Noometry

Model comparison

Gemma 3 27B vs Granite 4.2 8B

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 30.8 on the Noometry Index.

Last verified . 11 shared benchmarks.

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Gemma 3 27B scores higher in 3 categories and Granite 4.2 8B in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Granite 4.2 8B leads 40.5 to 22.5.
  • Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.06 / $0.25 for Granite 4.2 8B.

Side by side

Gemma 3 27BGranite 4.2 8B
ProviderGoogleIBM
Noometry Index30.840.5
Released2025-03-11—
WeightsOpenOpen
Context window131K131K
Max output8K118K
Input $ / M tokens$0.08$0.06
Output $ / M tokens$0.16$0.25
Results tracked4311

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Granite 4.2 8B leads

Gemma 3 27B: 22.5 (#334), Granite 4.2 8B: 40.5 (#137)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Coding13221380
Aider Polyglot4.9%—
SciCode21.2%—
LiveBench Coding39.9%—

Agentic & Tool Use Not comparable

Gemma 3 27B: 25.1 (#110), Granite 4.2 8B: —

BenchmarkGemma 3 27BGranite 4.2 8B
Berkeley Function Calling Leaderboard29.5%—

Reasoning Granite 4.2 8B leads

Gemma 3 27B: 16.7 (#301), Granite 4.2 8B: 26.6 (#131)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Hard Prompts13401329
Kagi LLM Benchmark40.4%—
CritPt0%—
Chess Puzzles0%—
LiveBench Reasoning43.8%—
DTBench52.5%—
LiveBench Data Analysis51.5%—
LMCA12.3%—
Epoch Capabilities Index130.04—
LiveBench50%—

Math Not comparable

Gemma 3 27B: 25.9 (#265), Granite 4.2 8B: —

BenchmarkGemma 3 27BGranite 4.2 8B
OTIS Mock AIME 2024-202522.5%—
LiveBench Math55.4%—
LMArena Math1312—
MATH Level 574%—

Knowledge Granite 4.2 8B leads

Gemma 3 27B: 25.5 (#261), Granite 4.2 8B: 38.4 (#145)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Expert13041384
GPQA Diamond47.7%—
Confabulations40.3%—
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 3 27B: 32.6 (#100), Granite 4.2 8B: —

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Vision1164—
GeoBench52%—

Multilingual Gemma 3 27B leads

Gemma 3 27B: 46.9 (#155), Granite 4.2 8B: 44.5 (#178)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Non-English13341302
LMArena Chinese13461366
LMArena Russian13491285
LMArena French1368—
LMArena German1362—
LMArena Japanese1287—
LMArena Korean1308—
LMArena Spanish1349—

Instruction Following Gemma 3 27B leads

Gemma 3 27B: 70.6 (#160), Granite 4.2 8B: 68.7 (#184)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Instruction Following13211301
LiveBench Instruction Following74.9%—

Long Context Granite 4.2 8B leads

Gemma 3 27B: 27.6 (#293), Granite 4.2 8B: 40.3 (#159)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Longer Query13331324
Fiction.LiveBench33.3%—

Writing & Preference Gemma 3 27B leads

Gemma 3 27B: 52.5 (#168), Granite 4.2 8B: 49.6 (#189)

BenchmarkGemma 3 27BGranite 4.2 8B
LMArena Text13581320
LMArena Creative Writing13461236
LMArena Multi-Turn13451301
Short-Story Creative Writing79.9%—
EQ-Bench Creative Writing1266—
LiveBench Language34.6%—

Frequently asked questions

Is Gemma 3 27B better than Granite 4.2 8B?

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 30.8 on the Noometry Index.

Which is cheaper, Gemma 3 27B or Granite 4.2 8B?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Granite 4.2 8B lists at $0.06 and $0.25.

Is Gemma 3 27B or Granite 4.2 8B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 22.5 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 27B and Granite 4.2 8B share?

11 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Granite 4.2 8B has 11.

Related comparisons

Go deeper