measured
ARC-AGI-20.0%Not measuredOnly GPT-4.1 Nano measured
SimpleBenchNot measured17.8%Only GPT-4o (2024-08-06) measured
Chess puzzles0.0%6.0%GPT-4o (2024-08-06)
LMArena Text: hard prompts12861264GPT-4.1 Nano
LMArena Text: expert12711241GPT-4.1 Nano
LMArena Text: hard prompts in English12931277GPT-4.1 Nano
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index43
Math benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
AIME26.5%14.0%GPT-4.1 Nano
MATH 500 (Vals AI)80.2%75.2%GPT-4.1 Nano
MGSM (Vals AI)69.3%90.7%GPT-4o (2024-08-06)
AA Math Index24.0Not measuredOnly GPT-4.1 Nano measured
AIME 2025 (Artificial Analysis run)24.0%Not measuredOnly GPT-4.1 Nano measured
OTIS Mock AIME28.9%6.4%GPT-4.1 Nano
FrontierMath, tiers 1 to 3Not measured0.4%Only GPT-4o (2024-08-06) measured
MATH level 570.0%53.3%GPT-4.1 Nano
LMArena Text: math12741285GPT-4o (2024-08-06)
LMArena Text: mathematical work12741283GPT-4o (2024-08-06)
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index56
Knowledge benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
MMLU Pro63.5%74.1%GPT-4o (2024-08-06)
LegalBench (Vals AI)61.1%80.1%GPT-4o (2024-08-06)
CorpFin (Vals AI)42.1%39.4%GPT-4.1 Nano
TaxEval (Vals AI)60.8%71.1%GPT-4o (2024-08-06)
MortgageTax (Vals AI)52.8%61.0%GPT-4o (2024-08-06)
MedQA (Vals AI)68.2%88.2%GPT-4o (2024-08-06)
MMLU Pro (Artificial Analysis run)65.7%Not measuredOnly GPT-4.1 Nano measured
SimpleQA Verified6.0%26.0%GPT-4o (2024-08-06)
MMLUNot measured84.3%Only GPT-4o (2024-08-06) measured
LMArena Text: science12971274GPT-4.1 Nano
LMArena Text: medicine and healthcare12761252GPT-4.1 Nano
LMArena Text: legal and government13001275GPT-4.1 Nano
LMArena Text: business and finance12671232GPT-4.1 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-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
Design Arena: websites973Not measuredOnly GPT-4.1 Nano measured
Design Arena: UI components916Not measuredOnly GPT-4.1 Nano measured
Design Arena: game dev971Not measuredOnly GPT-4.1 Nano measured
Design Arena: data viz891Not measuredOnly GPT-4.1 Nano measured
Design Arena: 3D925Not measuredOnly GPT-4.1 Nano measured
Design Arena: all code categories963Not 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 index512
General benchmarks for GPT-4.1 Nano and GPT-4o (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
IFBench32.0%36.0%GPT-4o (2024-08-06)
Long context reasoning (AA-LCR)20.3%41.0%GPT-4o (2024-08-06)
DTBench52.5%Not measuredOnly GPT-4.1 Nano measured
LMCA5.5%Not measuredOnly GPT-4.1 Nano measured
Fiction.LiveBench25.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text12851283GPT-4.1 Nano
LMArena Text: instruction following12661267GPT-4o (2024-08-06)
LMArena Text: creative writing12601274GPT-4o (2024-08-06)
LMArena Vision10631065GPT-4o (2024-08-06)
LMArena Text: English13031297GPT-4.1 Nano
LMArena Text: non-English12601262GPT-4o (2024-08-06)
LMArena Text: Chinese12701254GPT-4.1 Nano
LMArena Text: German12881257GPT-4.1 Nano
LMArena Text: Japanese11981234GPT-4o (2024-08-06)
LMArena Text: KoreanNot measured1218Only GPT-4o (2024-08-06) measured
LMArena Text: FrenchNot measured1263Only GPT-4o (2024-08-06) measured
LMArena Text: SpanishNot measured1269Only GPT-4o (2024-08-06) measured
LMArena Text: Russian12611272GPT-4o (2024-08-06)
LMArena Text: multi-turn12771279GPT-4o (2024-08-06)
LMArena Text: longer queries12831283GPT-4o (2024-08-06)
LMArena Text: writing and language12611290GPT-4o (2024-08-06)
LMArena Text: entertainment and media12431267GPT-4o (2024-08-06)
LMArena Vision: English11011072GPT-4.1 Nano
LMArena Vision: ChineseNot measured1009Only GPT-4o (2024-08-06) measured
Neither model has a result on the other 22 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 (2024-08-06)
BenchmarkGPT-4.1 NanoGPT-4o (2024-08-06)Leader
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 (2024-08-06)$0.0075Fits 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 (2024-08-06)$0.155Fits 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 (2024-08-06)$0.600Exceeds 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 (2024-08-06)
SpecificationOpenAI GPT-4.1 NanoOpenAI GPT-4o (2024-08-06)
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025August 6, 2024
Context window1.05M128K
Input $/Mtok$0.10$2.50
Output $/Mtok$0.40$10.00
Coding index8.923.1
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Nano better than GPT-4o (2024-08-06) for coding?

Pick GPT-4o (2024-08-06) for coding: it scores 23.1 on the Vibe Coding Index against 8.9 for GPT-4.1 Nano. Pick GPT-4.1 Nano when output tokens cost 25.0x less, or when the context window is larger, 1.05M against 128K tokens.

Which is cheaper, GPT-4.1 Nano or GPT-4o (2024-08-06)?

GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens; GPT-4o (2024-08-06) costs $2.50 and $10.00. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4.1 Nano or GPT-4o (2024-08-06)?

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

How many benchmarks is the GPT-4.1 Nano vs GPT-4o (2024-08-06) comparison based on?

50 benchmarks have a result for both models as of October 21, 2026. GPT-4.1 Nano's coding index rests on 1 independent benchmark and GPT-4o (2024-08-06)'s on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next