Enter opens the highlighted result. Esc closes.

Llama 4 Maverick vs Qwen3 Coder 480B A35B

Qwen3 Coder 480B A35B leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 11.9 to 9.3, and Llama 4 Maverick costs 1.5x less per output token ($1.00 vs $1.50 per million). Updated October 21, 2026; 48 benchmarks have a result for both.

Replace Llama 4 Maverick Replace Qwen3 Coder 480B A35B
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
6
Qwen3 Coder 480B A35BQwen
Coding
No data
Overall
No data
Output $/M
$1.50
42
vs boards won of 48 shared

Llama 4 Maverick or Qwen3 Coder 480B A35B: which to pick

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

Pick Llama 4 Maverick for output tokens 1.5x cheaper ($1.00 vs $1.50 per million) and a larger context window (524K against 262K tokens).

Model ALlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved taskModel BQwen3 Coder 480B A35BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
48
Llama 4 Maverick only
37
Qwen3 Coder 480B A35B only
5
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
Llama 4 Maverick not benchmarked, Qwen3 Coder 480B A35B not benchmarked.
Widest category
Web design, 30.7 points apart on average over 5 shared benchmarks.
Widest single gap
SWE-bench Verified: Llama 4 Maverick 21.0% against Qwen3 Coder 480B A35B 69.6%, 48.6 points apart on a 0 to 100 scale.
Output price
Llama 4 Maverick $1.00 against Qwen3 Coder 480B A35B $1.50 per million output tokens, 1.5x apart.
Context window
Llama 4 Maverick takes 524K tokens, Qwen3 Coder 480B A35B 262K.

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
CategoryLlama 4 MaverickBarsQwen3 Coder 480B A35BTies
Coding07
Intelligence01
Agentic work01
Reasoning33
Math04
Knowledge14
Web design05
General217
All shared boards642
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
Coding benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
Aider polyglot15.6%Not measuredOnly Llama 4 Maverick measured
SWE-bench Verified21.0%69.6%Qwen3 Coder 480B A35B
LMArena WebDevNot measured1275Only Qwen3 Coder 480B A35B measured
AA Coding Index16.3Not measuredOnly Llama 4 Maverick measured
LiveCodeBench (Vals AI)47.3%Not measuredOnly Llama 4 Maverick measured
LiveCodeBench (Artificial Analysis run)39.7%58.5%Qwen3 Coder 480B A35B
SciCode31.7%Not measuredOnly Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)6.8%18.9%Qwen3 Coder 480B A35B
Terminal-BenchNot measured27.2%Only Qwen3 Coder 480B A35B measured
GSO-BenchNot measured4.9%Only Qwen3 Coder 480B A35B measured
WeirdML24.5%41.2%Qwen3 Coder 480B A35B
ALE-Bench173.0461.4Qwen3 Coder 480B A35B
LMArena Text: coding13011412Qwen3 Coder 480B A35B
LMArena Text: software and IT12991393Qwen3 Coder 480B A35B
LMArena WebDev: ReactNot measured1257Only Qwen3 Coder 480B A35B measured
LMArena WebDev: HTMLNot measured1287Only Qwen3 Coder 480B A35B measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
AA Intelligence Index9.311.9Qwen3 Coder 480B A35B
Epoch Capabilities Index132.2Not measuredOnly Llama 4 Maverick measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
AA Agentic Index0.6Not measuredOnly Llama 4 Maverick measured
τ²-Bench Telecom17.8%43.6%Qwen3 Coder 480B A35B
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
Reasoning benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
GPQA Diamond69.4%Not measuredOnly Llama 4 Maverick measured
MMMU Pro (Vals AI)71.7%Not measuredOnly Llama 4 Maverick measured
GPQA Diamond (Artificial Analysis run)67.1%61.8%Llama 4 Maverick
Humanity's Last Exam (Artificial Analysis run)4.9%4.5%Llama 4 Maverick
ARC-AGI4.4%Not measuredOnly Llama 4 Maverick measured
ARC-AGI-20.0%Not measuredOnly Llama 4 Maverick measured
SimpleBench27.7%Not measuredOnly Llama 4 Maverick measured
LMArena Text: hard prompts12811372Qwen3 Coder 480B A35B
LMArena Text: expert12591338Qwen3 Coder 480B A35B
LMArena Text: hard prompts in English12951380Qwen3 Coder 480B A35B
LMArena Vision: diagrams1134Not measuredOnly Llama 4 Maverick measured
LMArena Vision: homework1164Not measuredOnly Llama 4 Maverick measured
Kagi LLM Benchmark55.9%49.5%Llama 4 Maverick
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
AIME25.2%Not measuredOnly Llama 4 Maverick measured
MATH 500 (Vals AI)85.2%Not measuredOnly Llama 4 Maverick measured
MGSM (Vals AI)92.4%Not measuredOnly Llama 4 Maverick measured
AA Math Index19.339.3Qwen3 Coder 480B A35B
AIME 2025 (Artificial Analysis run)19.3%39.3%Qwen3 Coder 480B A35B
LMArena Text: math12991365Qwen3 Coder 480B A35B
LMArena Text: mathematical work12951367Qwen3 Coder 480B A35B
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
Knowledge benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
MMLU Pro79.4%Not measuredOnly Llama 4 Maverick measured
LegalBench (Vals AI)77.8%Not measuredOnly Llama 4 Maverick measured
CorpFin (Vals AI)49.7%Not measuredOnly Llama 4 Maverick measured
TaxEval (Vals AI)66.6%Not measuredOnly Llama 4 Maverick measured
MortgageTax (Vals AI)58.5%Not measuredOnly Llama 4 Maverick measured
MedQA (Vals AI)43.3%Not measuredOnly Llama 4 Maverick measured
MedCode (Vals AI)36.5%Not measuredOnly Llama 4 Maverick measured
MMLU Pro (Artificial Analysis run)80.9%78.8%Llama 4 Maverick
GeoBench52.0%Not measuredOnly Llama 4 Maverick measured
LMArena Text: science12881347Qwen3 Coder 480B A35B
LMArena Text: medicine and healthcare12751347Qwen3 Coder 480B A35B
LMArena Text: legal and government12861358Qwen3 Coder 480B A35B
LMArena Text: business and finance12601343Qwen3 Coder 480B A35B
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
Design Arena: websites8711159Qwen3 Coder 480B A35B
Design Arena: UI components8991113Qwen3 Coder 480B A35B
Design Arena: game dev8381099Qwen3 Coder 480B A35B
Design Arena: data viz8821084Qwen3 Coder 480B A35B
Design Arena: 3D901Not measuredOnly Llama 4 Maverick measured
Design Arena: all code categories8801143Qwen3 Coder 480B A35B
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index217
General benchmarks for Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
SAGE (Vals AI)35.7%Not measuredOnly Llama 4 Maverick measured
MedScribe (Vals AI)54.2%Not measuredOnly Llama 4 Maverick measured
IFBench43.0%40.5%Llama 4 Maverick
Long context reasoning (AA-LCR)50.0%45.7%Llama 4 Maverick
DTBench61.9%Not measuredOnly Llama 4 Maverick measured
LMCA15.9%Not measuredOnly Llama 4 Maverick measured
Fiction.LiveBench46.2%Not measuredOnly Llama 4 Maverick measured
Creative writing (Lech Mazur)62.0%Not measuredOnly Llama 4 Maverick measured
LMArena Text12871357Qwen3 Coder 480B A35B
LMArena Text: instruction following12671355Qwen3 Coder 480B A35B
LMArena Text: creative writing12661333Qwen3 Coder 480B A35B
LMArena Vision1142Not measuredOnly Llama 4 Maverick measured
LMArena Text: English13031359Qwen3 Coder 480B A35B
LMArena Text: non-English12691346Qwen3 Coder 480B A35B
LMArena Text: Chinese12771357Qwen3 Coder 480B A35B
LMArena Text: German12911325Qwen3 Coder 480B A35B
LMArena Text: Japanese12061311Qwen3 Coder 480B A35B
LMArena Text: Korean12031305Qwen3 Coder 480B A35B
LMArena Text: French12591398Qwen3 Coder 480B A35B
LMArena Text: Spanish12931360Qwen3 Coder 480B A35B
LMArena Text: Russian12861366Qwen3 Coder 480B A35B
LMArena Text: Polish12751344Qwen3 Coder 480B A35B
LMArena Text: multi-turn12891366Qwen3 Coder 480B A35B
LMArena Text: longer queries12801378Qwen3 Coder 480B A35B
LMArena Text: writing and language12771340Qwen3 Coder 480B A35B
LMArena Text: entertainment and media12501317Qwen3 Coder 480B A35B
LMArena Vision: English1150Not measuredOnly Llama 4 Maverick measured
LMArena Vision: Chinese1141Not measuredOnly Llama 4 Maverick measured
LMArena Vision: reading text1143Not measuredOnly Llama 4 Maverick measured
LMArena Vision: humor1100Not measuredOnly Llama 4 Maverick measured
LMArena Vision: creative writing1099Not measuredOnly 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 Llama 4 Maverick and Qwen3 Coder 480B A35B
BenchmarkLlama 4 MaverickQwen3 Coder 480B A35BLeader
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

Llama 4 Maverick$0.0008Fits in one request
Qwen3 Coder 480B A35B$0.0010Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

Llama 4 Maverick$0.021Fits in one request
Qwen3 Coder 480B A35B$0.019Fits in one request

Qwen3 Coder 480B A35B costs less

Agent loop

200K input + 10K output tokens

Llama 4 Maverick$0.080Fits in one request
Qwen3 Coder 480B A35B$0.075Fits in one request

Qwen3 Coder 480B A35B 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 Llama 4 Maverick and Qwen3 Coder 480B A35B
SpecificationMeta Llama 4 MaverickQwen3 Coder 480B A35B
MakerMeta LlamaQwen
WeightsOpen weightsOpen weights
ReleasedApril 5, 2025July 23, 2025
Context window524K262K
Input $/Mtok$0.35$0.30
Output $/Mtok$1.00$1.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved task$1.491Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 4 Maverick better than Qwen3 Coder 480B A35B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 4 Maverick for output tokens 1.5x cheaper ($1.00 vs $1.50 per million) and a larger context window (524K against 262K tokens).

Which is cheaper, Llama 4 Maverick or Qwen3 Coder 480B A35B?

Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens; Qwen3 Coder 480B A35B costs $0.30 and $1.50. Cost per solved task is known for Llama 4 Maverick only.

Which has the bigger context window, Llama 4 Maverick or Qwen3 Coder 480B A35B?

Llama 4 Maverick, with 524K tokens against 262K.

How many benchmarks is the Llama 4 Maverick vs Qwen3 Coder 480B A35B comparison based on?

48 benchmarks have a result for both models as of October 21, 2026. Llama 4 Maverick's coding index rests on 0 independent benchmarks and Qwen3 Coder 480B A35B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next