Enter opens the highlighted result. Esc closes.

Gemma 3 12B vs Granite 4.2 8B

Granite 4.2 8B leads Gemma 3 12B on the Artificial Analysis Intelligence Index, 11.1 to 3.8, and Gemma 3 12B costs 1.2x less per output token ($0.1625 vs $0.20 per million). Updated October 22, 2026; 26 benchmarks have a result for both.

Replace Gemma 3 12B Replace Granite 4.2 8B
Gemma 3 12BGoogle
Coding
No data
Overall
28.0
Output $/M
$0.1625
11
Granite 4.2 8BIBM Granite
Coding
No data
Overall
No data
Output $/M
$0.20
15
vs boards won of 26 shared

Gemma 3 12B 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 12B for output tokens 1.2x cheaper ($0.1625 vs $0.20 per million) and work measured by AA Coding Index or SciCode, where it leads.

Model AGemma 3 12BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGranite 4.2 8BIBM GraniteNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
26
Gemma 3 12B only
17
Granite 4.2 8B only
1
Like-for-like categories
6 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, Granite 4.2 8B not benchmarked.
Widest category
Coding, 14.2 points apart on average over 4 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): Gemma 3 12B 8.3% against Granite 4.2 8B 45.0%, 36.7 points apart on a 0 to 100 scale.
Output price
Gemma 3 12B $0.1625 against Granite 4.2 8B $0.20 per million output tokens, 1.2x 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 12BBarsGranite 4.2 8BTies
Coding04
Intelligence01
Agentic work01
Reasoning05
Knowledge31
General83
All shared boards1115
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
AA Coding Index5.822.4Granite 4.2 8B
LiveCodeBench (Artificial Analysis run)13.7%Not measuredOnly Gemma 3 12B measured
SciCode16.4%31.5%Granite 4.2 8B
Terminal-Bench Hard (Artificial Analysis run)0.8%Not measuredOnly Gemma 3 12B measured
LMArena Text: coding12811378Granite 4.2 8B
LMArena Text: software and IT13131367Granite 4.2 8B
SciCode0.0%Not measuredOnly Gemma 3 12B measured
Neither model has a result on the other 36 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
AA Intelligence Index3.811.1Granite 4.2 8B
Epoch Capabilities Index123.5Not measuredOnly Gemma 3 12B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
AA Agentic Index0.11.3Granite 4.2 8B
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 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
GPQA Diamond (Artificial Analysis run)34.9%63.1%Granite 4.2 8B
Humanity's Last Exam (Artificial Analysis run)4.2%9.7%Granite 4.2 8B
GPQA Diamond (Epoch AI run)39.5%Not measuredOnly Gemma 3 12B measured
LMArena Text: hard prompts13091327Granite 4.2 8B
LMArena Text: expert12481386Granite 4.2 8B
LMArena Text: hard prompts in English13181345Granite 4.2 8B
Neither model has a result on the other 17 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Math benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
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: math1307Not measuredOnly Gemma 3 12B measured
LMArena Text: mathematical work1336Not measuredOnly Gemma 3 12B measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
Knowledge benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
MMLU Pro (Artificial Analysis run)59.5%Not measuredOnly Gemma 3 12B measured
LMArena Text: science13661336Gemma 3 12B
LMArena Text: medicine and healthcare13341336Granite 4.2 8B
LMArena Text: legal and government13811327Gemma 3 12B
LMArena Text: business and finance13761322Gemma 3 12B
Neither model has a result on the other 15 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 Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index83
General benchmarks for Gemma 3 12B and Granite 4.2 8B
BenchmarkGemma 3 12BGranite 4.2 8BLeader
IFBench36.7%Not measuredOnly Gemma 3 12B measured
Long context reasoning (AA-LCR)8.3%45.0%Granite 4.2 8B
DTBench48.8%Not measuredOnly Gemma 3 12B measured
LMCA4.5%Not measuredOnly Gemma 3 12B measured
LMArena Text13341319Gemma 3 12B
LMArena Text: instruction following12991300Granite 4.2 8B
LMArena Text: creative writing13311236Gemma 3 12B
LMArena Text: English13491337Gemma 3 12B
LMArena Text: non-English13181301Gemma 3 12B
LMArena Text: ChineseNot measured1367Only Granite 4.2 8B measured
LMArena Text: German1370Not measuredOnly Gemma 3 12B measured
LMArena Text: Russian13351282Gemma 3 12B
LMArena Text: multi-turn13341301Gemma 3 12B
LMArena Text: longer queries13171325Granite 4.2 8B
LMArena Text: writing and language13071269Gemma 3 12B
LMArena Text: entertainment and media12971271Gemma 3 12B
Neither model has a result on the other 32 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 Granite 4.2 8B
BenchmarkGemma 3 12BGranite 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 12B$0.0002Fits in one request
Granite 4.2 8B$0.0002Fits in one request

Gemma 3 12B costs less

Repository review

50K input + 3K output tokens

Gemma 3 12B$0.0042Fits in one request
Granite 4.2 8B$0.0046Fits in one request

Gemma 3 12B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 12B$0.017Exceeds the context window
Granite 4.2 8B$0.018Exceeds 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 Granite 4.2 8B
SpecificationGoogle Gemma 3 12BIBM Granite 4.2 8B
MakerGoogleIBM Granite
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025August 31, 2026
Context window131K131K
Input $/Mtok$0.075$0.08
Output $/Mtok$0.1625$0.20
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 12B 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 12B for output tokens 1.2x cheaper ($0.1625 vs $0.20 per million) and work measured by AA Coding Index or SciCode, where it leads.

Which is cheaper, Gemma 3 12B or Granite 4.2 8B?

Gemma 3 12B costs $0.075 per million input tokens and $0.1625 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 12B or Granite 4.2 8B?

Neither: both take 131K tokens.

How many benchmarks is the Gemma 3 12B vs Granite 4.2 8B comparison based on?

26 benchmarks have a result for both models as of October 22, 2026. Gemma 3 12B'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