Enter opens the highlighted result. Esc closes.

Llama 4 Maverick vs Mistral Medium 3.1

Llama 4 Maverick leads Mistral Medium 3.1 on the Artificial Analysis Intelligence Index, 9.3 to 9.2, and Llama 4 Maverick costs 2.0x less per output token ($1.00 vs $2.00 per million). Updated October 21, 2026; 70 benchmarks have a result for both.

Replace Llama 4 Maverick Replace Mistral Medium 3.1
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
12
Mistral Medium 3.1Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
58
vs boards won of 70 shared

Llama 4 Maverick or Mistral Medium 3.1: 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 2.0x cheaper ($1.00 vs $2.00 per million) and a larger context window (524K against 131K tokens).

Model ALlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved taskModel BMistral Medium 3.1Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
70
Llama 4 Maverick only
15
Mistral Medium 3.1 only
4
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, Mistral Medium 3.1 not benchmarked.
Widest category
Web design, 28.8 points apart on average over 6 shared benchmarks.
Widest single gap
MedQA (Vals AI): Llama 4 Maverick 43.3% against Mistral Medium 3.1 78.2%, 34.9 points apart on a 0 to 100 scale.
Output price
Llama 4 Maverick $1.00 against Mistral Medium 3.1 $2.00 per million output tokens, 2.0x apart.
Context window
Llama 4 Maverick takes 524K tokens, Mistral Medium 3.1 131K.

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 MaverickBarsMistral Medium 3.1Ties
Coding17
Intelligence10
Agentic work02
Reasoning35
Math16
Knowledge47
Web design06
General225
All shared boards1258
CodingLike-for-likeSix of these boards feed the Vibe Coding Index17
Coding benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
Aider polyglot15.6%Not measuredOnly Llama 4 Maverick measured
SWE-bench Verified21.0%Not measuredOnly Llama 4 Maverick measured
AA Coding Index16.320.5Mistral Medium 3.1
LiveCodeBench (Vals AI)47.3%44.8%Llama 4 Maverick
LiveCodeBench (Artificial Analysis run)39.7%40.6%Mistral Medium 3.1
SciCode31.7%32.4%Mistral Medium 3.1
Terminal-Bench Hard (Artificial Analysis run)6.8%10.6%Mistral Medium 3.1
WeirdML24.5%Not measuredOnly Llama 4 Maverick measured
ALE-Bench173.0210.2Mistral Medium 3.1
LMArena Text: coding13011433Mistral Medium 3.1
LMArena Text: software and IT12991436Mistral Medium 3.1
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
AA Intelligence Index9.39.2Llama 4 Maverick
Epoch Capabilities Index132.2Not measuredOnly Llama 4 Maverick measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
AA Agentic Index0.61.9Mistral Medium 3.1
τ²-Bench Telecom17.8%40.6%Mistral Medium 3.1
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index35
Reasoning benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
GPQA Diamond69.4%Not measuredOnly Llama 4 Maverick measured
MMMU Pro (Vals AI)71.7%63.0%Llama 4 Maverick
GPQA Diamond (Artificial Analysis run)67.1%58.8%Llama 4 Maverick
Humanity's Last Exam (Artificial Analysis run)4.9%4.7%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 prompts12811426Mistral Medium 3.1
LMArena Text: expert12591408Mistral Medium 3.1
LMArena Text: hard prompts in English12951435Mistral Medium 3.1
LMArena Vision: diagrams11341175Mistral Medium 3.1
LMArena Vision: homework11641165Mistral Medium 3.1
Kagi LLM Benchmark55.9%Not measuredOnly Llama 4 Maverick measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index16
Math benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
AIME25.2%42.3%Mistral Medium 3.1
MATH 500 (Vals AI)85.2%87.0%Mistral Medium 3.1
MGSM (Vals AI)92.4%90.9%Llama 4 Maverick
AA Math Index19.338.3Mistral Medium 3.1
AIME 2025 (Artificial Analysis run)19.3%38.3%Mistral Medium 3.1
LMArena Text: math12991408Mistral Medium 3.1
LMArena Text: mathematical work12951412Mistral Medium 3.1
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index47
Knowledge benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
MMLU Pro79.4%75.3%Llama 4 Maverick
LegalBench (Vals AI)77.8%62.0%Llama 4 Maverick
CorpFin (Vals AI)49.7%50.7%Mistral Medium 3.1
TaxEval (Vals AI)66.6%70.3%Mistral Medium 3.1
MortgageTax (Vals AI)58.5%36.5%Llama 4 Maverick
MedQA (Vals AI)43.3%78.2%Mistral Medium 3.1
MedCode (Vals AI)36.5%Not measuredOnly Llama 4 Maverick measured
MMLU Pro (Artificial Analysis run)80.9%68.3%Llama 4 Maverick
GeoBench52.0%Not measuredOnly Llama 4 Maverick measured
LMArena Text: science12881444Mistral Medium 3.1
LMArena Text: medicine and healthcare12751449Mistral Medium 3.1
LMArena Text: legal and government12861439Mistral Medium 3.1
LMArena Text: business and finance12601418Mistral Medium 3.1
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
Design Arena: websites8711133Mistral Medium 3.1
Design Arena: UI components8991100Mistral Medium 3.1
Design Arena: game dev8381074Mistral Medium 3.1
Design Arena: data viz8821144Mistral Medium 3.1
Design Arena: 3D9011081Mistral Medium 3.1
Design Arena: all code categories8801120Mistral Medium 3.1
Design Arena: SVGNot measured993Only Mistral Medium 3.1 measured
Design Arena: ASCII artNot measured997Only Mistral Medium 3.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index225
General benchmarks for Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
SAGE (Vals AI)35.7%Not measuredOnly Llama 4 Maverick measured
MedScribe (Vals AI)54.2%Not measuredOnly Llama 4 Maverick measured
IFBench43.0%39.8%Llama 4 Maverick
Long context reasoning (AA-LCR)50.0%42.7%Llama 4 Maverick
DTBench61.9%67.5%Mistral Medium 3.1
LMCA15.9%19.1%Mistral Medium 3.1
Fiction.LiveBench46.2%Not measuredOnly Llama 4 Maverick measured
Creative writing (Lech Mazur)62.0%Not measuredOnly Llama 4 Maverick measured
LMArena Text12871424Mistral Medium 3.1
LMArena Text: instruction following12671398Mistral Medium 3.1
LMArena Text: creative writing12661391Mistral Medium 3.1
LMArena Vision11421172Mistral Medium 3.1
LMArena Text: English13031438Mistral Medium 3.1
LMArena Text: non-English12691408Mistral Medium 3.1
LMArena Text: Chinese12771447Mistral Medium 3.1
LMArena Text: German12911432Mistral Medium 3.1
LMArena Text: Japanese12061379Mistral Medium 3.1
LMArena Text: Korean12031380Mistral Medium 3.1
LMArena Text: French12591460Mistral Medium 3.1
LMArena Text: Spanish12931433Mistral Medium 3.1
LMArena Text: Russian12861411Mistral Medium 3.1
LMArena Text: Polish12751430Mistral Medium 3.1
LMArena Text: multi-turn12891418Mistral Medium 3.1
LMArena Text: longer queries12801406Mistral Medium 3.1
LMArena Text: writing and language12771395Mistral Medium 3.1
LMArena Text: entertainment and media12501390Mistral Medium 3.1
LMArena Vision: English11501179Mistral Medium 3.1
LMArena Vision: Chinese11411190Mistral Medium 3.1
LMArena Vision: reading text11431175Mistral Medium 3.1
LMArena Vision: humor11001168Mistral Medium 3.1
LMArena Vision: captioningNot measured1145Only Mistral Medium 3.1 measured
LMArena Vision: recognizing thingsNot measured1147Only Mistral Medium 3.1 measured
LMArena Vision: creative writing10991200Mistral Medium 3.1
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 Llama 4 Maverick and Mistral Medium 3.1
BenchmarkLlama 4 MaverickMistral Medium 3.1Leader
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
Mistral Medium 3.1$0.0014Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

Llama 4 Maverick$0.021Fits in one request
Mistral Medium 3.1$0.026Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

Llama 4 Maverick$0.080Fits in one request
Mistral Medium 3.1$0.100Exceeds the context window

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 Llama 4 Maverick and Mistral Medium 3.1
SpecificationMeta Llama 4 MaverickMistral Medium 3.1
MakerMeta LlamaMistral AI
WeightsOpen weightsNo public weights listed
ReleasedApril 5, 2025August 13, 2025
Context window524K131K
Input $/Mtok$0.35$0.40
Output $/Mtok$1.00$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$1.491Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 4 Maverick better than Mistral Medium 3.1 for coding?

Neither model has a coding score yet, 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 131K tokens).

Which is cheaper, Llama 4 Maverick or Mistral Medium 3.1?

Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens; Mistral Medium 3.1 costs $0.40 and $2.00. Cost per solved task is known for Llama 4 Maverick only.

Which has the bigger context window, Llama 4 Maverick or Mistral Medium 3.1?

Llama 4 Maverick, with 524K tokens against 131K.

How many benchmarks is the Llama 4 Maverick vs Mistral Medium 3.1 comparison based on?

70 benchmarks have a result for both models as of October 21, 2026. Llama 4 Maverick's coding index rests on 0 independent benchmarks and Mistral Medium 3.1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next