Enter opens the highlighted result. Esc closes.

GPT-4.1 vs Llama 4 Maverick

GPT-4.1 leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 12.7 to 9.3, and Llama 4 Maverick costs 8.0x less per output token ($1.00 vs $8.00 per million). Updated October 22, 2026; 78 benchmarks have a result for both.

Replace GPT-4.1 Replace Llama 4 Maverick
GPT-4.1OpenAI
Coding
No data
Overall
36.5
Output $/M
$8.00
69
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
8
vs boards won of 78 shared, 1 tied

GPT-4.1 or Llama 4 Maverick: which to pick

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

Pick GPT-4.1 for a lower cost per solved task ($0.37 against $1.491) and a larger context window (1.05M against 524K tokens).

Model AGPT-4.1OpenAINot benchmarkedNo coding benchmark$0.37 per solved taskModel BLlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved task
Shared results
78
GPT-4.1 only
14
Llama 4 Maverick only
7
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 not benchmarked, Llama 4 Maverick not benchmarked.
Widest category
Agentic work, 29.2 points apart on average over 1 shared benchmark.
Widest single gap
MedQA (Vals AI): GPT-4.1 91.2% against Llama 4 Maverick 43.3%, 47.9 points apart on a 0 to 100 scale.
Output price
GPT-4.1 $8.00 against Llama 4 Maverick $1.00 per million output tokens, 8.0x apart.
Context window
GPT-4.1 takes 1.05M 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-4.1BarsLlama 4 MaverickTies
Coding90
Intelligence20
Agentic work10
Reasoning85
Math61
Knowledge111
Web design51
General2701 tie
All shared boards6981 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index90
Coding benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
Aider polyglot52.4%15.6%GPT-4.1
SWE-bench Verified39.6%21.0%GPT-4.1
SWE-bench Multimodal31.1%Not measuredOnly GPT-4.1 measured
AA Coding IndexNot measured16.3Only Llama 4 Maverick measured
LiveCodeBench (Vals AI)54.7%47.3%GPT-4.1
LiveCodeBench (Artificial Analysis run)45.7%39.7%GPT-4.1
SciCodeNot measured31.7%Only Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)13.6%6.8%GPT-4.1
WeirdML39.0%24.5%GPT-4.1
ALE-Bench558.1173.0GPT-4.1
LMArena Text: coding13901301GPT-4.1
LMArena Text: software and IT13911299GPT-4.1
SciCode4.6%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
AA Intelligence Index12.79.3GPT-4.1
Epoch Capabilities Index136.7132.2GPT-4.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
AA Agentic IndexNot measured0.6Only Llama 4 Maverick measured
τ²-Bench Telecom47.1%17.8%GPT-4.1
Berkeley Function Calling Leaderboard (BFCL)54.0%Not measuredOnly GPT-4.1 measured
BrowseComp-Plus36.4%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index85
Reasoning benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
GPQA Diamond65.4%69.4%Llama 4 Maverick
MMMU Pro (Vals AI)72.4%71.7%GPT-4.1
GPQA Diamond (Artificial Analysis run)66.6%67.1%Llama 4 Maverick
Humanity's Last Exam (Artificial Analysis run)4.2%4.9%Llama 4 Maverick
GPQA Diamond (Epoch AI run)66.9%Not measuredOnly GPT-4.1 measured
ARC-AGI5.5%4.4%GPT-4.1
ARC-AGI-20.4%0.0%GPT-4.1
SimpleBench27.0%27.7%Llama 4 Maverick
Chess puzzles3.0%Not measuredOnly GPT-4.1 measured
LMArena Text: hard prompts13841281GPT-4.1
LMArena Text: expert13641259GPT-4.1
LMArena Text: hard prompts in English13931295GPT-4.1
LMArena Vision: diagrams12151134GPT-4.1
LMArena Vision: homework12481164GPT-4.1
Kagi LLM Benchmark52.3%55.9%Llama 4 Maverick
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index61
Math benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
AIME39.6%25.2%GPT-4.1
MATH 500 (Vals AI)87.2%85.2%GPT-4.1
MGSM (Vals AI)87.7%92.4%Llama 4 Maverick
AA Math Index34.719.3GPT-4.1
AIME 2025 (Artificial Analysis run)34.7%19.3%GPT-4.1
OTIS Mock AIME38.3%Not measuredOnly GPT-4.1 measured
FrontierMath, tiers 1 to 36.0%Not measuredOnly GPT-4.1 measured
MATH level 583.0%Not measuredOnly GPT-4.1 measured
LMArena Text: math13691299GPT-4.1
LMArena Text: mathematical work13601295GPT-4.1
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
MMLU Pro80.5%79.4%GPT-4.1
LegalBench (Vals AI)83.1%77.8%GPT-4.1
CaseLaw (Vals AI)69.9%Not measuredOnly GPT-4.1 measured
CorpFin (Vals AI)63.0%49.7%GPT-4.1
TaxEval (Vals AI)75.1%66.6%GPT-4.1
MortgageTax (Vals AI)65.9%58.5%GPT-4.1
MedQA (Vals AI)91.2%43.3%GPT-4.1
MedCode (Vals AI)Not measured36.5%Only Llama 4 Maverick measured
MMLU Pro (Artificial Analysis run)80.6%80.9%Llama 4 Maverick
SimpleQA Verified31.1%Not measuredOnly GPT-4.1 measured
GeoBench72.0%52.0%GPT-4.1
LMArena Text: science13821288GPT-4.1
LMArena Text: medicine and healthcare13791275GPT-4.1
LMArena Text: legal and government13991286GPT-4.1
LMArena Text: business and finance13691260GPT-4.1
FACTS Benchmark Suite45.8%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index51
Web design benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
Design Arena: websites1038871GPT-4.1
Design Arena: UI components997896GPT-4.1
Design Arena: game dev1079837GPT-4.1
Design Arena: data viz1104882GPT-4.1
Design Arena: 3D849900Llama 4 Maverick
Design Arena: all code categories1025879GPT-4.1
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index270
General benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 4 MaverickLeader
SAGE (Vals AI)Not measured35.7%Only Llama 4 Maverick measured
MedScribe (Vals AI)Not measured54.2%Only Llama 4 Maverick measured
IFBench43.0%43.0%Tie
Long context reasoning (AA-LCR)68.3%50.0%GPT-4.1
DTBench68.3%61.9%GPT-4.1
LMCA25.6%15.9%GPT-4.1
Fiction.LiveBench63.9%46.2%GPT-4.1
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
LMArena Text13831287GPT-4.1
LMArena Text: instruction following13671267GPT-4.1
LMArena Text: creative writing13631266GPT-4.1
LMArena Vision12101142GPT-4.1
LMArena Text: English13921303GPT-4.1
LMArena Text: non-English13701269GPT-4.1
LMArena Text: Chinese13821277GPT-4.1
LMArena Text: German13811291GPT-4.1
LMArena Text: Japanese13191206GPT-4.1
LMArena Text: Korean13381203GPT-4.1
LMArena Text: French13821259GPT-4.1
LMArena Text: Spanish13761293GPT-4.1
LMArena Text: Russian13771286GPT-4.1
LMArena Text: Polish13891275GPT-4.1
LMArena Text: multi-turn13971289GPT-4.1
LMArena Text: longer queries13851280GPT-4.1
LMArena Text: writing and language13711277GPT-4.1
LMArena Text: entertainment and media13651250GPT-4.1
LMArena Vision: English12091150GPT-4.1
LMArena Vision: Chinese12261141GPT-4.1
LMArena Vision: reading text12181143GPT-4.1
LMArena Vision: humor11961100GPT-4.1
LMArena Vision: captioning1207Not measuredOnly GPT-4.1 measured
LMArena Vision: recognizing things1208Not measuredOnly GPT-4.1 measured
LMArena Vision: creative writing12101099GPT-4.1
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4.1 and Llama 4 Maverick
BenchmarkGPT-4.1Llama 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-4.1$0.0060Fits in one request
Llama 4 Maverick$0.0008Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

GPT-4.1$0.124Fits in one request
Llama 4 Maverick$0.021Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

GPT-4.1$0.480Fits in one request
Llama 4 Maverick$0.080Fits in one request

Llama 4 Maverick 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 and Llama 4 Maverick
SpecificationOpenAI GPT-4.1Meta Llama 4 Maverick
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedApril 14, 2025April 5, 2025
Context window1.05M524K
Input $/Mtok$2.00$0.35
Output $/Mtok$8.00$1.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$0.37$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 better than Llama 4 Maverick for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 for a lower cost per solved task ($0.37 against $1.491) and a larger context window (1.05M against 524K tokens).

Which is cheaper, GPT-4.1 or Llama 4 Maverick?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, GPT-4.1 costs $0.37 and Llama 4 Maverick $1.491.

Which has the bigger context window, GPT-4.1 or Llama 4 Maverick?

GPT-4.1, with 1.05M tokens against 524K.

How many benchmarks is the GPT-4.1 vs Llama 4 Maverick comparison based on?

78 benchmarks have a result for both models as of October 22, 2026. GPT-4.1'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