Enter opens the highlighted result. Esc closes.

Ministral 3 8B 2512 vs Mistral Small 3.2 24B

Ministral 3 8B 2512 costs 2.0x less per output token than Mistral Small 3.2 24B ($0.15 vs $0.30 per million). Updated October 22, 2026; 3 benchmarks have a result for both.

Replace Ministral 3 8B 2512 Replace Mistral Small 3.2 24B
Ministral 3 8B 2512Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.15
3
Mistral Small 3.2 24BMistral AI
Coding
No data
Overall
No data
Output $/M
$0.30
0
vs boards won of 3 shared

Ministral 3 8B 2512 or Mistral Small 3.2 24B: which to pick

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

Pick Ministral 3 8B 2512 for output tokens 2.0x cheaper ($0.15 vs $0.30 per million) and a larger context window (262K against 256K tokens).

Model AMinistral 3 8B 2512Mistral AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Small 3.2 24BMistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
3
Ministral 3 8B 2512 only
4
Mistral Small 3.2 24B only
2
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
Ministral 3 8B 2512 not benchmarked, Mistral Small 3.2 24B not benchmarked.
Widest category
Web design, 17.3 points apart on average over 3 shared benchmarks.
Widest single gap
Design Arena: websites: Ministral 3 8B 2512 1065 against Mistral Small 3.2 24B 896, 21.1 points apart on a 0 to 100 scale.
Output price
Ministral 3 8B 2512 $0.15 against Mistral Small 3.2 24B $0.30 per million output tokens, 2.0x apart.
Context window
Ministral 3 8B 2512 takes 262K tokens, Mistral Small 3.2 24B 256K.

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
CategoryMinistral 3 8B 2512BarsMistral Small 3.2 24BTies
Web design30
All shared boards30
CodingDirectional onlySix of these boards feed the Vibe Coding Index1 board, none shared
Coding benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
AA Coding Index9.7Not measuredOnly Ministral 3 8B 2512 measured
Neither model has a result on the other 42 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Intelligence benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
AA Intelligence Index5.5Not measuredOnly Ministral 3 8B 2512 measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
AA Agentic Index0.6Not measuredOnly Ministral 3 8B 2512 measured
Neither model has a result on the other 41 boards here
ReasoningNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Reasoning benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
Neither model has a result on 23 boards here
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Math benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
Neither model has a result on 14 boards here
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Knowledge benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
Neither model has a result on 20 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index30
Web design benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
Design Arena: websites1065896Ministral 3 8B 2512
Design Arena: UI componentsNot measured904Only Mistral Small 3.2 24B measured
Design Arena: game dev990889Ministral 3 8B 2512
Design Arena: data vizNot measured929Only Mistral Small 3.2 24B measured
Design Arena: 3D1031Not measuredOnly Ministral 3 8B 2512 measured
Design Arena: all code categories1052907Ministral 3 8B 2512
Neither model has a result on the other 3 boards here
GeneralNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
General benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
Neither model has a result on 48 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Ministral 3 8B 2512 and Mistral Small 3.2 24B
BenchmarkMinistral 3 8B 2512Mistral Small 3.2 24BLeader
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

Ministral 3 8B 2512$0.0002Fits in one request
Mistral Small 3.2 24B$0.0003Fits in one request

Ministral 3 8B 2512 costs less

Repository review

50K input + 3K output tokens

Ministral 3 8B 2512$0.0080Fits in one request
Mistral Small 3.2 24B$0.0059Fits in one request

Mistral Small 3.2 24B costs less

Agent loop

200K input + 10K output tokens

Ministral 3 8B 2512$0.032Fits in one request
Mistral Small 3.2 24B$0.023Fits in one request

Mistral Small 3.2 24B 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 Ministral 3 8B 2512 and Mistral Small 3.2 24B
SpecificationMistral Ministral 3 8B 2512Mistral Small 3.2 24B
MakerMistral AIMistral AI
WeightsOpen weightsOpen weights
ReleasedDecember 2, 2025June 20, 2025
Context window262K256K
Input $/Mtok$0.15$0.10
Output $/Mtok$0.15$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Ministral 3 8B 2512 better than Mistral Small 3.2 24B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Ministral 3 8B 2512 for output tokens 2.0x cheaper ($0.15 vs $0.30 per million) and a larger context window (262K against 256K tokens).

Which is cheaper, Ministral 3 8B 2512 or Mistral Small 3.2 24B?

Ministral 3 8B 2512 costs $0.15 per million input tokens and $0.15 per million output tokens; Mistral Small 3.2 24B costs $0.10 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, Ministral 3 8B 2512 or Mistral Small 3.2 24B?

Ministral 3 8B 2512, with 262K tokens against 256K.

How many benchmarks is the Ministral 3 8B 2512 vs Mistral Small 3.2 24B comparison based on?

3 benchmarks have a result for both models as of October 22, 2026. Ministral 3 8B 2512's coding index rests on 0 independent benchmarks and Mistral Small 3.2 24B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next