Enter opens the highlighted result. Esc closes.

Gemma 3 4B vs Gemma 4 26B A4B

Gemma 4 26B A4B leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 16.7 to 4.8, and Gemma 3 4B costs 8.0x less per output token ($0.075 vs $0.60 per million). Updated October 21, 2026; 34 benchmarks have a result for both.

Replace Gemma 3 4B Replace Gemma 4 26B A4B
Gemma 3 4BGoogle
Coding
No data
Overall
22.6
Output $/M
$0.075
0
Gemma 4 26B A4BGoogle
Coding
No data
Overall
54.7
Output $/M
$0.60
34
vs boards won of 34 shared

Gemma 3 4B or Gemma 4 26B A4B: which to pick

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

Pick Gemma 3 4B for output tokens 8.0x cheaper ($0.075 vs $0.60 per million) and work measured by AA Coding Index or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AGemma 3 4BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGemma 4 26B A4BGoogleNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
34
Gemma 3 4B only
8
Gemma 4 26B A4B only
21
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 4B not benchmarked, Gemma 4 26B A4B not benchmarked.
Widest category
Math, 49.9 points apart on average over 3 shared benchmarks.
Widest single gap
OTIS Mock AIME: Gemma 3 4B 7.5% against Gemma 4 26B A4B 82.2%, 74.7 points apart on a 0 to 100 scale.
Output price
Gemma 3 4B $0.075 against Gemma 4 26B A4B $0.60 per million output tokens, 8.0x apart.
Context window
Gemma 3 4B takes 131K tokens, Gemma 4 26B A4B 262K.

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 4BBarsGemma 4 26B A4BTies
Coding04
Intelligence02
Agentic work01
Reasoning06
Math03
Knowledge04
General014
All shared boards034
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
LMArena WebDevNot measured1360Only Gemma 4 26B A4B measured
AA Coding Index2.739.3Gemma 4 26B A4B
LiveCodeBench (Artificial Analysis run)11.2%Not measuredOnly Gemma 3 4B measured
SciCodeNot measured40.0%Only Gemma 4 26B A4B measured
Terminal-Bench Hard (Artificial Analysis run)0.8%25.0%Gemma 4 26B A4B
WeirdMLNot measured35.2%Only Gemma 4 26B A4B measured
ALE-BenchNot measured927.2Only Gemma 4 26B A4B measured
LMArena Text: coding12301446Gemma 4 26B A4B
LMArena Text: software and IT12691454Gemma 4 26B A4B
LMArena WebDev: ReactNot measured1351Only Gemma 4 26B A4B measured
LMArena WebDev: HTMLNot measured1362Only Gemma 4 26B A4B measured
SciCode0.0%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
AA Intelligence Index4.816.7Gemma 4 26B A4B
Epoch Capabilities Index115.9141.9Gemma 4 26B A4B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
AA Agentic IndexNot measured2.9Only Gemma 4 26B A4B measured
τ²-Bench Telecom5.0%43.6%Gemma 4 26B A4B
Berkeley Function Calling Leaderboard (BFCL)19.6%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
GPQA Diamond (Artificial Analysis run)29.1%79.2%Gemma 4 26B A4B
Humanity's Last Exam (Artificial Analysis run)5.3%19.3%Gemma 4 26B A4B
GPQA Diamond (Epoch AI run)23.2%73.2%Gemma 4 26B A4B
LMArena Text: hard prompts12531438Gemma 4 26B A4B
LMArena Text: expert12231447Gemma 4 26B A4B
LMArena Text: hard prompts in English12531448Gemma 4 26B A4B
LMArena Vision: diagramsNot measured1264Only Gemma 4 26B A4B measured
LMArena Vision: homeworkNot measured1293Only Gemma 4 26B A4B measured
Kagi LLM Benchmark25.2%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
AA Math Index12.7Not measuredOnly Gemma 3 4B measured
AIME 2025 (Artificial Analysis run)12.7%Not measuredOnly Gemma 3 4B measured
OTIS Mock AIME7.5%82.2%Gemma 4 26B A4B
LMArena Text: math12391470Gemma 4 26B A4B
LMArena Text: mathematical work12561475Gemma 4 26B A4B
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
MMLU Pro (Artificial Analysis run)41.7%Not measuredOnly Gemma 3 4B measured
LMArena Text: science13061446Gemma 4 26B A4B
LMArena Text: medicine and healthcare13421428Gemma 4 26B A4B
LMArena Text: legal and government13271457Gemma 4 26B A4B
LMArena Text: business and finance13111429Gemma 4 26B A4B
FACTS Benchmark SuiteNot measured42.7%Only Gemma 4 26B A4B measured
Neither model has a result on the other 12 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index014
General benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
IFBench28.3%72.4%Gemma 4 26B A4B
Long context reasoning (AA-LCR)6.7%65.7%Gemma 4 26B A4B
DTBench50.9%74.9%Gemma 4 26B A4B
LMCA2.8%29.7%Gemma 4 26B A4B
LMArena Text12911434Gemma 4 26B A4B
LMArena Text: instruction following12391420Gemma 4 26B A4B
LMArena Text: creative writing12701400Gemma 4 26B A4B
LMArena VisionNot measured1260Only Gemma 4 26B A4B measured
LMArena Text: English13001444Gemma 4 26B A4B
LMArena Text: non-English12731421Gemma 4 26B A4B
LMArena Text: ChineseNot measured1495Only Gemma 4 26B A4B measured
LMArena Text: German1281Not measuredOnly Gemma 3 4B measured
LMArena Text: FrenchNot measured1460Only Gemma 4 26B A4B measured
LMArena Text: SpanishNot measured1415Only Gemma 4 26B A4B measured
LMArena Text: Russian12941434Gemma 4 26B A4B
LMArena Text: multi-turn12551441Gemma 4 26B A4B
LMArena Text: longer queries12731427Gemma 4 26B A4B
LMArena Text: writing and language12881405Gemma 4 26B A4B
LMArena Text: entertainment and media12331403Gemma 4 26B A4B
LMArena Vision: EnglishNot measured1256Only Gemma 4 26B A4B measured
LMArena Vision: ChineseNot measured1312Only Gemma 4 26B A4B measured
LMArena Vision: reading textNot measured1268Only Gemma 4 26B A4B measured
LMArena Vision: humorNot measured1272Only Gemma 4 26B A4B measured
LMArena Vision: captioningNot measured1297Only Gemma 4 26B A4B measured
LMArena Vision: recognizing thingsNot measured1191Only Gemma 4 26B A4B measured
LMArena Vision: creative writingNot measured1256Only Gemma 4 26B A4B measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 3 4B and Gemma 4 26B A4B
BenchmarkGemma 3 4BGemma 4 26B A4BLeader
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 4B$0.0001Fits in one request
Gemma 4 26B A4B$0.0004Fits in one request

Gemma 3 4B costs less

Repository review

50K input + 3K output tokens

Gemma 3 4B$0.0025Fits in one request
Gemma 4 26B A4B$0.0093Fits in one request

Gemma 3 4B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 4B$0.0097Exceeds the context window
Gemma 4 26B A4B$0.036Fits in one request

Gemma 3 4B 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 4B and Gemma 4 26B A4B
SpecificationGoogle Gemma 3 4BGoogle Gemma 4 26B A4B
MakerGoogleGoogle
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025April 3, 2026
Context window131K262K
Input $/Mtok$0.045$0.15
Output $/Mtok$0.075$0.60
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 4B better than Gemma 4 26B A4B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 4B for output tokens 8.0x cheaper ($0.075 vs $0.60 per million) and work measured by AA Coding Index or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Gemma 3 4B or Gemma 4 26B A4B?

Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; Gemma 4 26B A4B costs $0.15 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 3 4B or Gemma 4 26B A4B?

Gemma 4 26B A4B, with 262K tokens against 131K.

How many benchmarks is the Gemma 3 4B vs Gemma 4 26B A4B comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. Gemma 3 4B's coding index rests on 0 independent benchmarks and Gemma 4 26B A4B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next