Enter opens the highlighted result. Esc closes.

Llama 3.2 3B Instruct vs Ministral 3 3B 2512

Llama 3.2 3B Instruct leads Ministral 3 3B 2512 on the Artificial Analysis Intelligence Index, 5.7 to 4.8, and Ministral 3 3B 2512 costs 3.3x less per output token ($0.10 vs $0.3325 per million). Updated October 22, 2026; 1 benchmarks have a result for both.

Replace Llama 3.2 3B Instruct Replace Ministral 3 3B 2512
Llama 3.2 3B InstructMeta Llama
Coding
No data
Overall
No data
Output $/M
$0.3325
1
Ministral 3 3B 2512Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.10
0
vs boards won of 1 shared

Llama 3.2 3B Instruct or Ministral 3 3B 2512: which to pick

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

Compare them on price, context and the boards below.

Model ALlama 3.2 3B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMinistral 3 3B 2512Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
1
Llama 3.2 3B Instruct only
34
Ministral 3 3B 2512 only
6
Like-for-like categories
1 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 3.2 3B Instruct not benchmarked, Ministral 3 3B 2512 not benchmarked.
Widest category
Intelligence, 0.9 points apart on average over 1 shared benchmark.
Widest single gap
AA Intelligence Index: Llama 3.2 3B Instruct 5.7 against Ministral 3 3B 2512 4.8, 0.9 points apart on a 0 to 100 scale.
Output price
Llama 3.2 3B Instruct $0.3325 against Ministral 3 3B 2512 $0.10 per million output tokens, 3.3x apart.
Context window
Both take 131K tokens.

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 3B InstructBarsMinistral 3 3B 2512Ties
Intelligence10
All shared boards10
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards, none shared
Coding benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
AA Coding IndexNot measured4.8Only Ministral 3 3B 2512 measured
LiveCodeBench (Artificial Analysis run)8.3%Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: coding1098Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: software and IT1103Not measuredOnly Llama 3.2 3B Instruct measured
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
AA Intelligence Index5.74.8Llama 3.2 3B Instruct
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
AA Agentic IndexNot measured0.8Only Ministral 3 3B 2512 measured
τ²-Bench Telecom21.1%Not measuredOnly Llama 3.2 3B Instruct measured
BALROG10.1%Not measuredOnly Llama 3.2 3B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)21.9%Not measuredOnly Llama 3.2 3B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Reasoning benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
GPQA Diamond (Artificial Analysis run)25.5%Not measuredOnly Llama 3.2 3B Instruct measured
Humanity's Last Exam (Artificial Analysis run)5.3%Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: hard prompts1095Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: expert1090Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: hard prompts in English1141Not measuredOnly Llama 3.2 3B Instruct measured
Neither model has a result on the other 17 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
AA Math Index3.3Not measuredOnly Llama 3.2 3B Instruct measured
AIME 2025 (Artificial Analysis run)3.3%Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: math1126Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: mathematical work1128Not measuredOnly Llama 3.2 3B Instruct measured
Neither model has a result on the other 9 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Knowledge benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
MMLU Pro (Artificial Analysis run)34.7%Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: science1106Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: medicine and healthcare1104Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: legal and government1115Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: business and finance1074Not measuredOnly Llama 3.2 3B Instruct measured
Neither model has a result on the other 13 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Web design benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
Design Arena: websitesNot measured1027Only Ministral 3 3B 2512 measured
Design Arena: game devNot measured948Only Ministral 3 3B 2512 measured
Design Arena: 3DNot measured962Only Ministral 3 3B 2512 measured
Design Arena: all code categoriesNot measured1010Only Ministral 3 3B 2512 measured
Neither model has a result on the other 5 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
General benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
IFBench26.2%Not measuredOnly Llama 3.2 3B Instruct measured
Long context reasoning (AA-LCR)4.3%Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text1110Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: instruction following1089Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: creative writing1094Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: English1180Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: non-English1019Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: Chinese1017Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: German1056Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: Russian949Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: multi-turn1105Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: longer queries1100Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: writing and language1096Not measuredOnly Llama 3.2 3B Instruct measured
LMArena Text: entertainment and media1083Not measuredOnly Llama 3.2 3B Instruct measured
Neither model has a result on the other 32 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Llama 3.2 3B Instruct and Ministral 3 3B 2512
BenchmarkLlama 3.2 3B InstructMinistral 3 3B 2512Leader
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 3B Instruct$0.0002Fits in one request
Ministral 3 3B 2512$0.0001Fits in one request

Ministral 3 3B 2512 costs less

Repository review

50K input + 3K output tokens

Llama 3.2 3B Instruct$0.0035Fits in one request
Ministral 3 3B 2512$0.0053Fits in one request

Llama 3.2 3B Instruct costs less

Agent loop

200K input + 10K output tokens

Llama 3.2 3B Instruct$0.013Exceeds the context window
Ministral 3 3B 2512$0.021Exceeds the context window

Llama 3.2 3B 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 3B Instruct and Ministral 3 3B 2512
SpecificationMeta Llama 3.2 3B InstructMistral Ministral 3 3B 2512
MakerMeta LlamaMistral AI
WeightsOpen weightsOpen weights
ReleasedSeptember 25, 2024December 2, 2025
Context window131K131K
Input $/Mtok$0.0505$0.10
Output $/Mtok$0.3325$0.10
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 3.2 3B Instruct better than Ministral 3 3B 2512 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, Llama 3.2 3B Instruct or Ministral 3 3B 2512?

Llama 3.2 3B Instruct costs $0.0505 per million input tokens and $0.3325 per million output tokens; Ministral 3 3B 2512 costs $0.10 and $0.10. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.2 3B Instruct or Ministral 3 3B 2512?

Neither: both take 131K tokens.

How many benchmarks is the Llama 3.2 3B Instruct vs Ministral 3 3B 2512 comparison based on?

1 benchmarks have a result for both models as of October 22, 2026. Llama 3.2 3B Instruct's coding index rests on 0 independent benchmarks and Ministral 3 3B 2512's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next