Noometry

Model comparison

Gemma 2 27B vs Ministral 3B

Gemma 2 27B is the stronger model overall, scoring 29.4 to 26.2 on the Noometry Index. Ministral 3B costs 6.5× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.

Last verified . 5 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Ministral 3B Mistral AI

26.2

Rank #338 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and Ministral 3B in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Ministral 3B leads 26.6 to 10.7.
  • The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 14.4% for Ministral 3B.
  • Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
  • Ministral 3B accepts more context: 131K tokens versus 8K.

Side by side

Gemma 2 27BMinistral 3B
ProviderGoogleMistral AI
Noometry Index29.426.2
Released2024-06-242024-10-01
WeightsOpenOpen
Context window8K131K
Max output2K262K
Input $ / M tokens$0.65$0.10
Output $ / M tokens$0.65$0.10
Results tracked346

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

Category by category

Coding Not comparable

Gemma 2 27B: 34.1 (#246), Ministral 3B: —

BenchmarkGemma 2 27BMinistral 3B
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
LMArena Coding1211—
BigCodeBench Complete52.5%—

Reasoning Ministral 3B leads

Gemma 2 27B: 15.3 (#315), Ministral 3B: 18.4 (#282)

BenchmarkGemma 2 27BMinistral 3B
DTBench48%51.7%
LMCA7.1%5.5%
Epoch Capabilities Index122.08118.1
LiveBench Reasoning28.1%—
LMArena Hard Prompts1198—
LiveBench Data Analysis47.9%—
LiveBench38.2%—

Math Ministral 3B leads

Gemma 2 27B: 10.7 (#311), Ministral 3B: 26.6 (#258)

BenchmarkGemma 2 27BMinistral 3B
MATH Level 527.9%14.4%
OTIS Mock AIME 2024-20251.4%—
LiveBench Math26.5%—
LMArena Math1212—

Knowledge Gemma 2 27B leads

Gemma 2 27B: 19.0 (#280), Ministral 3B: 10.4 (#302)

BenchmarkGemma 2 27BMinistral 3B
GPQA Diamond36.5%25.3%
Confabulations27.1%—
Vectara Hallucination Rate—7.3%
LMArena Expert1172—
MMLU75.7%—

Multilingual Not comparable

Gemma 2 27B: 38.6 (#226), Ministral 3B: —

BenchmarkGemma 2 27BMinistral 3B
LMArena Non-English1217—
LMArena Chinese1221—
LMArena French1247—
LMArena German1209—
LMArena Japanese1175—
LMArena Korean1174—
LMArena Russian1234—
LMArena Spanish1228—

Instruction Following Not comparable

Gemma 2 27B: 60.5 (#249), Ministral 3B: —

BenchmarkGemma 2 27BMinistral 3B
LiveBench Instruction Following58.1%—
LMArena Instruction Following1206—

Long Context Not comparable

Gemma 2 27B: 37.3 (#218), Ministral 3B: —

BenchmarkGemma 2 27BMinistral 3B
LMArena Longer Query1231—

Writing & Preference Not comparable

Gemma 2 27B: 44.2 (#225), Ministral 3B: —

BenchmarkGemma 2 27BMinistral 3B
LMArena Text1231—
LMArena Creative Writing1241—
LMArena Multi-Turn1224—
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than Ministral 3B?

Gemma 2 27B is the stronger model overall, scoring 29.4 to 26.2 on the Noometry Index. Ministral 3B costs 6.5× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.

Which is cheaper, Gemma 2 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 2 27B lists at $0.65 and $0.65.

Which has the bigger context window?

Ministral 3B does, with 131K tokens against 8K.

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

5 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Ministral 3B has 6.

Related comparisons

Go deeper