Noometry

Model comparison

Gemma 2 27B vs Mixtral 8x7B

Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.1 on the Noometry Index.

Last verified . 22 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Mixtral 8x7B Mistral AI

27.1

Rank #334 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemma 2 27B scores higher in 6 categories and Mixtral 8x7B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 2 27B leads 44.2 to 34.2.
  • The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 10% for Mixtral 8x7B.
  • Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
  • Mixtral 8x7B accepts more context: 32K tokens versus 8K.

Side by side

Gemma 2 27BMixtral 8x7B
ProviderGoogleMistral AI
Noometry Index29.427.1
Released2024-06-242023-12-11
WeightsOpenOpen
Context window8K32K
Max output2K32K
Input $ / M tokens$0.65$0.70
Output $ / M tokens$0.65$0.70
Results tracked3438

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

Category by category

Coding Gemma 2 27B leads

Gemma 2 27B: 34.1 (#246), Mixtral 8x7B: 32.8 (#269)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Coding12111126
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—
HumanEval+—39.6%
MBPP+—49.7%

Reasoning Mixtral 8x7B leads

Gemma 2 27B: 15.3 (#315), Mixtral 8x7B: 18.2 (#285)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Hard Prompts11981115
DTBench48%49.6%
Epoch Capabilities Index122.08118.47
LiveBench Reasoning28.1%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
Adversarial NLI—55.2%
ForecastBench—56.3
HellaSwag—86.7%
LiveBench38.2%—
PIQA—83.6%
WinoGrande—77.2%

Math Mixtral 8x7B leads

Gemma 2 27B: 10.7 (#311), Mixtral 8x7B: 18.8 (#289)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Math12121147
MATH Level 527.9%10%
OTIS Mock AIME 2024-20251.4%—
Omni-MATH—10.5%
LiveBench Math26.5%—
GSM8K—74.4%

Knowledge Gemma 2 27B leads

Gemma 2 27B: 19.0 (#280), Mixtral 8x7B: 11.0 (#301)

BenchmarkGemma 2 27BMixtral 8x7B
GPQA Diamond36.5%30.6%
LMArena Expert11721088
MMLU75.7%70.6%
MMLU-Pro—33.5%
Confabulations27.1%—
GPQA (HELM)—29.6%
ARC (AI2) Challenge—87.3%
OpenBookQA—85.8%
TriviaQA—82.2%

Multilingual Gemma 2 27B leads

Gemma 2 27B: 38.6 (#226), Mixtral 8x7B: 29.6 (#266)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Non-English12171077
LMArena Chinese12211055
LMArena French12471166
LMArena German12091114
LMArena Japanese1175931
LMArena Korean1174968
LMArena Russian12341090
LMArena Spanish12281111

Instruction Following Gemma 2 27B leads

Gemma 2 27B: 60.5 (#249), Mixtral 8x7B: 51.0 (#297)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Instruction Following12061109
LiveBench Instruction Following58.1%—
IFEval—57.5%

Long Context Gemma 2 27B leads

Gemma 2 27B: 37.3 (#218), Mixtral 8x7B: 33.4 (#260)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Longer Query12311103

Writing & Preference Gemma 2 27B leads

Gemma 2 27B: 44.2 (#225), Mixtral 8x7B: 34.2 (#270)

BenchmarkGemma 2 27BMixtral 8x7B
LMArena Text12311132
LMArena Creative Writing12411109
LMArena Multi-Turn12241115
WildBench—67.3%
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than Mixtral 8x7B?

Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.1 on the Noometry Index.

Which is cheaper, Gemma 2 27B or Mixtral 8x7B?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

Is Gemma 2 27B or Mixtral 8x7B better for coding?

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 32.8 in the Noometry coding category.

Which has the bigger context window?

Mixtral 8x7B does, with 32K tokens against 8K.

How many benchmarks do Gemma 2 27B and Mixtral 8x7B share?

22 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Mixtral 8x7B has 38.

Related comparisons

Go deeper