Enter opens the highlighted result. Esc closes.

GPT-5 Mini vs Llama 4 Maverick

GPT-5 Mini leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 20.6 to 9.3, and Llama 4 Maverick costs 2.0x less per output token ($1.00 vs $2.00 per million). Updated October 21, 2026; 79 benchmarks have a result for both.

Replace GPT-5 Mini Replace Llama 4 Maverick
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
79
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
0
vs boards won of 79 shared

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

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding.

Pick Llama 4 Maverick for output tokens 2.0x cheaper ($1.00 vs $2.00 per million) and a larger context window (524K against 400K tokens).

Model AGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved taskModel BLlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved task
Shared results
79
GPT-5 Mini only
22
Llama 4 Maverick only
6
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 Mini 34.2 from 2 benchmarks, Llama 4 Maverick not benchmarked.
Widest category
Agentic work, 53.2 points apart on average over 1 shared benchmark.
Widest single gap
AA Math Index: GPT-5 Mini 90.7 against Llama 4 Maverick 19.3, 71.4 points apart on a 0 to 100 scale.
Output price
GPT-5 Mini $2.00 against Llama 4 Maverick $1.00 per million output tokens, 2.0x apart.
Context window
GPT-5 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 MiniBarsLlama 4 MaverickTies
Coding80
Intelligence20
Agentic work10
Reasoning120
Math70
Knowledge120
Web design60
General310
All shared boards790
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
Coding benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench Verified59.8%21.0%GPT-5 Mini
SWE-bench Multilingual39.7%Not measuredOnly GPT-5 Mini measured
AA Coding IndexNot measured16.3Only Llama 4 Maverick measured
LiveCodeBench (Vals AI)86.6%47.3%GPT-5 Mini
SWE-bench Verified (Vals AI)60.8%Not measuredOnly GPT-5 Mini measured
Vibe Code Bench (Vals AI)14.2%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)83.8%39.7%GPT-5 Mini
SciCode39.0%31.7%GPT-5 Mini
Terminal-Bench Hard (Artificial Analysis run)33.3%6.8%GPT-5 Mini
Terminal-Bench34.8%Not measuredOnly GPT-5 Mini measured
WeirdML52.7%24.5%GPT-5 Mini
ALE-BenchNot measured173.0Only Llama 4 Maverick measured
LMArena Text: coding14061301GPT-5 Mini
LMArena Text: software and IT13941299GPT-5 Mini
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
AA Intelligence Index20.69.3GPT-5 Mini
Epoch Capabilities Index145.3132.2GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
AA Agentic IndexNot measured0.6Only Llama 4 Maverick measured
τ²-Bench Telecom71.1%17.8%GPT-5 Mini
Vending-Bench 2-$31Not measuredOnly GPT-5 Mini measured
Berkeley Function Calling Leaderboard (BFCL)55.5%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
GPQA Diamond80.3%69.4%GPT-5 Mini
MMMU Pro (Vals AI)78.9%71.7%GPT-5 Mini
GPQA Diamond (Artificial Analysis run)82.8%67.1%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)21.5%4.9%GPT-5 Mini
GPQA Diamond (Epoch AI run)75.0%Not measuredOnly GPT-5 Mini measured
ARC-AGI54.3%4.4%GPT-5 Mini
ARC-AGI-24.4%0.0%GPT-5 Mini
SimpleBenchNot measured27.7%Only Llama 4 Maverick measured
Chess puzzles24.0%Not measuredOnly GPT-5 Mini measured
Mystery game puzzles10.0%Not measuredOnly GPT-5 Mini measured
VPCT40.2%Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts13801281GPT-5 Mini
LMArena Text: expert13791259GPT-5 Mini
LMArena Text: hard prompts in English13831295GPT-5 Mini
LMArena Vision: diagrams12021134GPT-5 Mini
LMArena Vision: homework12101164GPT-5 Mini
Kagi LLM Benchmark70.3%55.9%GPT-5 Mini
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index70
Math benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
AIME91.5%25.2%GPT-5 Mini
MATH 500 (Vals AI)94.8%85.2%GPT-5 Mini
MGSM (Vals AI)92.6%92.4%GPT-5 Mini
AA Math Index90.719.3GPT-5 Mini
AIME 2025 (Artificial Analysis run)90.7%19.3%GPT-5 Mini
OTIS Mock AIME86.7%Not measuredOnly GPT-5 Mini measured
FrontierMath, tiers 1 to 346.7%Not measuredOnly GPT-5 Mini measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5 Mini measured
ProofBench9.0%Not measuredOnly GPT-5 Mini measured
MATH level 597.8%Not measuredOnly GPT-5 Mini measured
LMArena Text: math13781299GPT-5 Mini
LMArena Text: mathematical work13801295GPT-5 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index120
Knowledge benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
MMLU Pro82.2%79.4%GPT-5 Mini
LegalBench (Vals AI)81.8%77.8%GPT-5 Mini
CaseLaw (Vals AI)68.5%Not measuredOnly GPT-5 Mini measured
CorpFin (Vals AI)60.2%49.7%GPT-5 Mini
TaxEval (Vals AI)75.2%66.6%GPT-5 Mini
MortgageTax (Vals AI)66.9%58.5%GPT-5 Mini
MedQA (Vals AI)96.1%43.3%GPT-5 Mini
MedCode (Vals AI)43.0%36.5%GPT-5 Mini
MMLU Pro (Artificial Analysis run)83.7%80.9%GPT-5 Mini
SimpleQA Verified21.6%Not measuredOnly GPT-5 Mini measured
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science13711288GPT-5 Mini
LMArena Text: medicine and healthcare13801275GPT-5 Mini
LMArena Text: legal and government13751286GPT-5 Mini
LMArena Text: business and finance13581260GPT-5 Mini
FACTS Benchmark Suite38.6%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
Design Arena: websites1125871GPT-5 Mini
Design Arena: UI components1106899GPT-5 Mini
Design Arena: game dev1130838GPT-5 Mini
Design Arena: data viz1130882GPT-5 Mini
Design Arena: 3D1037901GPT-5 Mini
Design Arena: all code categories1115880GPT-5 Mini
Design Arena: SVG1091Not measuredOnly GPT-5 Mini measured
Design Arena: ASCII art1125Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index310
General benchmarks for GPT-5 Mini and Llama 4 Maverick
BenchmarkGPT-5 MiniLlama 4 MaverickLeader
SAGE (Vals AI)43.0%35.7%GPT-5 Mini
MedScribe (Vals AI)80.6%54.2%GPT-5 Mini
IFBench75.4%43.0%GPT-5 Mini
Long context reasoning (AA-LCR)72.3%50.0%GPT-5 Mini
DTBench80.5%61.9%GPT-5 Mini
LMCA34.2%15.9%GPT-5 Mini
Fiction.LiveBench69.4%46.2%GPT-5 Mini
Creative writing (Lech Mazur)83.1%62.0%GPT-5 Mini
LMArena Text13731287GPT-5 Mini
LMArena Text: instruction following13571267GPT-5 Mini
LMArena Text: creative writing13251266GPT-5 Mini
LMArena Vision12021142GPT-5 Mini
LMArena Text: English13791303GPT-5 Mini
LMArena Text: non-English13631269GPT-5 Mini
LMArena Text: Chinese13861277GPT-5 Mini
LMArena Text: German13661291GPT-5 Mini
LMArena Text: Japanese13411206GPT-5 Mini
LMArena Text: Korean13081203GPT-5 Mini
LMArena Text: French13861259GPT-5 Mini
LMArena Text: Spanish13541293GPT-5 Mini
LMArena Text: Russian13621286GPT-5 Mini
LMArena Text: Polish13781275GPT-5 Mini
LMArena Text: multi-turn13631289GPT-5 Mini
LMArena Text: longer queries13551280GPT-5 Mini
LMArena Text: writing and language13441277GPT-5 Mini
LMArena Text: entertainment and media13401250GPT-5 Mini
LMArena Vision: English12161150GPT-5 Mini
LMArena Vision: Chinese12141141GPT-5 Mini
LMArena Vision: reading text11991143GPT-5 Mini
LMArena Vision: humor12051100GPT-5 Mini
LMArena Vision: captioning1217Not measuredOnly GPT-5 Mini measured
LMArena Vision: recognizing things1226Not measuredOnly GPT-5 Mini measured
LMArena Vision: creative writing11811099GPT-5 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 Mini and Llama 4 Maverick
BenchmarkGPT-5 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 Mini$0.0013Fits in one request
Llama 4 Maverick$0.0008Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

GPT-5 Mini$0.018Fits in one request
Llama 4 Maverick$0.021Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5 Mini$0.070Fits in one request
Llama 4 Maverick$0.080Fits in one request

GPT-5 Mini 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 Mini and Llama 4 Maverick
SpecificationOpenAI GPT-5 MiniMeta Llama 4 Maverick
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedAugust 7, 2025April 5, 2025
Context window400K524K
Input $/Mtok$0.25$0.35
Output $/Mtok$2.00$1.00
Coding index34.2Not benchmarked
Independent measurements behind it20
Cost per solved task$0.08$1.491
SourceOpenRouter listingOpenRouter listing

Questions

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

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding. Pick Llama 4 Maverick for output tokens 2.0x cheaper ($1.00 vs $2.00 per million) and a larger context window (524K against 400K tokens).

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

GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, GPT-5 Mini costs $0.08 and Llama 4 Maverick $1.491.

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

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

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

79 benchmarks have a result for both models as of October 21, 2026. GPT-5 Mini's coding index rests on 2 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