Enter opens the highlighted result. Esc closes.

Gemma 3 4B vs Granite 4.2 8B

Granite 4.2 8B leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 11.1 to 4.8, and Gemma 3 4B costs 2.7x less per output token ($0.075 vs $0.20 per million). Updated October 22, 2026; 24 benchmarks have a result for both.

Replace Gemma 3 4B Replace Granite 4.2 8B
Gemma 3 4BGoogle
Coding
No data
Overall
22.6
Output $/M
$0.075
5
Granite 4.2 8BIBM Granite
Coding
No data
Overall
No data
Output $/M
$0.20
19
vs boards won of 24 shared

Gemma 3 4B or Granite 4.2 8B: 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 2.7x cheaper ($0.075 vs $0.20 per million) and work measured by AA Coding Index or LMArena Text: coding, where it leads.

Model AGemma 3 4BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGranite 4.2 8BIBM GraniteNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
24
Gemma 3 4B only
18
Granite 4.2 8B only
3
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 4B not benchmarked, Granite 4.2 8B not benchmarked.
Widest category
Coding, 20.3 points apart on average over 3 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): Gemma 3 4B 6.7% against Granite 4.2 8B 45.0%, 38.3 points apart on a 0 to 100 scale.
Output price
Gemma 3 4B $0.075 against Granite 4.2 8B $0.20 per million output tokens, 2.7x apart.
Context window
Both take 131K tokens.

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 4BBarsGranite 4.2 8BTies
Coding03
Intelligence01
Reasoning05
Knowledge22
General38
All shared boards519
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
AA Coding Index2.722.4Granite 4.2 8B
LiveCodeBench (Artificial Analysis run)11.2%Not measuredOnly Gemma 3 4B measured
SciCodeNot measured31.5%Only Granite 4.2 8B measured
Terminal-Bench Hard (Artificial Analysis run)0.8%Not measuredOnly Gemma 3 4B measured
LMArena Text: coding12301378Granite 4.2 8B
LMArena Text: software and IT12691367Granite 4.2 8B
SciCode0.0%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
AA Intelligence Index4.811.1Granite 4.2 8B
Epoch Capabilities Index115.9Not measuredOnly Gemma 3 4B measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
AA Agentic IndexNot measured1.3Only Granite 4.2 8B measured
τ²-Bench Telecom5.0%Not measuredOnly Gemma 3 4B measured
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 index05
Reasoning benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
GPQA Diamond (Artificial Analysis run)29.1%63.1%Granite 4.2 8B
Humanity's Last Exam (Artificial Analysis run)5.3%9.7%Granite 4.2 8B
GPQA Diamond (Epoch AI run)23.2%Not measuredOnly Gemma 3 4B measured
LMArena Text: hard prompts12531327Granite 4.2 8B
LMArena Text: expert12231386Granite 4.2 8B
LMArena Text: hard prompts in English12531345Granite 4.2 8B
Kagi LLM Benchmark25.2%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 15 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Math benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
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%Not measuredOnly Gemma 3 4B measured
LMArena Text: math1239Not measuredOnly Gemma 3 4B measured
LMArena Text: mathematical work1256Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
Knowledge benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
MMLU Pro (Artificial Analysis run)41.7%Not measuredOnly Gemma 3 4B measured
LMArena Text: science13061336Granite 4.2 8B
LMArena Text: medicine and healthcare13421336Gemma 3 4B
LMArena Text: legal and government13271327Gemma 3 4B
LMArena Text: business and finance13111322Granite 4.2 8B
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 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index38
General benchmarks for Gemma 3 4B and Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
IFBench28.3%Not measuredOnly Gemma 3 4B measured
Long context reasoning (AA-LCR)6.7%45.0%Granite 4.2 8B
DTBench50.9%Not measuredOnly Gemma 3 4B measured
LMCA2.8%Not measuredOnly Gemma 3 4B measured
LMArena Text12911319Granite 4.2 8B
LMArena Text: instruction following12391300Granite 4.2 8B
LMArena Text: creative writing12701236Gemma 3 4B
LMArena Text: English13001337Granite 4.2 8B
LMArena Text: non-English12731301Granite 4.2 8B
LMArena Text: ChineseNot measured1367Only Granite 4.2 8B measured
LMArena Text: German1281Not measuredOnly Gemma 3 4B measured
LMArena Text: Russian12941282Gemma 3 4B
LMArena Text: multi-turn12551301Granite 4.2 8B
LMArena Text: longer queries12731325Granite 4.2 8B
LMArena Text: writing and language12881269Gemma 3 4B
LMArena Text: entertainment and media12331271Granite 4.2 8B
Neither model has a result on the other 30 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 Granite 4.2 8B
BenchmarkGemma 3 4BGranite 4.2 8BLeader
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
Granite 4.2 8B$0.0002Fits in one request

Gemma 3 4B costs less

Repository review

50K input + 3K output tokens

Gemma 3 4B$0.0025Fits in one request
Granite 4.2 8B$0.0046Fits in one request

Gemma 3 4B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 4B$0.0097Exceeds the context window
Granite 4.2 8B$0.018Exceeds the context window

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 Granite 4.2 8B
SpecificationGoogle Gemma 3 4BIBM Granite 4.2 8B
MakerGoogleIBM Granite
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025August 31, 2026
Context window131K131K
Input $/Mtok$0.045$0.08
Output $/Mtok$0.075$0.20
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 4B better than Granite 4.2 8B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 4B for output tokens 2.7x cheaper ($0.075 vs $0.20 per million) and work measured by AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, Gemma 3 4B or Granite 4.2 8B?

Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; Granite 4.2 8B costs $0.08 and $0.20. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 3 4B or Granite 4.2 8B?

Neither: both take 131K tokens.

How many benchmarks is the Gemma 3 4B vs Granite 4.2 8B comparison based on?

24 benchmarks have a result for both models as of October 22, 2026. Gemma 3 4B's coding index rests on 0 independent benchmarks and Granite 4.2 8B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next