Noometry

Model comparison

Gemma 2 9B vs Gemma 3 27B

Gemma 3 27B is the stronger model overall, scoring 30.5 to 25.7 on the Noometry Index.

Last verified . 29 shared benchmarks.

Gemma 2 9B Google

25.7

Rank #334 Confirmed

Gemma 3 27B Google

30.5

Rank #277 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Gemma 2 9B scores higher in 2 categories and Gemma 3 27B in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 3 27B leads 52.7 to 32.3.
  • The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 74% for Gemma 3 27B.

Side by side

Gemma 2 9BGemma 3 27B
ProviderGoogleGoogle
Noometry Index25.730.5
Released2024-06-242025-03-11
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.08
Output $ / M tokens—$0.16
Results tracked3543

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

Category by category

Coding Gemma 2 9B leads

Gemma 2 9B: 29.0 (#299), Gemma 3 27B: 22.1 (#329)

BenchmarkGemma 2 9BGemma 3 27B
LiveBench Coding22.5%39.9%
LMArena Coding11741322
Aider Polyglot—4.9%
SciCode—21.2%
BigCodeBench Instruct34.7%—
BigCodeBench Complete40.6%—

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Gemma 3 27B: 24.9 (#105)

BenchmarkGemma 2 9BGemma 3 27B
Berkeley Function Calling Leaderboard—29.5%

Reasoning Too close to call

Gemma 2 9B: 15.3 (#306), Gemma 3 27B: 16.3 (#297)

BenchmarkGemma 2 9BGemma 3 27B
LiveBench Reasoning15.2%43.8%
LMArena Hard Prompts11721340
LiveBench Data Analysis36.4%51.5%
Epoch Capabilities Index119.78130.04
LiveBench28.7%50%
Kagi LLM Benchmark—40.4%
CritPt—0%
Chess Puzzles—0%
DTBench—52.5%
LMCA—12.3%
PIQA83.7%—

Math Gemma 3 27B leads

Gemma 2 9B: 9.3 (#312), Gemma 3 27B: 24.4 (#261)

BenchmarkGemma 2 9BGemma 3 27B
OTIS Mock AIME 2024-20250.6%22.5%
LiveBench Math19.8%55.4%
LMArena Math11831312
MATH Level 521%74%
GSM8K84.9%—

Knowledge Gemma 3 27B leads

Gemma 2 9B: 9.7 (#300), Gemma 3 27B: 25.4 (#256)

BenchmarkGemma 2 9BGemma 3 27B
GPQA Diamond27.5%47.7%
LMArena Expert11471303
Confabulations—40.3%
Vectara Hallucination Rate—7.4%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, Gemma 3 27B: 32.0 (#94)

BenchmarkGemma 2 9BGemma 3 27B
LMArena Vision—1165
GeoBench—52%

Multilingual Gemma 3 27B leads

Gemma 2 9B: 36.8 (#233), Gemma 3 27B: 47.0 (#150)

BenchmarkGemma 2 9BGemma 3 27B
LMArena Non-English11881334
LMArena Chinese11851347
LMArena French11891368
LMArena German11861362
LMArena Japanese11441287
LMArena Korean11371308
LMArena Russian12001349
LMArena Spanish12001348

Instruction Following Gemma 3 27B leads

Gemma 2 9B: 57.8 (#264), Gemma 3 27B: 70.8 (#155)

BenchmarkGemma 2 9BGemma 3 27B
LiveBench Instruction Following52.6%74.9%
LMArena Instruction Following11781321

Long Context Gemma 2 9B leads

Gemma 2 9B: 36.3 (#228), Gemma 3 27B: 27.6 (#288)

BenchmarkGemma 2 9BGemma 3 27B
LMArena Longer Query11971333
Fiction.LiveBench—33.3%

Writing & Preference Gemma 3 27B leads

Gemma 2 9B: 32.3 (#276), Gemma 3 27B: 52.7 (#161)

BenchmarkGemma 2 9BGemma 3 27B
LMArena Text12071358
LMArena Creative Writing12061346
EQ-Bench Creative Writing8411266
LMArena Multi-Turn11931344
LiveBench Language25.5%34.6%
Short-Story Creative Writing—79.9%

Frequently asked questions

Is Gemma 2 9B better than Gemma 3 27B?

Gemma 3 27B is the stronger model overall, scoring 30.5 to 25.7 on the Noometry Index.

Is Gemma 2 9B or Gemma 3 27B better for coding?

Gemma 2 9B scores higher on coding benchmarks: 29.0 versus 22.1 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Gemma 3 27B share?

29 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Gemma 3 27B has 43.

Related comparisons

Go deeper