Noometry

Model comparison

Gemma 3 27B vs Gemma 7B

Gemma 3 27B and Gemma 7B score almost the same on the Noometry Index (30.8 vs 30.0), so choose on price, context window or the category you care about most.

Last verified . 14 shared benchmarks.

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Gemma 7B Google

30.0

Rank #299 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemma 3 27B scores higher in 3 categories and Gemma 7B in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 27.1.

Side by side

Gemma 3 27BGemma 7B
ProviderGoogleGoogle
Noometry Index30.830.0
Released2025-03-112024-02-21
WeightsOpenOpen
Context window131K—
Max output8K—
Input $ / M tokens$0.08—
Output $ / M tokens$0.16—
Results tracked4327

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

Category by category

Coding Gemma 7B leads

Gemma 3 27B: 22.5 (#334), Gemma 7B: 30.5 (#294)

BenchmarkGemma 3 27BGemma 7B
LMArena Coding13221048
Aider Polyglot4.9%—
SciCode21.2%—
LiveBench Coding39.9%—
HumanEval+—28.7%
MBPP+—43.4%

Agentic & Tool Use Not comparable

Gemma 3 27B: 25.1 (#110), Gemma 7B: —

BenchmarkGemma 3 27BGemma 7B
Berkeley Function Calling Leaderboard29.5%—

Reasoning Gemma 7B leads

Gemma 3 27B: 16.7 (#301), Gemma 7B: 19.9 (#249)

BenchmarkGemma 3 27BGemma 7B
LMArena Hard Prompts13401042
Epoch Capabilities Index130.04111.99
Kagi LLM Benchmark40.4%—
CritPt0%—
Chess Puzzles0%—
LiveBench Reasoning43.8%—
DTBench52.5%—
LiveBench Data Analysis51.5%—
LMCA12.3%—
Adversarial NLI—48.7%
BIG-Bench Hard—55.1%
HellaSwag—82.2%
LiveBench50%—
PIQA—81.2%
WinoGrande—79%

Math Gemma 7B leads

Gemma 3 27B: 25.9 (#265), Gemma 7B: 31.2 (#228)

BenchmarkGemma 3 27BGemma 7B
LMArena Math13121066
OTIS Mock AIME 2024-202522.5%—
LiveBench Math55.4%—
MATH Level 574%—
GSM8K—46.4%

Knowledge Gemma 7B leads

Gemma 3 27B: 25.5 (#261), Gemma 7B: 27.3 (#252)

BenchmarkGemma 3 27BGemma 7B
LMArena Expert13041001
GPQA Diamond47.7%—
Confabulations40.3%—
Vectara Hallucination Rate7.4%—
ARC (AI2) Challenge—78.3%
BoolQ—83.2%
MMLU—66.1%
OpenBookQA—78.6%
TriviaQA—72.3%

Multimodal Not comparable

Gemma 3 27B: 32.6 (#100), Gemma 7B: —

BenchmarkGemma 3 27BGemma 7B
LMArena Vision1164—
GeoBench52%—

Multilingual Gemma 3 27B leads

Gemma 3 27B: 46.9 (#155), Gemma 7B: 25.1 (#287)

BenchmarkGemma 3 27BGemma 7B
LMArena Non-English1334999
LMArena Chinese13461035
LMArena French13681025
LMArena Russian1349993
LMArena German1362—
LMArena Japanese1287—
LMArena Korean1308—
LMArena Spanish1349—

Instruction Following Gemma 3 27B leads

Gemma 3 27B: 70.6 (#160), Gemma 7B: 51.5 (#295)

BenchmarkGemma 3 27BGemma 7B
LMArena Instruction Following13211017
LiveBench Instruction Following74.9%—

Long Context Gemma 7B leads

Gemma 3 27B: 27.6 (#293), Gemma 7B: 31.1 (#282)

BenchmarkGemma 3 27BGemma 7B
LMArena Longer Query13331022
Fiction.LiveBench33.3%—

Writing & Preference Gemma 3 27B leads

Gemma 3 27B: 52.5 (#168), Gemma 7B: 27.1 (#302)

BenchmarkGemma 3 27BGemma 7B
LMArena Text13581056
LMArena Creative Writing13461024
LMArena Multi-Turn1345963
Short-Story Creative Writing79.9%—
EQ-Bench Creative Writing1266—
LiveBench Language34.6%—

Frequently asked questions

Is Gemma 3 27B better than Gemma 7B?

Gemma 3 27B and Gemma 7B score almost the same on the Noometry Index (30.8 vs 30.0), so choose on price, context window or the category you care about most.

Is Gemma 3 27B or Gemma 7B better for coding?

Gemma 7B scores higher on coding benchmarks: 30.5 versus 22.5 in the Noometry coding category.

How many benchmarks do Gemma 3 27B and Gemma 7B share?

14 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Gemma 7B has 27.

Related comparisons

Go deeper