Noometry

Model comparison

Gemma 3 27B vs Ministral 3B

Gemma 3 27B is the stronger model overall, scoring 30.8 to 26.2 on the Noometry Index.

Last verified . 6 shared benchmarks.

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Ministral 3B Mistral AI

26.2

Rank #338 Confirmed

Summary

  • They share 6 benchmarks with published results for both. Gemma 3 27B scores higher in 1 category and Ministral 3B in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemma 3 27B leads 25.5 to 10.4.
  • The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 14.4% for Ministral 3B.
  • Both cost about the same: $0.08 input and $0.16 output per million tokens.

Side by side

Gemma 3 27BMinistral 3B
ProviderGoogleMistral AI
Noometry Index30.826.2
Released2025-03-112024-10-01
WeightsOpenOpen
Context window131K131K
Max output8K262K
Input $ / M tokens$0.08$0.10
Output $ / M tokens$0.16$0.10
Results tracked436

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

Category by category

Coding Not comparable

Gemma 3 27B: 22.5 (#334), Ministral 3B: —

BenchmarkGemma 3 27BMinistral 3B
Aider Polyglot4.9%—
SciCode21.2%—
LiveBench Coding39.9%—
LMArena Coding1322—

Agentic & Tool Use Not comparable

Gemma 3 27B: 25.1 (#110), Ministral 3B: —

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

Reasoning Ministral 3B leads

Gemma 3 27B: 16.7 (#301), Ministral 3B: 18.4 (#282)

BenchmarkGemma 3 27BMinistral 3B
DTBench52.5%51.7%
LMCA12.3%5.5%
Epoch Capabilities Index130.04118.1
Kagi LLM Benchmark40.4%—
CritPt0%—
Chess Puzzles0%—
LiveBench Reasoning43.8%—
LMArena Hard Prompts1340—
LiveBench Data Analysis51.5%—
LiveBench50%—

Math Too close to call

Gemma 3 27B: 25.9 (#265), Ministral 3B: 26.6 (#258)

BenchmarkGemma 3 27BMinistral 3B
MATH Level 574%14.4%
OTIS Mock AIME 2024-202522.5%—
LiveBench Math55.4%—
LMArena Math1312—

Knowledge Gemma 3 27B leads

Gemma 3 27B: 25.5 (#261), Ministral 3B: 10.4 (#302)

BenchmarkGemma 3 27BMinistral 3B
GPQA Diamond47.7%25.3%
Vectara Hallucination Rate7.4%7.3%
Confabulations40.3%—
LMArena Expert1304—

Multimodal Not comparable

Gemma 3 27B: 32.6 (#100), Ministral 3B: —

BenchmarkGemma 3 27BMinistral 3B
LMArena Vision1164—
GeoBench52%—

Multilingual Not comparable

Gemma 3 27B: 46.9 (#155), Ministral 3B: —

BenchmarkGemma 3 27BMinistral 3B
LMArena Non-English1334—
LMArena Chinese1346—
LMArena French1368—
LMArena German1362—
LMArena Japanese1287—
LMArena Korean1308—
LMArena Russian1349—
LMArena Spanish1349—

Instruction Following Not comparable

Gemma 3 27B: 70.6 (#160), Ministral 3B: —

BenchmarkGemma 3 27BMinistral 3B
LiveBench Instruction Following74.9%—
LMArena Instruction Following1321—

Long Context Not comparable

Gemma 3 27B: 27.6 (#293), Ministral 3B: —

BenchmarkGemma 3 27BMinistral 3B
Fiction.LiveBench33.3%—
LMArena Longer Query1333—

Writing & Preference Not comparable

Gemma 3 27B: 52.5 (#168), Ministral 3B: —

BenchmarkGemma 3 27BMinistral 3B
LMArena Text1358—
LMArena Creative Writing1346—
Short-Story Creative Writing79.9%—
EQ-Bench Creative Writing1266—
LMArena Multi-Turn1345—
LiveBench Language34.6%—

Frequently asked questions

Is Gemma 3 27B better than Ministral 3B?

Gemma 3 27B is the stronger model overall, scoring 30.8 to 26.2 on the Noometry Index.

Which is cheaper, Gemma 3 27B or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Gemma 3 27B lists at $0.08 and $0.16.

Which has the bigger context window?

Both accept 131K tokens.

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

6 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Ministral 3B has 6.

Related comparisons

Go deeper