Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs Llama 4 Maverick

Updated October 21, 2026. 62 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.4 Mini Replace Llama 4 Maverick
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
62
Llama 4 MaverickMeta Llama
Coding
18.1
Overall
9.3
Output $/M
$0.6525
0
vs boards won of 62 shared

Decision reading

Pick GPT-5.4 Mini for coding: it scores 28.2 on the Vibe Coding Index against 18.1 for Llama 4 Maverick, though on 1 benchmark against 2.

Pick Llama 4 Maverick when output tokens cost 6.9x less, or when the context window is larger, 524K against 400K tokens.

Model AGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved taskModel BLlama 4 MaverickMeta Llama18.1/1002 independent benchmarks$1.491 per solved task
Shared results
62
GPT-5.4 Mini only
26
Llama 4 Maverick only
22
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-5.4 Mini 28.2 from 1 benchmark, Llama 4 Maverick 18.1 from 2 benchmarks.
Widest category
Agentic work, 41.4 points apart on average over 2 shared benchmarks.
Widest single gap
AIME: GPT-5.4 Mini 95.6% against Llama 4 Maverick 25.2%, 70.4 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against Llama 4 Maverick $0.6525 per million output tokens, 6.9x apart.
Context window
GPT-5.4 Mini 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-5.4 MiniBarsLlama 4 MaverickTies
Coding80
Intelligence20
Agentic work20
Reasoning110
Math30
Knowledge80
General280
All shared boards620
CodingLike-for-likeFour of these boards feed the Vibe Coding Index80
Coding benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench VerifiedNot measured21.0%Only Llama 4 Maverick measured
LMArena WebDev1397Not measuredOnly GPT-5.4 Mini measured
AA Coding Index56.116.3GPT-5.4 Mini
LiveCodeBench (Vals AI)81.5%47.3%GPT-5.4 Mini
SWE-bench Verified (Vals AI)73.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 4 (Vals AI)2.5%Not measuredOnly GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)48.0%Not measuredOnly GPT-5.4 Mini measured
Code migration (Vals AI)12.9%Not measuredOnly GPT-5.4 Mini measured
ProgramBench (Vals AI)0.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)54.7%Not measuredOnly GPT-5.4 Mini measured
LiveCodeBench (Artificial Analysis run)Not measured39.7%Only Llama 4 Maverick measured
SciCode52.1%31.7%GPT-5.4 Mini
Terminal-Bench Hard (Artificial Analysis run)52.3%6.8%GPT-5.4 Mini
FrontierCode27.0%Not measuredOnly GPT-5.4 Mini measured
WeirdML60.3%24.5%GPT-5.4 Mini
ALE-Bench1188.6173.0GPT-5.4 Mini
LMArena Text: coding14381301GPT-5.4 Mini
LMArena Text: software and IT14361299GPT-5.4 Mini
LMArena WebDev: React1386Not measuredOnly GPT-5.4 Mini measured
LMArena WebDev: HTML1419Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
AA Intelligence Index24.19.3GPT-5.4 Mini
Epoch Capabilities Index148.7132.2GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
AA Agentic Index17.90.6GPT-5.4 Mini
Finance Agent (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)8.8%Not measuredOnly GPT-5.4 Mini measured
Legal Research Bench (Vals AI)12.5%Not measuredOnly GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
τ²-Bench Telecom83.3%17.8%GPT-5.4 Mini
DeepResearch Bench36.3%Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
Reasoning benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
GPQA Diamond83.1%69.4%GPT-5.4 Mini
MMMU Pro (Vals AI)79.3%71.7%GPT-5.4 Mini
GPQA Diamond (Artificial Analysis run)87.5%67.1%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)28.1%4.9%GPT-5.4 Mini
GPQA Diamond (Epoch AI run)86.9%Not measuredOnly GPT-5.4 Mini measured
ARC-AGI63.7%4.4%GPT-5.4 Mini
ARC-AGI-218.9%0.0%GPT-5.4 Mini
SimpleBenchNot measured27.7%Only Llama 4 Maverick measured
Chess puzzles23.0%Not measuredOnly GPT-5.4 Mini measured
Mystery game puzzles11.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: hard prompts14241281GPT-5.4 Mini
LMArena Text: expert14351259GPT-5.4 Mini
LMArena Text: hard prompts in English14201295GPT-5.4 Mini
LMArena Vision: diagrams12661134GPT-5.4 Mini
LMArena Vision: homework12851164GPT-5.4 Mini
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
AIME95.6%25.2%GPT-5.4 Mini
MATH 500 (Vals AI)Not measured85.2%Only Llama 4 Maverick measured
MGSM (Vals AI)Not measured92.4%Only Llama 4 Maverick measured
AA Math IndexNot measured19.3Only Llama 4 Maverick measured
AIME 2025 (Artificial Analysis run)Not measured19.3%Only Llama 4 Maverick measured
OTIS Mock AIME88.9%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tiers 1 to 351.2%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tier 49.8%Not measuredOnly GPT-5.4 Mini measured
ProofBench21.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: math14181299GPT-5.4 Mini
LMArena Text: mathematical work14291295GPT-5.4 Mini
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
Knowledge benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
MMLU Pro84.5%79.4%GPT-5.4 Mini
LegalBench (Vals AI)Not measured77.8%Only Llama 4 Maverick measured
CaseLaw (Vals AI)51.7%Not measuredOnly GPT-5.4 Mini measured
CorpFin (Vals AI)60.9%49.7%GPT-5.4 Mini
TaxEval (Vals AI)71.2%66.6%GPT-5.4 Mini
MortgageTax (Vals AI)63.5%58.5%GPT-5.4 Mini
MedQA (Vals AI)Not measured43.3%Only Llama 4 Maverick measured
MedCode (Vals AI)Not measured36.5%Only Llama 4 Maverick measured
MMLU Pro (Artificial Analysis run)Not measured80.9%Only Llama 4 Maverick measured
SimpleQA Verified29.4%Not measuredOnly GPT-5.4 Mini measured
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science14171288GPT-5.4 Mini
LMArena Text: medicine and healthcare13951275GPT-5.4 Mini
LMArena Text: legal and government14141286GPT-5.4 Mini
LMArena Text: business and finance14181260GPT-5.4 Mini
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
Design Arena: websitesNot measured871Only Llama 4 Maverick measured
Design Arena: UI componentsNot measured899Only Llama 4 Maverick measured
Design Arena: game devNot measured838Only Llama 4 Maverick measured
Design Arena: data vizNot measured882Only Llama 4 Maverick measured
Design Arena: 3DNot measured901Only Llama 4 Maverick measured
Design Arena: all code categoriesNot measured880Only Llama 4 Maverick measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index280
General benchmarks for GPT-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 4 MaverickLeader
SAGE (Vals AI)50.8%35.7%GPT-5.4 Mini
MedScribe (Vals AI)Not measured54.2%Only Llama 4 Maverick measured
Vals Multimodal Index54.2%Not measuredOnly GPT-5.4 Mini measured
IFBench73.3%43.0%GPT-5.4 Mini
Long context reasoning (AA-LCR)77.0%50.0%GPT-5.4 Mini
DTBench80.0%61.9%GPT-5.4 Mini
LMCA40.8%15.9%GPT-5.4 Mini
Fiction.LiveBenchNot measured46.2%Only Llama 4 Maverick measured
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
LMArena Text14121287GPT-5.4 Mini
LMArena Text: instruction following14051267GPT-5.4 Mini
LMArena Text: creative writing13701266GPT-5.4 Mini
LMArena Vision12451142GPT-5.4 Mini
LMArena Text: English14121303GPT-5.4 Mini
LMArena Text: non-English14051269GPT-5.4 Mini
LMArena Text: Chinese14461277GPT-5.4 Mini
LMArena Text: German14081291GPT-5.4 Mini
LMArena Text: Japanese13751206GPT-5.4 Mini
LMArena Text: Korean13701203GPT-5.4 Mini
LMArena Text: French14411259GPT-5.4 Mini
LMArena Text: Spanish14051293GPT-5.4 Mini
LMArena Text: Russian14171286GPT-5.4 Mini
LMArena Text: Polish14151275GPT-5.4 Mini
LMArena Text: multi-turn14291289GPT-5.4 Mini
LMArena Text: longer queries14081280GPT-5.4 Mini
LMArena Text: writing and language13931277GPT-5.4 Mini
LMArena Text: entertainment and media13731250GPT-5.4 Mini
LMArena Vision: English12441150GPT-5.4 Mini
LMArena Vision: Chinese12861141GPT-5.4 Mini
LMArena Vision: reading text12531143GPT-5.4 Mini
LMArena Vision: humor12351100GPT-5.4 Mini
LMArena Vision: recognizing things1218Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: creative writing12221099GPT-5.4 Mini
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-5.4 Mini and Llama 4 Maverick
BenchmarkGPT-5.4 MiniLlama 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-5.4 Mini$0.0030Fits in one request
Llama 4 Maverick$0.0005Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Mini$0.051Fits in one request
Llama 4 Maverick$0.011Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Mini$0.195Fits in one request
Llama 4 Maverick$0.044Fits 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-5.4 Mini and Llama 4 Maverick
SpecificationOpenAI GPT-5.4 MiniMeta Llama 4 Maverick
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026April 5, 2025
Context window400K524K
Input $/Mtok$0.75$0.1875
Output $/Mtok$4.50$0.6525
Coding index28.218.1
Independent measurements behind it12
Cost per solved task$0.70$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Mini better than Llama 4 Maverick for coding?

Pick GPT-5.4 Mini for coding: it scores 28.2 on the Vibe Coding Index against 18.1 for Llama 4 Maverick, though on 1 benchmark against 2. Pick Llama 4 Maverick when output tokens cost 6.9x less, or when the context window is larger, 524K against 400K tokens.

Which is cheaper, GPT-5.4 Mini or Llama 4 Maverick?

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Llama 4 Maverick costs $0.1875 and $0.6525. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and Llama 4 Maverick $1.491.

Which has the bigger context window, GPT-5.4 Mini or Llama 4 Maverick?

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

How many benchmarks is the GPT-5.4 Mini vs Llama 4 Maverick comparison based on?

62 benchmarks have a result for both models as of October 21, 2026. GPT-5.4 Mini's coding index rests on 1 independent benchmark and Llama 4 Maverick's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next