Noometry

Model comparison

Mistral Large 4 vs Mixtral 8x22B

Mistral Large 4 is the stronger model overall, scoring 43.1 to 27.1 on the Noometry Index.

Last verified . 12 shared benchmarks.

Mistral Large 4 Mistral AI

43.1

Rank #99 Confirmed

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Mistral Large 4 scores higher in 8 categories and Mixtral 8x22B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Mistral Large 4 leads 48.6 to 24.2.
  • Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
  • Mistral Large 4 accepts more context: 1.05M tokens versus 64K.
  • Mixtral 8x22B has downloadable open weights; the other is API-only.

Side by side

Mistral Large 4Mixtral 8x22B
ProviderMistral AIMistral AI
Noometry Index43.127.1
Released2026-10-062024-04-17
WeightsProprietaryOpen
Context window1.05M64K
Max output262K64K
Input $ / M tokens$0.68$2
Output $ / M tokens$2.09$6
Results tracked1534

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

Category by category

Coding Mistral Large 4 leads

Mistral Large 4: 48.6 (#57), Mixtral 8x22B: 24.2 (#329)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Coding14751166
LMArena WebDev1541—
WeirdML—3.2%
BigCodeBench Instruct—40.6%
BigCodeBench Complete—50.2%
HumanEval+—72%
MBPP+—64.3%

Agentic & Tool Use Not comparable

Mistral Large 4: —, Mixtral 8x22B: 23.1 (#127)

BenchmarkMistral Large 4Mixtral 8x22B
Cybench—7.5%

Reasoning Mistral Large 4 leads

Mistral Large 4: 22.5 (#192), Mixtral 8x22B: 19.9 (#248)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Hard Prompts14441150
NYT Connections (extended)27.4%—
DTBench—55.1%
Epoch Capabilities Index—122.03
ForecastBench—56.3

Math Mistral Large 4 leads

Mistral Large 4: 40.4 (#91), Mixtral 8x22B: 22.9 (#275)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Math14881184
Omni-MATH—16.3%
MATH Level 5—24.2%

Knowledge Mistral Large 4 leads

Mistral Large 4: 36.6 (#166), Mixtral 8x22B: 15.1 (#293)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Expert14471113
GPQA Diamond—34.1%
SimpleQA Verified20%—
MMLU-Pro—46%
GPQA (HELM)—33.4%
MMLU—77.8%

Multilingual Mistral Large 4 leads

Mistral Large 4: 52.6 (#82), Mixtral 8x22B: 32.8 (#255)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Non-English14151128
LMArena Chinese14911116
LMArena Russian14141158
LMArena French—1166
LMArena German—1141
LMArena Japanese—1037
LMArena Korean—1057
LMArena Spanish—1151

Instruction Following Mistral Large 4 leads

Mistral Large 4: 75.0 (#76), Mixtral 8x22B: 57.7 (#266)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Instruction Following14241147
IFEval—72.4%

Long Context Mistral Large 4 leads

Mistral Large 4: 43.6 (#89), Mixtral 8x22B: 34.7 (#247)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Longer Query14291144

Writing & Preference Mistral Large 4 leads

Mistral Large 4: 60.4 (#97), Mixtral 8x22B: 36.9 (#262)

BenchmarkMistral Large 4Mixtral 8x22B
LMArena Text14271162
LMArena Creative Writing13611141
LMArena Multi-Turn14241130
WildBench—71.1%

Frequently asked questions

Is Mistral Large 4 better than Mixtral 8x22B?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 27.1 on the Noometry Index.

Which is cheaper, Mistral Large 4 or Mixtral 8x22B?

Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Mixtral 8x22B lists at $2 and $6.

Is Mistral Large 4 or Mixtral 8x22B better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 24.2 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 64K.

How many benchmarks do Mistral Large 4 and Mixtral 8x22B share?

12 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Mixtral 8x22B has 34.

Related comparisons

Go deeper