Enter opens the highlighted result. Esc closes.

Llama 3.2 1B Instruct vs Mistral Large

Updated October 21, 2026. 28 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Llama 3.2 1B Instruct Replace Mistral Large
Llama 3.2 1B InstructMeta Llama
Coding
No data
Overall
4.8
Output $/M
$0.201
1
Mistral LargeMistral AI
Coding
No data
Overall
5.8
Output $/M
$6.00
27
vs boards won of 28 shared

Decision reading

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

Llama 3.2 1B Instruct has the edge where output tokens cost 29.9x less, and where what matters is LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model ALlama 3.2 1B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral LargeMistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
28
Llama 3.2 1B Instruct only
9
Mistral Large only
16
Like-for-like categories
6 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 3.2 1B Instruct not benchmarked, Mistral Large not benchmarked.
Widest category
General, 36.6 points apart on average over 12 shared benchmarks.
Widest single gap
LMArena Text: Russian: Llama 3.2 1B Instruct 941 against Mistral Large 1252, 41.9 points apart on a 0 to 100 scale.
Output price
Llama 3.2 1B Instruct $0.201 against Mistral Large $6.00 per million output tokens, 29.9x apart.
Context window
Llama 3.2 1B Instruct takes 60K tokens, Mistral Large 128K.

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 3.2 1B InstructBarsMistral LargeTies
Coding03
Intelligence01
Reasoning14
Math02
Knowledge05
General012
All shared boards127
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
LiveCodeBench (Vals AI)Not measured37.1%Only Mistral Large measured
LiveCodeBench (Artificial Analysis run)1.9%17.8%Mistral Large
Terminal-Bench Hard (Artificial Analysis run)0.0%Not measuredOnly Llama 3.2 1B Instruct measured
LMArena Text: coding10701275Mistral Large
LMArena Text: software and IT10561274Mistral Large
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
AA Intelligence Index4.85.8Mistral Large
Epoch Capabilities IndexNot measured122.1Only Mistral Large measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
τ²-Bench Telecom0.0%Not measuredOnly Llama 3.2 1B Instruct measured
BALROG6.6%Not measuredOnly Llama 3.2 1B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
GPQA DiamondNot measured47.7%Only Mistral Large measured
GPQA Diamond (Artificial Analysis run)19.6%35.1%Mistral Large
Humanity's Last Exam (Artificial Analysis run)5.5%3.5%Llama 3.2 1B Instruct
GPQA Diamond (Epoch AI run)23.9%Not measuredOnly Llama 3.2 1B Instruct measured
LMArena Text: hard prompts10441257Mistral Large
LMArena Text: expert10071208Mistral Large
LMArena Text: hard prompts in English10871268Mistral Large
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
AIMENot measured9.2%Only Mistral Large measured
MATH 500 (Vals AI)Not measured74.4%Only Mistral Large measured
MGSM (Vals AI)Not measured87.2%Only Mistral Large measured
AA Math Index0.0Not measuredOnly Llama 3.2 1B Instruct measured
AIME 2025 (Artificial Analysis run)0.0%Not measuredOnly Llama 3.2 1B Instruct measured
OTIS Mock AIME0.6%Not measuredOnly Llama 3.2 1B Instruct measured
LMArena Text: math10861261Mistral Large
LMArena Text: mathematical work10981257Mistral Large
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
MMLU ProNot measured69.7%Only Mistral Large measured
TaxEval (Vals AI)Not measured63.8%Only Mistral Large measured
MedQA (Vals AI)Not measured76.2%Only Mistral Large measured
MMLU Pro (Artificial Analysis run)20.0%51.5%Mistral Large
MMLUNot measured68.8%Only Mistral Large measured
LMArena Text: science10551260Mistral Large
LMArena Text: medicine and healthcare10091255Mistral Large
LMArena Text: legal and government10711275Mistral Large
LMArena Text: business and finance10001238Mistral Large
Neither model has a result on the other 8 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index012
General benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
IFBench22.8%Not measuredOnly Llama 3.2 1B Instruct measured
Long context reasoning (AA-LCR)6.7%Not measuredOnly Llama 3.2 1B Instruct measured
DTBenchNot measured60.8%Only Mistral Large measured
LMArena Text10551265Mistral Large
LMArena Text: instruction following10311249Mistral Large
LMArena Text: creative writing10331242Mistral Large
LMArena Text: English11171284Mistral Large
LMArena Text: non-English9731235Mistral Large
LMArena Text: Chinese9591239Mistral Large
LMArena Text: German10141242Mistral Large
LMArena Text: JapaneseNot measured1170Only Mistral Large measured
LMArena Text: KoreanNot measured1202Only Mistral Large measured
LMArena Text: FrenchNot measured1325Only Mistral Large measured
LMArena Text: SpanishNot measured1268Only Mistral Large measured
LMArena Text: Russian9411252Mistral Large
LMArena Text: PolishNot measured1157Only Mistral Large measured
LMArena Text: multi-turn10301260Mistral Large
LMArena Text: longer queries10501261Mistral Large
LMArena Text: writing and language10301261Mistral Large
LMArena Text: entertainment and media10251230Mistral Large
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Llama 3.2 1B Instruct and Mistral Large
BenchmarkLlama 3.2 1B InstructMistral LargeLeader
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 3.2 1B Instruct$0.0001Fits in one request
Mistral Large$0.0050Fits in one request

Llama 3.2 1B Instruct costs less

Repository review

50K input + 3K output tokens

Llama 3.2 1B Instruct$0.0020Fits in one request
Mistral Large$0.118Fits in one request

Llama 3.2 1B Instruct costs less

Agent loop

200K input + 10K output tokens

Llama 3.2 1B Instruct$0.0074Exceeds the context window
Mistral Large$0.460Exceeds the context window

Llama 3.2 1B Instruct 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 3.2 1B Instruct and Mistral Large
SpecificationMeta Llama 3.2 1B InstructMistral Large
MakerMeta LlamaMistral AI
WeightsOpen weightsNo public weights listed
ReleasedSeptember 25, 2024February 26, 2024
Context window60K128K
Input $/Mtok$0.027$2.00
Output $/Mtok$0.201$6.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 3.2 1B Instruct better than Mistral Large for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Llama 3.2 1B Instruct has the edge where output tokens cost 29.9x less, and where what matters is LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Llama 3.2 1B Instruct or Mistral Large?

Llama 3.2 1B Instruct costs $0.027 per million input tokens and $0.201 per million output tokens; Mistral Large costs $2.00 and $6.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.2 1B Instruct or Mistral Large?

Mistral Large, with 128K tokens against 60K.

How many benchmarks is the Llama 3.2 1B Instruct vs Mistral Large comparison based on?

28 benchmarks have a result for both models as of October 21, 2026. Llama 3.2 1B Instruct's coding index rests on 0 independent benchmarks and Mistral Large's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next