Enter opens the highlighted result. Esc closes.

Gemma 3 12B vs Mistral Small 3.1 24B

Gemma 3 12B costs 3.4x less per output token than Mistral Small 3.1 24B ($0.1625 vs $0.555 per million). Updated October 22, 2026; 22 benchmarks have a result for both.

Replace Gemma 3 12B Replace Mistral Small 3.1 24B
Gemma 3 12BGoogle
Coding
No data
Overall
28.0
Output $/M
$0.1625
20
Mistral Small 3.1 24BMistral AI
Coding
No data
Overall
No data
Output $/M
$0.555
2
vs boards won of 22 shared

Gemma 3 12B or Mistral Small 3.1 24B: which to pick

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

Pick Gemma 3 12B for output tokens 3.4x cheaper ($0.1625 vs $0.555 per million) and a larger context window (131K against 128K tokens).

Model AGemma 3 12BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Small 3.1 24BMistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
22
Gemma 3 12B only
21
Mistral Small 3.1 24B only
16
Like-for-like categories
5 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
Gemma 3 12B not benchmarked, Mistral Small 3.1 24B not benchmarked.
Widest category
Knowledge, 16.5 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: business and finance: Gemma 3 12B 1376 against Mistral Small 3.1 24B 1257, 19.8 points apart on a 0 to 100 scale.
Output price
Gemma 3 12B $0.1625 against Mistral Small 3.1 24B $0.555 per million output tokens, 3.4x apart.
Context window
Gemma 3 12B takes 131K tokens, Mistral Small 3.1 24B 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
CategoryGemma 3 12BBarsMistral Small 3.1 24BTies
Coding11
Reasoning21
Math20
Knowledge40
General110
All shared boards202
CodingLike-for-likeSix of these boards feed the Vibe Coding Index11
Coding benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
AA Coding Index5.8Not measuredOnly Gemma 3 12B measured
LiveCodeBench (Artificial Analysis run)13.7%Not measuredOnly Gemma 3 12B measured
SciCode16.4%Not measuredOnly Gemma 3 12B measured
Terminal-Bench Hard (Artificial Analysis run)0.8%Not measuredOnly Gemma 3 12B measured
LMArena Text: coding12811309Mistral Small 3.1 24B
LMArena Text: software and IT13131301Gemma 3 12B
SciCode0.0%Not measuredOnly Gemma 3 12B measured
Neither model has a result on the other 32 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
AA Intelligence Index3.8Not measuredOnly Gemma 3 12B measured
Epoch Capabilities Index123.5Not measuredOnly Gemma 3 12B measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
AA Agentic Index0.1Not measuredOnly Gemma 3 12B measured
τ²-Bench Telecom10.8%Not measuredOnly Gemma 3 12B measured
Berkeley Function Calling Leaderboard (BFCL)30.4%Not measuredOnly Gemma 3 12B measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
Reasoning benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
GPQA Diamond (Artificial Analysis run)34.9%Not measuredOnly Gemma 3 12B measured
Humanity's Last Exam (Artificial Analysis run)4.2%Not measuredOnly Gemma 3 12B measured
GPQA Diamond (Epoch AI run)39.5%Not measuredOnly Gemma 3 12B measured
LMArena Text: hard prompts13091278Gemma 3 12B
LMArena Text: expert12481257Mistral Small 3.1 24B
LMArena Text: hard prompts in English13181290Gemma 3 12B
LMArena Vision: diagramsNot measured1119Only Mistral Small 3.1 24B measured
LMArena Vision: homeworkNot measured1158Only Mistral Small 3.1 24B measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
AA Math Index18.3Not measuredOnly Gemma 3 12B measured
AIME 2025 (Artificial Analysis run)18.3%Not measuredOnly Gemma 3 12B measured
OTIS Mock AIME16.7%Not measuredOnly Gemma 3 12B measured
LMArena Text: math13071261Gemma 3 12B
LMArena Text: mathematical work13361271Gemma 3 12B
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
MMLU Pro (Artificial Analysis run)59.5%Not measuredOnly Gemma 3 12B measured
LMArena Text: science13661265Gemma 3 12B
LMArena Text: medicine and healthcare13341267Gemma 3 12B
LMArena Text: legal and government13811271Gemma 3 12B
LMArena Text: business and finance13761257Gemma 3 12B
Neither model has a result on the other 13 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index110
General benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 24BLeader
IFBench36.7%Not measuredOnly Gemma 3 12B measured
Long context reasoning (AA-LCR)8.3%Not measuredOnly Gemma 3 12B measured
DTBench48.8%Not measuredOnly Gemma 3 12B measured
LMCA4.5%Not measuredOnly Gemma 3 12B measured
LMArena Text13341277Gemma 3 12B
LMArena Text: instruction following12991263Gemma 3 12B
LMArena Text: creative writing13311252Gemma 3 12B
LMArena VisionNot measured1136Only Mistral Small 3.1 24B measured
LMArena Text: English13491295Gemma 3 12B
LMArena Text: non-English13181255Gemma 3 12B
LMArena Text: ChineseNot measured1253Only Mistral Small 3.1 24B measured
LMArena Text: German13701266Gemma 3 12B
LMArena Text: JapaneseNot measured1208Only Mistral Small 3.1 24B measured
LMArena Text: KoreanNot measured1207Only Mistral Small 3.1 24B measured
LMArena Text: FrenchNot measured1273Only Mistral Small 3.1 24B measured
LMArena Text: SpanishNot measured1284Only Mistral Small 3.1 24B measured
LMArena Text: Russian13351263Gemma 3 12B
LMArena Text: PolishNot measured1242Only Mistral Small 3.1 24B measured
LMArena Text: multi-turn13341270Gemma 3 12B
LMArena Text: longer queries13171299Gemma 3 12B
LMArena Text: writing and language13071268Gemma 3 12B
LMArena Text: entertainment and media12971250Gemma 3 12B
LMArena Vision: EnglishNot measured1157Only Mistral Small 3.1 24B measured
LMArena Vision: ChineseNot measured1155Only Mistral Small 3.1 24B measured
LMArena Vision: reading textNot measured1132Only Mistral Small 3.1 24B measured
LMArena Vision: humorNot measured1142Only Mistral Small 3.1 24B measured
LMArena Vision: captioningNot measured1153Only Mistral Small 3.1 24B measured
LMArena Vision: recognizing thingsNot measured1155Only Mistral Small 3.1 24B measured
LMArena Vision: creative writingNot measured1123Only Mistral Small 3.1 24B measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 3 12B and Mistral Small 3.1 24B
BenchmarkGemma 3 12BMistral Small 3.1 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

Gemma 3 12B$0.0002Fits in one request
Mistral Small 3.1 24B$0.0006Fits in one request

Gemma 3 12B costs less

Repository review

50K input + 3K output tokens

Gemma 3 12B$0.0042Fits in one request
Mistral Small 3.1 24B$0.019Fits in one request

Gemma 3 12B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 12B$0.017Exceeds the context window
Mistral Small 3.1 24B$0.076Exceeds the context window

Gemma 3 12B 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 Gemma 3 12B and Mistral Small 3.1 24B
SpecificationGoogle Gemma 3 12BMistral Small 3.1 24B
MakerGoogleMistral AI
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025March 17, 2025
Context window131K128K
Input $/Mtok$0.075$0.351
Output $/Mtok$0.1625$0.555
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 12B better than Mistral Small 3.1 24B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 12B for output tokens 3.4x cheaper ($0.1625 vs $0.555 per million) and a larger context window (131K against 128K tokens).

Which is cheaper, Gemma 3 12B or Mistral Small 3.1 24B?

Gemma 3 12B costs $0.075 per million input tokens and $0.1625 per million output tokens; Mistral Small 3.1 24B costs $0.351 and $0.555. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 3 12B or Mistral Small 3.1 24B?

Gemma 3 12B, with 131K tokens against 128K.

How many benchmarks is the Gemma 3 12B vs Mistral Small 3.1 24B comparison based on?

22 benchmarks have a result for both models as of October 22, 2026. Gemma 3 12B's coding index rests on 0 independent benchmarks and Mistral Small 3.1 24B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next