Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs Llama 4 Scout

Gemma 4 31B leads Llama 4 Scout on the Artificial Analysis Intelligence Index, 14.7 to 6.5, and Gemma 4 31B costs 1.3x less per output token ($0.40 vs $0.50 per million). Updated October 22, 2026; 51 benchmarks have a result for both.

Replace Gemma 4 31B Replace Llama 4 Scout
Gemma 4 31BGoogle
Coding
39.0
Overall
42.1
Output $/M
$0.40
51
Llama 4 ScoutMeta Llama
Coding
No data
Overall
24.9
Output $/M
$0.50
0
vs boards won of 51 shared

Gemma 4 31B or Llama 4 Scout: which to pick

Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; Llama 4 Scout has none, so the two cannot be ranked on coding.

Pick Llama 4 Scout for a larger context window (1.31M against 262K tokens).

Model AGemma 4 31BGoogle39.0/1002 independent benchmarksNo cost per solved taskModel BLlama 4 ScoutMeta LlamaNot benchmarkedNo coding benchmark$1.276 per solved task
Shared results
51
Gemma 4 31B only
20
Llama 4 Scout only
31
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 4 31B 39.0 from 2 benchmarks, Llama 4 Scout not benchmarked.
Widest category
Math, 41.6 points apart on average over 3 shared benchmarks.
Widest single gap
OTIS Mock AIME: Gemma 4 31B 73.3% against Llama 4 Scout 7.8%, 65.6 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against Llama 4 Scout $0.50 per million output tokens, 1.3x apart.
Context window
Gemma 4 31B takes 262K 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 4 31BBarsLlama 4 ScoutTies
Coding50
Intelligence20
Agentic work20
Reasoning90
Math30
Knowledge50
General250
All shared boards510
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 4 ScoutLeader
SWE-bench VerifiedNot measured9.1%Only Llama 4 Scout measured
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev1367Not measuredOnly Gemma 4 31B measured
AA Coding Index43.48.2Gemma 4 31B
LiveCodeBench (Vals AI)Not measured38.5%Only Llama 4 Scout measured
LiveCodeBench (Artificial Analysis run)Not measured29.9%Only Llama 4 Scout measured
SciCode45.5%21.3%Gemma 4 31B
Terminal-Bench Hard (Artificial Analysis run)36.4%1.5%Gemma 4 31B
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5Not measuredOnly Gemma 4 31B measured
LMArena Text: coding14591286Gemma 4 31B
LMArena Text: software and IT14631286Gemma 4 31B
LMArena WebDev: React1359Not measuredOnly Gemma 4 31B measured
LMArena WebDev: HTML1380Not measuredOnly Gemma 4 31B measured
SciCode8.9%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 4 ScoutLeader
AA Intelligence Index14.76.5Gemma 4 31B
Epoch Capabilities Index143.0129.6Gemma 4 31B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 4 ScoutLeader
AA Agentic Index4.20.5Gemma 4 31B
LiveBench research44.4%Not measuredOnly Gemma 4 31B measured
LiveBench browser4.0%Not measuredOnly Gemma 4 31B measured
LiveBench long agentic13.3%Not measuredOnly Gemma 4 31B measured
τ²-Bench Telecom65.5%15.5%Gemma 4 31B
Berkeley Function Calling Leaderboard (BFCL)Not measured28.1%Only Llama 4 Scout measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 4 ScoutLeader
GPQA DiamondNot measured47.0%Only Llama 4 Scout measured
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
MMMU Pro (Vals AI)Not measured58.8%Only Llama 4 Scout measured
GPQA Diamond (Artificial Analysis run)85.7%58.7%Gemma 4 31B
Humanity's Last Exam (Artificial Analysis run)23.6%3.8%Gemma 4 31B
GPQA Diamond (Epoch AI run)75.8%51.8%Gemma 4 31B
ARC-AGINot measured0.5%Only Llama 4 Scout measured
ARC-AGI-2Not measured0.0%Only Llama 4 Scout measured
LMArena Text: hard prompts14481266Gemma 4 31B
LMArena Text: expert14641235Gemma 4 31B
LMArena Text: hard prompts in English14561293Gemma 4 31B
LMArena Vision: diagrams12831125Gemma 4 31B
LMArena Vision: homework13101148Gemma 4 31B
Kagi LLM Benchmark63.5%36.9%Gemma 4 31B
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 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 IndexNot measured14.0Only Llama 4 Scout measured
AIME 2025 (Artificial Analysis run)Not measured14.0%Only Llama 4 Scout measured
OTIS Mock AIME73.3%7.8%Gemma 4 31B
MATH level 5Not measured62.3%Only Llama 4 Scout measured
LMArena Text: math14631287Gemma 4 31B
LMArena Text: mathematical work14651286Gemma 4 31B
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 4 ScoutLeader
MMLU ProNot measured69.6%Only Llama 4 Scout measured
LegalBench (Vals AI)Not measured72.0%Only Llama 4 Scout measured
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B 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)61.4%57.8%Gemma 4 31B
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)Not measured75.2%Only Llama 4 Scout measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571278Gemma 4 31B
LMArena Text: medicine and healthcare14511275Gemma 4 31B
LMArena Text: legal and government14381285Gemma 4 31B
LMArena Text: business and finance14301257Gemma 4 31B
FACTS Benchmark Suite45.3%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 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
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index250
General benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 4 ScoutLeader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%34.8%Gemma 4 31B
MedScribe (Vals AI)Not measured50.6%Only Llama 4 Scout measured
IFBench75.6%39.5%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%27.7%Gemma 4 31B
DTBench82.7%57.9%Gemma 4 31B
LMCA39.3%12.0%Gemma 4 31B
Fiction.LiveBenchNot measured36.0%Only Llama 4 Scout measured
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431279Gemma 4 31B
LMArena Text: instruction following14331248Gemma 4 31B
LMArena Text: creative writing14171249Gemma 4 31B
LMArena Vision12761118Gemma 4 31B
LMArena Text: English14511304Gemma 4 31B
LMArena Text: non-English14301252Gemma 4 31B
LMArena Text: Chinese14751255Gemma 4 31B
LMArena Text: GermanNot measured1273Only Llama 4 Scout measured
LMArena Text: JapaneseNot measured1206Only Llama 4 Scout measured
LMArena Text: KoreanNot measured1207Only Llama 4 Scout measured
LMArena Text: French14361283Gemma 4 31B
LMArena Text: Spanish14421278Gemma 4 31B
LMArena Text: Russian14601263Gemma 4 31B
LMArena Text: Polish14331265Gemma 4 31B
LMArena Text: multi-turn14521280Gemma 4 31B
LMArena Text: longer queries14461265Gemma 4 31B
LMArena Text: writing and language14321269Gemma 4 31B
LMArena Text: entertainment and media14051242Gemma 4 31B
LMArena Vision: English12711143Gemma 4 31B
LMArena Vision: Chinese13261106Gemma 4 31B
LMArena Vision: reading text12821117Gemma 4 31B
LMArena Vision: humor12801102Gemma 4 31B
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things1226Not measuredOnly Gemma 4 31B measured
LMArena Vision: creative writing12851126Gemma 4 31B
LMArena Document1425Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 4 31B and Llama 4 Scout
BenchmarkGemma 4 31BLlama 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 4 31B$0.0003Fits in one request
Llama 4 Scout$0.0004Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.0082Fits in one request
Llama 4 Scout$0.010Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.032Fits in one request
Llama 4 Scout$0.040Fits in one request

Gemma 4 31B 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 4 31B and Llama 4 Scout
SpecificationGoogle Gemma 4 31BMeta Llama 4 Scout
MakerGoogleMeta Llama
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026April 5, 2025
Context window262K1.31M
Input $/Mtok$0.14$0.175
Output $/Mtok$0.40$0.50
Coding index39.0Not benchmarked
Independent measurements behind it20
Cost per solved taskNot computable$1.276
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than Llama 4 Scout for coding?

Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; Llama 4 Scout has none, so the two cannot be ranked on coding. Pick Llama 4 Scout for a larger context window (1.31M against 262K tokens).

Which is cheaper, Gemma 4 31B or Llama 4 Scout?

Gemma 4 31B costs $0.14 per million input tokens and $0.40 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 4 31B or Llama 4 Scout?

Llama 4 Scout, with 1.31M tokens against 262K.

How many benchmarks is the Gemma 4 31B vs Llama 4 Scout comparison based on?

51 benchmarks have a result for both models as of October 22, 2026. Gemma 4 31B's coding index rests on 2 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