Model comparison

Gemma 2 2b IT vs Gemma 3 27B

Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 30.8 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemma 2 2b IT Google

33.1

Rank #248 Confirmed

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 5 categories and Gemma 3 27B in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 36.5.

Side by side

Gemma 2 2b IT and Gemma 3 27B specifications
Gemma 2 2b ITGemma 3 27B
ProviderGoogleGoogle
Noometry Index33.130.8
Released—2025-03-11
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.08
Output $ / M tokens—$0.16
Results tracked1743

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

Category by category

Coding Gemma 2 2b IT leads

Gemma 2 2b IT: 32.3 (#273), Gemma 3 27B: 22.5 (#334)

Coding benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Coding11121322
Aider Polyglot—4.9%
SciCode—21.2%
LiveBench Coding—39.9%

Agentic & Tool Use Not comparable

Gemma 2 2b IT: —, Gemma 3 27B: 25.1 (#110)

Agentic & Tool Use benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
Berkeley Function Calling Leaderboard—29.5%

Reasoning Gemma 2 2b IT leads

Gemma 2 2b IT: 21.4 (#224), Gemma 3 27B: 16.7 (#301)

Reasoning benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Hard Prompts11131340
Kagi LLM Benchmark—40.4%
CritPt—0%
Chess Puzzles—0%
LiveBench Reasoning—43.8%
DTBench—52.5%
LiveBench Data Analysis—51.5%
LMCA—12.3%
Epoch Capabilities Index—130.04
LiveBench—50%

Math Gemma 2 2b IT leads

Gemma 2 2b IT: 32.6 (#212), Gemma 3 27B: 25.9 (#265)

Math benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Math11351312
OTIS Mock AIME 2024-2025—22.5%
LiveBench Math—55.4%
MATH Level 5—74%

Knowledge Gemma 2 2b IT leads

Gemma 2 2b IT: 29.9 (#231), Gemma 3 27B: 25.5 (#261)

Knowledge benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Expert10961304
GPQA Diamond—47.7%
Confabulations—40.3%
Vectara Hallucination Rate—7.4%

Multimodal Not comparable

Gemma 2 2b IT: —, Gemma 3 27B: 32.6 (#100)

Multimodal benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Vision—1164
GeoBench—52%

Multilingual Gemma 3 27B leads

Gemma 2 2b IT: 32.3 (#257), Gemma 3 27B: 46.9 (#155)

Multilingual benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Non-English11211334
LMArena Chinese11321346
LMArena French11571368
LMArena German11141362
LMArena Japanese10831287
LMArena Korean10551308
LMArena Russian11181349
LMArena Spanish11401349

Instruction Following Gemma 3 27B leads

Gemma 2 2b IT: 57.8 (#263), Gemma 3 27B: 70.6 (#160)

Instruction Following benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Instruction Following11181321
LiveBench Instruction Following—74.9%

Long Context Gemma 2 2b IT leads

Gemma 2 2b IT: 34.3 (#250), Gemma 3 27B: 27.6 (#293)

Long Context benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Longer Query11301333
Fiction.LiveBench—33.3%

Writing & Preference Gemma 3 27B leads

Gemma 2 2b IT: 36.5 (#263), Gemma 3 27B: 52.5 (#168)

Writing & Preference benchmarks
BenchmarkGemma 2 2b ITGemma 3 27B
LMArena Text11561358
LMArena Creative Writing11471346
LMArena Multi-Turn11181345
Short-Story Creative Writing—79.9%
EQ-Bench Creative Writing—1266
LiveBench Language—34.6%

Frequently asked questions

Is Gemma 2 2b IT better than Gemma 3 27B?

Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 30.8 on the Noometry Index.

Is Gemma 2 2b IT or Gemma 3 27B better for coding?

Gemma 2 2b IT scores higher on coding benchmarks: 32.3 versus 22.5 in the Noometry coding category.

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

17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Gemma 3 27B has 43.

Related comparisons

Go deeper