Noometry

Model comparison

Gemma 2 27B vs Mixtral 8x22B

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

Last verified . 24 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Gemma 2 27B scores higher in 6 categories and Mixtral 8x22B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Mixtral 8x22B leads 22.9 to 10.7.
  • The biggest single-benchmark swing is DTBench: 48% for Gemma 2 27B and 55.1% for Mixtral 8x22B.
  • Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
  • Mixtral 8x22B accepts more context: 64K tokens versus 8K.

Side by side

Gemma 2 27BMixtral 8x22B
ProviderGoogleMistral AI
Noometry Index29.427.1
Released2024-06-242024-04-17
WeightsOpenOpen
Context window8K64K
Max output2K64K
Input $ / M tokens$0.65$2
Output $ / M tokens$0.65$6
Results tracked3434

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 8x22B: 24.2 (#329)

BenchmarkGemma 2 27BMixtral 8x22B
BigCodeBench Instruct42.8%40.6%
LMArena Coding12111166
BigCodeBench Complete52.5%50.2%
WeirdML—3.2%
LiveBench Coding36%—
HumanEval+—72%
MBPP+—64.3%

Agentic & Tool Use Not comparable

Gemma 2 27B: —, Mixtral 8x22B: 23.1 (#127)

BenchmarkGemma 2 27BMixtral 8x22B
Cybench—7.5%

Reasoning Mixtral 8x22B leads

Gemma 2 27B: 15.3 (#315), Mixtral 8x22B: 19.9 (#248)

BenchmarkGemma 2 27BMixtral 8x22B
LMArena Hard Prompts11981150
DTBench48%55.1%
Epoch Capabilities Index122.08122.03
LiveBench Reasoning28.1%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
ForecastBench—56.3
LiveBench38.2%—

Math Mixtral 8x22B leads

Gemma 2 27B: 10.7 (#311), Mixtral 8x22B: 22.9 (#275)

BenchmarkGemma 2 27BMixtral 8x22B
LMArena Math12121184
MATH Level 527.9%24.2%
OTIS Mock AIME 2024-20251.4%—
Omni-MATH—16.3%
LiveBench Math26.5%—

Knowledge Gemma 2 27B leads

Gemma 2 27B: 19.0 (#280), Mixtral 8x22B: 15.1 (#293)

BenchmarkGemma 2 27BMixtral 8x22B
GPQA Diamond36.5%34.1%
LMArena Expert11721113
MMLU75.7%77.8%
MMLU-Pro—46%
Confabulations27.1%—
GPQA (HELM)—33.4%

Multilingual Gemma 2 27B leads

Gemma 2 27B: 38.6 (#226), Mixtral 8x22B: 32.8 (#255)

BenchmarkGemma 2 27BMixtral 8x22B
LMArena Non-English12171128
LMArena Chinese12211116
LMArena French12471166
LMArena German12091141
LMArena Japanese11751037
LMArena Korean11741057
LMArena Russian12341158
LMArena Spanish12281151

Instruction Following Gemma 2 27B leads

Gemma 2 27B: 60.5 (#249), Mixtral 8x22B: 57.7 (#266)

BenchmarkGemma 2 27BMixtral 8x22B
LMArena Instruction Following12061147
LiveBench Instruction Following58.1%—
IFEval—72.4%

Long Context Gemma 2 27B leads

Gemma 2 27B: 37.3 (#218), Mixtral 8x22B: 34.7 (#247)

BenchmarkGemma 2 27BMixtral 8x22B
LMArena Longer Query12311144

Writing & Preference Gemma 2 27B leads

Gemma 2 27B: 44.2 (#225), Mixtral 8x22B: 36.9 (#262)

BenchmarkGemma 2 27BMixtral 8x22B
LMArena Text12311162
LMArena Creative Writing12411141
LMArena Multi-Turn12241130
WildBench—71.1%
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than Mixtral 8x22B?

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 8x22B?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Mixtral 8x22B lists at $2 and $6.

Is Gemma 2 27B or Mixtral 8x22B better for coding?

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 24.2 in the Noometry coding category.

Which has the bigger context window?

Mixtral 8x22B does, with 64K tokens against 8K.

How many benchmarks do Gemma 2 27B and Mixtral 8x22B share?

24 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Mixtral 8x22B has 34.

Related comparisons

Go deeper