Enter opens the highlighted result. Esc closes.

Llama 4 Scout vs Mistral Medium 3

Updated October 21, 2026. 54 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Llama 4 Scout Replace Mistral Medium 3
Llama 4 ScoutMeta Llama
Coding
No data
Overall
6.5
Output $/M
$0.50
2
Mistral Medium 3Mistral AI
Coding
No data
Overall
9.0
Output $/M
$2.00
52
vs boards won of 54 shared

Decision reading

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

Llama 4 Scout has the edge where output tokens cost 4.0x less, and where the context window is larger, 1.31M against 131K tokens.

Model ALlama 4 ScoutMeta LlamaNot benchmarkedNo coding benchmark$1.276 per solved taskModel BMistral Medium 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
54
Llama 4 Scout only
26
Mistral Medium 3 only
3
Like-for-like categories
8 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
Llama 4 Scout not benchmarked, Mistral Medium 3 not benchmarked.
Widest category
Web design, 31.2 points apart on average over 5 shared benchmarks.
Widest single gap
Design Arena: websites: Llama 4 Scout 750 against Mistral Medium 3 1079, 41.1 points apart on a 0 to 100 scale.
Output price
Llama 4 Scout $0.50 against Mistral Medium 3 $2.00 per million output tokens, 4.0x apart.
Context window
Llama 4 Scout takes 1.31M tokens, Mistral Medium 3 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 ScoutBarsMistral Medium 3Ties
Coding04
Intelligence02
Agentic work01
Reasoning16
Math04
Knowledge05
Web design05
General125
All shared boards252
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
SWE-bench Verified9.1%Not measuredOnly Llama 4 Scout measured
AA Coding Index8.2Not measuredOnly Llama 4 Scout measured
LiveCodeBench (Vals AI)38.5%Not measuredOnly Llama 4 Scout measured
LiveCodeBench (Artificial Analysis run)29.9%40.0%Mistral Medium 3
SciCode21.3%Not measuredOnly Llama 4 Scout measured
Terminal-Bench Hard (Artificial Analysis run)1.5%3.8%Mistral Medium 3
LMArena Text: coding12861385Mistral Medium 3
LMArena Text: software and IT12861385Mistral Medium 3
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
AA Intelligence Index6.59.0Mistral Medium 3
Epoch Capabilities Index129.6134.0Mistral Medium 3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
AA Agentic Index0.5Not measuredOnly Llama 4 Scout measured
τ²-Bench Telecom15.5%24.3%Mistral Medium 3
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index16
Reasoning benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
GPQA Diamond47.0%Not measuredOnly Llama 4 Scout measured
MMMU Pro (Vals AI)58.8%Not measuredOnly Llama 4 Scout measured
GPQA Diamond (Artificial Analysis run)58.7%57.8%Llama 4 Scout
Humanity's Last Exam (Artificial Analysis run)3.8%4.1%Mistral Medium 3
GPQA Diamond (Epoch AI run)51.8%Not measuredOnly Llama 4 Scout measured
ARC-AGI0.5%Not measuredOnly Llama 4 Scout measured
ARC-AGI-20.0%Not measuredOnly Llama 4 Scout measured
LMArena Text: hard prompts12661364Mistral Medium 3
LMArena Text: expert12351342Mistral Medium 3
LMArena Text: hard prompts in English12931374Mistral Medium 3
LMArena Vision: diagrams11251155Mistral Medium 3
LMArena Vision: homework11481165Mistral Medium 3
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 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
AIME19.0%Not measuredOnly Llama 4 Scout measured
MATH 500 (Vals AI)79.2%Not measuredOnly Llama 4 Scout measured
MGSM (Vals AI)88.0%Not measuredOnly Llama 4 Scout measured
AA Math Index14.030.3Mistral Medium 3
AIME 2025 (Artificial Analysis run)14.0%30.3%Mistral Medium 3
OTIS Mock AIME7.8%Not measuredOnly Llama 4 Scout measured
MATH level 562.3%Not measuredOnly Llama 4 Scout measured
LMArena Text: math12871353Mistral Medium 3
LMArena Text: mathematical work12861354Mistral Medium 3
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
MMLU Pro69.6%Not measuredOnly Llama 4 Scout measured
LegalBench (Vals AI)72.0%Not measuredOnly Llama 4 Scout measured
CorpFin (Vals AI)46.8%Not measuredOnly Llama 4 Scout measured
TaxEval (Vals AI)55.2%Not measuredOnly Llama 4 Scout measured
MortgageTax (Vals AI)57.8%Not measuredOnly Llama 4 Scout measured
MedQA (Vals AI)50.9%Not measuredOnly Llama 4 Scout measured
MedCode (Vals AI)23.3%Not measuredOnly Llama 4 Scout measured
MMLU Pro (Artificial Analysis run)75.2%76.0%Mistral Medium 3
LMArena Text: science12781381Mistral Medium 3
LMArena Text: medicine and healthcare12751381Mistral Medium 3
LMArena Text: legal and government12851384Mistral Medium 3
LMArena Text: business and finance12571352Mistral Medium 3
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 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
Design Arena: websites7501079Mistral Medium 3
Design Arena: UI components7681024Mistral Medium 3
Design Arena: game dev7731018Mistral Medium 3
Design Arena: data viz8961034Mistral Medium 3
Design Arena: 3DNot measured1083Only Mistral Medium 3 measured
Design Arena: all code categories7901069Mistral Medium 3
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
General benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
SAGE (Vals AI)34.8%Not measuredOnly Llama 4 Scout measured
MedScribe (Vals AI)50.6%Not measuredOnly Llama 4 Scout measured
IFBench39.5%39.3%Llama 4 Scout
Long context reasoning (AA-LCR)27.7%31.3%Mistral Medium 3
DTBench57.9%62.3%Mistral Medium 3
LMCA12.0%Not measuredOnly Llama 4 Scout measured
Fiction.LiveBench36.0%Not measuredOnly Llama 4 Scout measured
LMArena Text12791370Mistral Medium 3
LMArena Text: instruction following12481338Mistral Medium 3
LMArena Text: creative writing12491343Mistral Medium 3
LMArena Vision11181157Mistral Medium 3
LMArena Text: English13041385Mistral Medium 3
LMArena Text: non-English12521353Mistral Medium 3
LMArena Text: Chinese12551374Mistral Medium 3
LMArena Text: German12731377Mistral Medium 3
LMArena Text: Japanese12061316Mistral Medium 3
LMArena Text: Korean12071304Mistral Medium 3
LMArena Text: French12831368Mistral Medium 3
LMArena Text: Spanish12781364Mistral Medium 3
LMArena Text: Russian12631359Mistral Medium 3
LMArena Text: Polish12651371Mistral Medium 3
LMArena Text: multi-turn12801384Mistral Medium 3
LMArena Text: longer queries12651360Mistral Medium 3
LMArena Text: writing and language12691352Mistral Medium 3
LMArena Text: entertainment and media12421335Mistral Medium 3
LMArena Vision: English11431172Mistral Medium 3
LMArena Vision: Chinese11061161Mistral Medium 3
LMArena Vision: reading text11171154Mistral Medium 3
LMArena Vision: humor11021145Mistral Medium 3
LMArena Vision: captioningNot measured1094Only Mistral Medium 3 measured
LMArena Vision: recognizing thingsNot measured1141Only Mistral Medium 3 measured
LMArena Vision: creative writing11261146Mistral Medium 3
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Llama 4 Scout and Mistral Medium 3
BenchmarkLlama 4 ScoutMistral Medium 3Leader
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 Scout$0.0004Fits in one request
Mistral Medium 3$0.0014Fits in one request

Llama 4 Scout costs less

Repository review

50K input + 3K output tokens

Llama 4 Scout$0.010Fits in one request
Mistral Medium 3$0.026Fits in one request

Llama 4 Scout costs less

Agent loop

200K input + 10K output tokens

Llama 4 Scout$0.040Fits in one request
Mistral Medium 3$0.100Exceeds the context window

Llama 4 Scout 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 Scout and Mistral Medium 3
SpecificationMeta Llama 4 ScoutMistral Medium 3
MakerMeta LlamaMistral AI
WeightsOpen weightsNo public weights listed
ReleasedApril 5, 2025May 7, 2025
Context window1.31M131K
Input $/Mtok$0.175$0.40
Output $/Mtok$0.50$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$1.276Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 4 Scout better than Mistral Medium 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Llama 4 Scout has the edge where output tokens cost 4.0x less, and where the context window is larger, 1.31M against 131K tokens.

Which is cheaper, Llama 4 Scout or Mistral Medium 3?

Llama 4 Scout costs $0.175 per million input tokens and $0.50 per million output tokens; Mistral Medium 3 costs $0.40 and $2.00. Cost per solved task is known for Llama 4 Scout only.

Which has the bigger context window, Llama 4 Scout or Mistral Medium 3?

Llama 4 Scout, with 1.31M tokens against 131K.

How many benchmarks is the Llama 4 Scout vs Mistral Medium 3 comparison based on?

54 benchmarks have a result for both models as of October 21, 2026. Llama 4 Scout's coding index rests on 0 independent benchmarks and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next