Noometry

Model comparison

Gemma 2 27B vs Granite 4.2 8B

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 29.2 on the Noometry Index.

Last verified . 11 shared benchmarks.

Gemma 2 27B Google

29.2

Rank #302 Confirmed

Granite 4.2 8B IBM

40.0

Rank #143 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Granite 4.2 8B in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Granite 4.2 8B leads 37.7 to 18.9.
  • Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
  • Granite 4.2 8B accepts more context: 131K tokens versus 8K.

Side by side

Gemma 2 27BGranite 4.2 8B
ProviderGoogleIBM
Noometry Index29.240.0
Released2024-06-24—
WeightsOpenOpen
Context window8K131K
Max output2K118K
Input $ / M tokens$0.65$0.06
Output $ / M tokens$0.65$0.25
Results tracked3411

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

Category by category

Coding Granite 4.2 8B leads

Gemma 2 27B: 33.5 (#243), Granite 4.2 8B: 39.9 (#138)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Coding12111379
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—

Reasoning Granite 4.2 8B leads

Gemma 2 27B: 14.8 (#313), Granite 4.2 8B: 25.5 (#130)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Hard Prompts11991327
LiveBench Reasoning28.1%—
DTBench48%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
Epoch Capabilities Index122.06—
LiveBench38.2%—

Math Not comparable

Gemma 2 27B: 10.0 (#306), Granite 4.2 8B: —

BenchmarkGemma 2 27BGranite 4.2 8B
OTIS Mock AIME 2024-20251.4%—
LiveBench Math26.5%—
LMArena Math1212—
MATH Level 527.9%—

Knowledge Granite 4.2 8B leads

Gemma 2 27B: 18.9 (#275), Granite 4.2 8B: 37.7 (#144)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Expert11721380
GPQA Diamond36.5%—
Confabulations27.1%—
MMLU75.7%—

Multilingual Granite 4.2 8B leads

Gemma 2 27B: 38.8 (#221), Granite 4.2 8B: 44.5 (#173)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Non-English12171299
LMArena Chinese12211361
LMArena Russian12341283
LMArena French1246—
LMArena German1209—
LMArena Japanese1175—
LMArena Korean1174—
LMArena Spanish1228—

Instruction Following Granite 4.2 8B leads

Gemma 2 27B: 60.7 (#244), Granite 4.2 8B: 68.7 (#183)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Instruction Following12061298
LiveBench Instruction Following58.1%—

Long Context Granite 4.2 8B leads

Gemma 2 27B: 37.3 (#213), Granite 4.2 8B: 40.2 (#154)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Longer Query12311323

Writing & Preference Granite 4.2 8B leads

Gemma 2 27B: 44.4 (#220), Granite 4.2 8B: 49.8 (#183)

BenchmarkGemma 2 27BGranite 4.2 8B
LMArena Text12311319
LMArena Creative Writing12411238
LMArena Multi-Turn12241299
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than Granite 4.2 8B?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 29.2 on the Noometry Index.

Which is cheaper, Gemma 2 27B or Granite 4.2 8B?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

Is Gemma 2 27B or Granite 4.2 8B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Granite 4.2 8B does, with 131K tokens against 8K.

How many benchmarks do Gemma 2 27B and Granite 4.2 8B share?

11 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Granite 4.2 8B has 11.

Related comparisons

Go deeper