Model comparison

Gemma 4 26B A4B IT vs Granite 4.2 8B

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 40.5 on the Noometry Index.

Last verified . 11 shared benchmarks.

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 5 categories and Granite 4.2 8B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 4 26B A4B IT leads 58.6 to 49.6.
  • Both cost about the same: $0.0675 input and $0.23 output per million tokens.
  • Gemma 4 26B A4B IT accepts more context: 262K tokens versus 131K.

Side by side

Gemma 4 26B A4B IT and Granite 4.2 8B specifications
Gemma 4 26B A4B ITGranite 4.2 8B
ProviderGoogleIBM
Noometry Index43.540.5
Released2026-04-02—
WeightsOpenOpen
Context window262K131K
Max output33K118K
Input $ / M tokens$0.0675$0.06
Output $ / M tokens$0.23$0.25
Results tracked2811

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

Category by category

Coding Granite 4.2 8B leads

Gemma 4 26B A4B IT: 39.0 (#164), Granite 4.2 8B: 40.5 (#137)

Coding benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Coding14471380
LMArena WebDev1359—
SciCode40%—
WeirdML35.2%—
ALE-Bench927.17—

Reasoning Granite 4.2 8B leads

Gemma 4 26B A4B IT: 21.8 (#213), Granite 4.2 8B: 26.6 (#131)

Reasoning benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Hard Prompts14391329
CritPt0%—
Chess Puzzles6%—
DTBench74.9%—
LMCA29.7%—
Epoch Capabilities Index141.85—

Math Not comparable

Gemma 4 26B A4B IT: 47.6 (#67), Granite 4.2 8B: —

Math benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
OTIS Mock AIME 2024-202582.2%—
LMArena Math1470—

Knowledge Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 45.7 (#85), Granite 4.2 8B: 38.4 (#145)

Knowledge benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Expert14471384
GPQA Diamond73.2%—
Vectara Hallucination Rate5.2%—

Multimodal Not comparable

Gemma 4 26B A4B IT: 40.6 (#46), Granite 4.2 8B: —

Multimodal benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Vision1260—

Multilingual Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 53.1 (#71), Granite 4.2 8B: 44.5 (#178)

Multilingual benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Non-English14211302
LMArena Chinese14951366
LMArena Russian14341285
LMArena French1460—
LMArena Spanish1417—

Instruction Following Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 74.8 (#82), Granite 4.2 8B: 68.7 (#184)

Instruction Following benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Instruction Following14201301

Long Context Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 43.6 (#91), Granite 4.2 8B: 40.3 (#159)

Long Context benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Longer Query14281324

Writing & Preference Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 58.6 (#115), Granite 4.2 8B: 49.6 (#189)

Writing & Preference benchmarks
BenchmarkGemma 4 26B A4B ITGranite 4.2 8B
LMArena Text14341320
LMArena Creative Writing14021236
LMArena Multi-Turn14411301
EQ-Bench Creative Writing1305—

Frequently asked questions

Is Gemma 4 26B A4B IT better than Granite 4.2 8B?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 40.5 on the Noometry Index.

Which is cheaper, Gemma 4 26B A4B IT or Granite 4.2 8B?

Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; Granite 4.2 8B lists at $0.06 and $0.25.

Is Gemma 4 26B A4B IT or Granite 4.2 8B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 39.0 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Gemma 4 26B A4B IT and Granite 4.2 8B share?

11 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Granite 4.2 8B has 11.

Related comparisons

Go deeper