Enter opens the highlighted result. Esc closes.

Gemma 3 12B vs Llama 4 Scout

Llama 4 Scout leads Gemma 3 12B on the Artificial Analysis Intelligence Index, 6.5 to 3.8, and Gemma 3 12B costs 3.1x less per output token ($0.1625 vs $0.50 per million). Updated October 22, 2026; 42 benchmarks have a result for both.

Replace Gemma 3 12B Replace Llama 4 Scout
Gemma 3 12BGoogle
Coding
No data
Overall
28.0
Output $/M
$0.1625
26
Llama 4 ScoutMeta Llama
Coding
No data
Overall
24.9
Output $/M
$0.50
16
vs boards won of 42 shared

Gemma 3 12B or Llama 4 Scout: 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 3.1x cheaper ($0.1625 vs $0.50 per million) and work measured by AA Coding Index or LiveCodeBench (Artificial Analysis run), where it leads.

Model AGemma 3 12BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 4 ScoutMeta LlamaNot benchmarkedNo coding benchmark$1.276 per solved task
Shared results
42
Gemma 3 12B only
1
Llama 4 Scout only
40
Like-for-like categories
7 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, Llama 4 Scout not benchmarked.
Widest category
Knowledge, 15.2 points apart on average over 5 shared benchmarks.
Widest single gap
GPQA Diamond (Artificial Analysis run): Gemma 3 12B 34.9% against Llama 4 Scout 58.7%, 23.8 points apart on a 0 to 100 scale.
Output price
Gemma 3 12B $0.1625 against Llama 4 Scout $0.50 per million output tokens, 3.1x apart.
Context window
Gemma 3 12B takes 131K tokens, Llama 4 Scout 1.31M.

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 12BBarsLlama 4 ScoutTies
Coding15
Intelligence02
Agentic work12
Reasoning42
Math50
Knowledge41
General114
All shared boards2616
CodingLike-for-likeSix of these boards feed the Vibe Coding Index15
Coding benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
SWE-bench VerifiedNot measured9.1%Only Llama 4 Scout measured
AA Coding Index5.88.2Llama 4 Scout
LiveCodeBench (Vals AI)Not measured38.5%Only Llama 4 Scout measured
LiveCodeBench (Artificial Analysis run)13.7%29.9%Llama 4 Scout
SciCode16.4%21.3%Llama 4 Scout
Terminal-Bench Hard (Artificial Analysis run)0.8%1.5%Llama 4 Scout
LMArena Text: coding12811286Llama 4 Scout
LMArena Text: software and IT13131286Gemma 3 12B
SciCode0.0%Not measuredOnly Gemma 3 12B measured
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 Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
AA Intelligence Index3.86.5Llama 4 Scout
Epoch Capabilities Index123.5129.6Llama 4 Scout
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
Agentic work benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
AA Agentic Index0.10.5Llama 4 Scout
τ²-Bench Telecom10.8%15.5%Llama 4 Scout
Berkeley Function Calling Leaderboard (BFCL)30.4%28.1%Gemma 3 12B
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
Reasoning benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
GPQA DiamondNot measured47.0%Only Llama 4 Scout measured
MMMU Pro (Vals AI)Not measured58.8%Only Llama 4 Scout measured
GPQA Diamond (Artificial Analysis run)34.9%58.7%Llama 4 Scout
Humanity's Last Exam (Artificial Analysis run)4.2%3.8%Gemma 3 12B
GPQA Diamond (Epoch AI run)39.5%51.8%Llama 4 Scout
ARC-AGINot measured0.5%Only Llama 4 Scout measured
ARC-AGI-2Not measured0.0%Only Llama 4 Scout measured
LMArena Text: hard prompts13091266Gemma 3 12B
LMArena Text: expert12481235Gemma 3 12B
LMArena Text: hard prompts in English13181293Gemma 3 12B
LMArena Vision: diagramsNot measured1125Only Llama 4 Scout measured
LMArena Vision: homeworkNot measured1148Only Llama 4 Scout measured
Kagi LLM BenchmarkNot measured36.9%Only Llama 4 Scout measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
AIMENot measured19.0%Only Llama 4 Scout measured
MATH 500 (Vals AI)Not measured79.2%Only Llama 4 Scout measured
MGSM (Vals AI)Not measured88.0%Only Llama 4 Scout measured
AA Math Index18.314.0Gemma 3 12B
AIME 2025 (Artificial Analysis run)18.3%14.0%Gemma 3 12B
OTIS Mock AIME16.7%7.8%Gemma 3 12B
MATH level 5Not measured62.3%Only Llama 4 Scout measured
LMArena Text: math13071287Gemma 3 12B
LMArena Text: mathematical work13361286Gemma 3 12B
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
Knowledge benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
MMLU ProNot measured69.6%Only Llama 4 Scout measured
LegalBench (Vals AI)Not measured72.0%Only Llama 4 Scout measured
CorpFin (Vals AI)Not measured46.8%Only Llama 4 Scout measured
TaxEval (Vals AI)Not measured55.2%Only Llama 4 Scout measured
MortgageTax (Vals AI)Not measured57.8%Only Llama 4 Scout measured
MedQA (Vals AI)Not measured50.9%Only Llama 4 Scout measured
MedCode (Vals AI)Not measured23.3%Only Llama 4 Scout measured
MMLU Pro (Artificial Analysis run)59.5%75.2%Llama 4 Scout
LMArena Text: science13661278Gemma 3 12B
LMArena Text: medicine and healthcare13341275Gemma 3 12B
LMArena Text: legal and government13811285Gemma 3 12B
LMArena Text: business and finance13761257Gemma 3 12B
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Web design benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
Design Arena: websitesNot measured750Only Llama 4 Scout measured
Design Arena: UI componentsNot measured765Only Llama 4 Scout measured
Design Arena: game devNot measured772Only Llama 4 Scout measured
Design Arena: data vizNot measured896Only Llama 4 Scout measured
Design Arena: all code categoriesNot measured789Only Llama 4 Scout measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index114
General benchmarks for Gemma 3 12B and Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
SAGE (Vals AI)Not measured34.8%Only Llama 4 Scout measured
MedScribe (Vals AI)Not measured50.6%Only Llama 4 Scout measured
IFBench36.7%39.5%Llama 4 Scout
Long context reasoning (AA-LCR)8.3%27.7%Llama 4 Scout
DTBench48.8%57.9%Llama 4 Scout
LMCA4.5%12.0%Llama 4 Scout
Fiction.LiveBenchNot measured36.0%Only Llama 4 Scout measured
LMArena Text13341279Gemma 3 12B
LMArena Text: instruction following12991248Gemma 3 12B
LMArena Text: creative writing13311249Gemma 3 12B
LMArena VisionNot measured1118Only Llama 4 Scout measured
LMArena Text: English13491304Gemma 3 12B
LMArena Text: non-English13181252Gemma 3 12B
LMArena Text: ChineseNot measured1255Only Llama 4 Scout measured
LMArena Text: German13701273Gemma 3 12B
LMArena Text: JapaneseNot measured1206Only Llama 4 Scout measured
LMArena Text: KoreanNot measured1207Only Llama 4 Scout measured
LMArena Text: FrenchNot measured1283Only Llama 4 Scout measured
LMArena Text: SpanishNot measured1278Only Llama 4 Scout measured
LMArena Text: Russian13351263Gemma 3 12B
LMArena Text: PolishNot measured1265Only Llama 4 Scout measured
LMArena Text: multi-turn13341280Gemma 3 12B
LMArena Text: longer queries13171265Gemma 3 12B
LMArena Text: writing and language13071269Gemma 3 12B
LMArena Text: entertainment and media12971242Gemma 3 12B
LMArena Vision: EnglishNot measured1143Only Llama 4 Scout measured
LMArena Vision: ChineseNot measured1106Only Llama 4 Scout measured
LMArena Vision: reading textNot measured1117Only Llama 4 Scout measured
LMArena Vision: humorNot measured1102Only Llama 4 Scout measured
LMArena Vision: creative writingNot measured1126Only Llama 4 Scout measured
Neither model has a result on the other 16 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 Llama 4 Scout
BenchmarkGemma 3 12BLlama 4 ScoutLeader
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
Llama 4 Scout$0.0004Fits in one request

Gemma 3 12B costs less

Repository review

50K input + 3K output tokens

Gemma 3 12B$0.0042Fits in one request
Llama 4 Scout$0.010Fits in one request

Gemma 3 12B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 12B$0.017Exceeds the context window
Llama 4 Scout$0.040Fits in one request

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 Llama 4 Scout
SpecificationGoogle Gemma 3 12BMeta Llama 4 Scout
MakerGoogleMeta Llama
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025April 5, 2025
Context window131K1.31M
Input $/Mtok$0.075$0.175
Output $/Mtok$0.1625$0.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computable$1.276
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 12B better than Llama 4 Scout for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 12B for output tokens 3.1x cheaper ($0.1625 vs $0.50 per million) and work measured by AA Coding Index or LiveCodeBench (Artificial Analysis run), where it leads.

Which is cheaper, Gemma 3 12B or Llama 4 Scout?

Gemma 3 12B costs $0.075 per million input tokens and $0.1625 per million output tokens; Llama 4 Scout costs $0.175 and $0.50. Cost per solved task is known for Llama 4 Scout only.

Which has the bigger context window, Gemma 3 12B or Llama 4 Scout?

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

How many benchmarks is the Gemma 3 12B vs Llama 4 Scout comparison based on?

42 benchmarks have a result for both models as of October 22, 2026. Gemma 3 12B's coding index rests on 0 independent benchmarks and Llama 4 Scout's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next