Noometry

Model comparison

Grok-3 mini vs Mixtral 8x22B

Grok-3 mini is the stronger model overall, scoring 41.2 to 27.1 on the Noometry Index.

Last verified . 26 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Mixtral 8x22B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 15.1.
  • The biggest single-benchmark swing is MATH Level 5: 90.9% for Grok-3 mini and 24.2% for Mixtral 8x22B.
  • Mixtral 8x22B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniMixtral 8x22B
ProviderxAIMistral AI
Noometry Index41.227.1
Released2025-04-092024-04-17
WeightsProprietaryOpen
Context window—64K
Max output—64K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3534

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.8 (#131), Mixtral 8x22B: 24.2 (#329)

BenchmarkGrok-3 miniMixtral 8x22B
WeirdML42.6%3.2%
LMArena Coding13791166
Aider Polyglot49.3%—
BigCodeBench Instruct—40.6%
BigCodeBench Complete—50.2%
HumanEval+—72%
MBPP+—64.3%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Mixtral 8x22B: 23.1 (#127)

BenchmarkGrok-3 miniMixtral 8x22B
Cybench—7.5%

Reasoning Mixtral 8x22B leads

Grok-3 mini: 13.6 (#334), Mixtral 8x22B: 19.9 (#248)

BenchmarkGrok-3 miniMixtral 8x22B
LMArena Hard Prompts13751150
Epoch Capabilities Index140.35122.03
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
DTBench—55.1%
ForecastBench—56.3

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Mixtral 8x22B: 22.9 (#275)

BenchmarkGrok-3 miniMixtral 8x22B
Omni-MATH31.8%16.3%
LMArena Math13861184
MATH Level 590.9%24.2%
OTIS Mock AIME 2024-202577.8%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Mixtral 8x22B: 15.1 (#293)

BenchmarkGrok-3 miniMixtral 8x22B
GPQA Diamond76.3%34.1%
MMLU-Pro79.9%46%
GPQA (HELM)67.5%33.4%
LMArena Expert13951113
Confabulations10.8%—
MMLU—77.8%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Mixtral 8x22B: 32.8 (#255)

BenchmarkGrok-3 miniMixtral 8x22B
LMArena Non-English13521128
LMArena Chinese13871116
LMArena French13571166
LMArena German13491141
LMArena Japanese13421037
LMArena Korean13351057
LMArena Russian13531158
LMArena Spanish13811151

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Mixtral 8x22B: 57.7 (#266)

BenchmarkGrok-3 miniMixtral 8x22B
IFEval95.1%72.4%
LMArena Instruction Following13571147

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Mixtral 8x22B: 34.7 (#247)

BenchmarkGrok-3 miniMixtral 8x22B
LMArena Longer Query13721144
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Mixtral 8x22B: 36.9 (#262)

BenchmarkGrok-3 miniMixtral 8x22B
LMArena Text13701162
LMArena Creative Writing13421141
WildBench65.1%71.1%
LMArena Multi-Turn13551130
Short-Story Creative Writing73.5%—

Frequently asked questions

Is Grok-3 mini better than Mixtral 8x22B?

Grok-3 mini is the stronger model overall, scoring 41.2 to 27.1 on the Noometry Index.

Is Grok-3 mini or Mixtral 8x22B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 24.2 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Mixtral 8x22B share?

26 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Mixtral 8x22B has 34.

Related comparisons

Go deeper