Enter opens the highlighted result. Esc closes.

GPT-5 Nano vs Llama 4 Maverick

GPT-5 Nano leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 13.0 to 9.3, and GPT-5 Nano costs 2.5x less per output token ($0.40 vs $1.00 per million). Updated October 22, 2026; 74 benchmarks have a result for both.

Replace GPT-5 Nano Replace Llama 4 Maverick
GPT-5 NanoOpenAI
Coding
No data
Overall
35.6
Output $/M
$0.40
60
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
14
vs boards won of 74 shared

GPT-5 Nano or Llama 4 Maverick: which to pick

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

Pick GPT-5 Nano for output tokens 2.5x cheaper ($0.40 vs $1.00 per million) and a lower cost per solved task ($0.109 against $1.491).

Model AGPT-5 NanoOpenAINot benchmarkedNo coding benchmark$0.109 per solved taskModel BLlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved task
Shared results
74
GPT-5 Nano only
13
Llama 4 Maverick only
11
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-5 Nano not benchmarked, Llama 4 Maverick not benchmarked.
Widest category
Math, 29.2 points apart on average over 7 shared benchmarks.
Widest single gap
AA Math Index: GPT-5 Nano 83.7 against Llama 4 Maverick 19.3, 64.4 points apart on a 0 to 100 scale.
Output price
GPT-5 Nano $0.40 against Llama 4 Maverick $1.00 per million output tokens, 2.5x apart.
Context window
GPT-5 Nano takes 400K tokens, Llama 4 Maverick 524K.

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 NanoBarsLlama 4 MaverickTies
Coding70
Intelligence20
Agentic work10
Reasoning93
Math61
Knowledge65
Web design60
General235
All shared boards6014
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench Verified34.8%21.0%GPT-5 Nano
AA Coding IndexNot measured16.3Only Llama 4 Maverick measured
LiveCodeBench (Vals AI)70.2%47.3%GPT-5 Nano
LiveCodeBench (Artificial Analysis run)78.9%39.7%GPT-5 Nano
SciCodeNot measured31.7%Only Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)17.4%6.8%GPT-5 Nano
Terminal-Bench21.8%Not measuredOnly GPT-5 Nano measured
WeirdML38.1%24.5%GPT-5 Nano
ALE-BenchNot measured173.0Only Llama 4 Maverick measured
LMArena Text: coding13511301GPT-5 Nano
LMArena Text: software and IT13451299GPT-5 Nano
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
AA Intelligence Index13.09.3GPT-5 Nano
Epoch Capabilities Index139.2132.2GPT-5 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
AA Agentic IndexNot measured0.6Only Llama 4 Maverick measured
τ²-Bench Telecom36.5%17.8%GPT-5 Nano
Berkeley Function Calling Leaderboard (BFCL)51.4%Not measuredOnly GPT-5 Nano measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index93
Reasoning benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
GPQA Diamond63.4%69.4%Llama 4 Maverick
MMMU Pro (Vals AI)70.9%71.7%Llama 4 Maverick
GPQA Diamond (Artificial Analysis run)67.6%67.1%GPT-5 Nano
Humanity's Last Exam (Artificial Analysis run)9.5%4.9%GPT-5 Nano
GPQA Diamond (Epoch AI run)69.4%Not measuredOnly GPT-5 Nano measured
ARC-AGI20.7%4.4%GPT-5 Nano
ARC-AGI-22.6%0.0%GPT-5 Nano
SimpleBenchNot measured27.7%Only Llama 4 Maverick measured
Chess puzzles22.0%Not measuredOnly GPT-5 Nano measured
Mystery game puzzles9.0%Not measuredOnly GPT-5 Nano measured
VPCT37.2%Not measuredOnly GPT-5 Nano measured
LMArena Text: hard prompts13281281GPT-5 Nano
LMArena Text: expert13211259GPT-5 Nano
LMArena Text: hard prompts in English13381295GPT-5 Nano
LMArena Vision: diagrams11411134GPT-5 Nano
LMArena Vision: homework11571164Llama 4 Maverick
Kagi LLM Benchmark62.2%55.9%GPT-5 Nano
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index61
Math benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
AIME81.2%25.2%GPT-5 Nano
MATH 500 (Vals AI)93.8%85.2%GPT-5 Nano
MGSM (Vals AI)89.3%92.4%Llama 4 Maverick
AA Math Index83.719.3GPT-5 Nano
AIME 2025 (Artificial Analysis run)83.7%19.3%GPT-5 Nano
OTIS Mock AIME81.1%Not measuredOnly GPT-5 Nano measured
FrontierMath, tiers 1 to 320.0%Not measuredOnly GPT-5 Nano measured
FrontierMath, tier 42.4%Not measuredOnly GPT-5 Nano measured
ProofBench12.0%Not measuredOnly GPT-5 Nano measured
MATH level 595.2%Not measuredOnly GPT-5 Nano measured
LMArena Text: math13171299GPT-5 Nano
LMArena Text: mathematical work13261295GPT-5 Nano
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index65
Knowledge benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
MMLU Pro76.1%79.4%Llama 4 Maverick
LegalBench (Vals AI)50.1%77.8%Llama 4 Maverick
CaseLaw (Vals AI)52.6%Not measuredOnly GPT-5 Nano measured
CorpFin (Vals AI)Not measured49.7%Only Llama 4 Maverick measured
TaxEval (Vals AI)67.4%66.6%GPT-5 Nano
MortgageTax (Vals AI)53.6%58.5%Llama 4 Maverick
MedQA (Vals AI)93.3%43.3%GPT-5 Nano
MedCode (Vals AI)30.4%36.5%Llama 4 Maverick
MMLU Pro (Artificial Analysis run)78.0%80.9%Llama 4 Maverick
SimpleQA Verified11.7%Not measuredOnly GPT-5 Nano measured
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science13181288GPT-5 Nano
LMArena Text: medicine and healthcare13351275GPT-5 Nano
LMArena Text: legal and government12981286GPT-5 Nano
LMArena Text: business and finance13111260GPT-5 Nano
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
Design Arena: websites1101871GPT-5 Nano
Design Arena: UI components1064896GPT-5 Nano
Design Arena: game dev1044837GPT-5 Nano
Design Arena: data viz1056882GPT-5 Nano
Design Arena: 3D965900GPT-5 Nano
Design Arena: all code categories1084879GPT-5 Nano
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index235
General benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
SAGE (Vals AI)30.4%35.7%Llama 4 Maverick
MedScribe (Vals AI)72.9%54.2%GPT-5 Nano
IFBench67.6%43.0%GPT-5 Nano
Long context reasoning (AA-LCR)45.0%50.0%Llama 4 Maverick
DTBench62.7%61.9%GPT-5 Nano
LMCA7.9%15.9%Llama 4 Maverick
Fiction.LiveBench44.4%46.2%Llama 4 Maverick
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
LMArena Text13201287GPT-5 Nano
LMArena Text: instruction following13061267GPT-5 Nano
LMArena Text: creative writing12491266Llama 4 Maverick
LMArena Vision11591142GPT-5 Nano
LMArena Text: English13211303GPT-5 Nano
LMArena Text: non-English13131269GPT-5 Nano
LMArena Text: Chinese13561277GPT-5 Nano
LMArena Text: German13271291GPT-5 Nano
LMArena Text: Japanese12271206GPT-5 Nano
LMArena Text: Korean12691203GPT-5 Nano
LMArena Text: FrenchNot measured1259Only Llama 4 Maverick measured
LMArena Text: Spanish13601293GPT-5 Nano
LMArena Text: Russian12961286GPT-5 Nano
LMArena Text: Polish13141275GPT-5 Nano
LMArena Text: multi-turn13111289GPT-5 Nano
LMArena Text: longer queries13121280GPT-5 Nano
LMArena Text: writing and language12831277GPT-5 Nano
LMArena Text: entertainment and media12681250GPT-5 Nano
LMArena Vision: English11701150GPT-5 Nano
LMArena Vision: Chinese11761141GPT-5 Nano
LMArena Vision: reading text11521143GPT-5 Nano
LMArena Vision: humor11101100GPT-5 Nano
LMArena Vision: creative writingNot measured1099Only Llama 4 Maverick measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 Nano and Llama 4 Maverick
BenchmarkGPT-5 NanoLlama 4 MaverickLeader
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 Nano$0.0003Fits in one request
Llama 4 Maverick$0.0008Fits in one request

GPT-5 Nano costs less

Repository review

50K input + 3K output tokens

GPT-5 Nano$0.0037Fits in one request
Llama 4 Maverick$0.021Fits in one request

GPT-5 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-5 Nano$0.014Fits in one request
Llama 4 Maverick$0.080Fits 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-5 Nano and Llama 4 Maverick
SpecificationOpenAI GPT-5 NanoMeta Llama 4 Maverick
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedAugust 7, 2025April 5, 2025
Context window400K524K
Input $/Mtok$0.05$0.35
Output $/Mtok$0.40$1.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$0.109$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Nano better than Llama 4 Maverick for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5 Nano for output tokens 2.5x cheaper ($0.40 vs $1.00 per million) and a lower cost per solved task ($0.109 against $1.491).

Which is cheaper, GPT-5 Nano or Llama 4 Maverick?

GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, GPT-5 Nano costs $0.109 and Llama 4 Maverick $1.491.

Which has the bigger context window, GPT-5 Nano or Llama 4 Maverick?

Llama 4 Maverick, with 524K tokens against 400K.

How many benchmarks is the GPT-5 Nano vs Llama 4 Maverick comparison based on?

74 benchmarks have a result for both models as of October 22, 2026. GPT-5 Nano's coding index rests on 0 independent benchmarks and Llama 4 Maverick's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next