Noometry

Model comparison

Grok-3 mini vs Mixtral 8x7B

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

Last verified . 25 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Mixtral 8x7B Mistral AI

27.1

Rank #334 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Mixtral 8x7B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 11.0.
  • The biggest single-benchmark swing is MATH Level 5: 90.9% for Grok-3 mini and 10% for Mixtral 8x7B.
  • Mixtral 8x7B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniMixtral 8x7B
ProviderxAIMistral AI
Noometry Index41.227.1
Released2025-04-092023-12-11
WeightsProprietaryOpen
Context window—32K
Max output—32K
Input $ / M tokens—$0.70
Output $ / M tokens—$0.70
Results tracked3538

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 8x7B: 32.8 (#269)

BenchmarkGrok-3 miniMixtral 8x7B
LMArena Coding13791126
Aider Polyglot49.3%—
WeirdML42.6%—
HumanEval+—39.6%
MBPP+—49.7%

Reasoning Mixtral 8x7B leads

Grok-3 mini: 13.6 (#334), Mixtral 8x7B: 18.2 (#285)

BenchmarkGrok-3 miniMixtral 8x7B
LMArena Hard Prompts13751115
Epoch Capabilities Index140.35118.47
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
DTBench—49.6%
Adversarial NLI—55.2%
ForecastBench—56.3
HellaSwag—86.7%
PIQA—83.6%
WinoGrande—77.2%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Mixtral 8x7B: 18.8 (#289)

BenchmarkGrok-3 miniMixtral 8x7B
Omni-MATH31.8%10.5%
LMArena Math13861147
MATH Level 590.9%10%
OTIS Mock AIME 2024-202577.8%—
FrontierMath (Feb 2025 set)5.9%—
GSM8K—74.4%

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Mixtral 8x7B: 11.0 (#301)

BenchmarkGrok-3 miniMixtral 8x7B
GPQA Diamond76.3%30.6%
MMLU-Pro79.9%33.5%
GPQA (HELM)67.5%29.6%
LMArena Expert13951088
Confabulations10.8%—
ARC (AI2) Challenge—87.3%
MMLU—70.6%
OpenBookQA—85.8%
TriviaQA—82.2%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Mixtral 8x7B: 29.6 (#266)

BenchmarkGrok-3 miniMixtral 8x7B
LMArena Non-English13521077
LMArena Chinese13871055
LMArena French13571166
LMArena German13491114
LMArena Japanese1342931
LMArena Korean1335968
LMArena Russian13531090
LMArena Spanish13811111

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Mixtral 8x7B: 51.0 (#297)

BenchmarkGrok-3 miniMixtral 8x7B
IFEval95.1%57.5%
LMArena Instruction Following13571109

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Mixtral 8x7B: 33.4 (#260)

BenchmarkGrok-3 miniMixtral 8x7B
LMArena Longer Query13721103
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Mixtral 8x7B: 34.2 (#270)

BenchmarkGrok-3 miniMixtral 8x7B
LMArena Text13701132
LMArena Creative Writing13421109
WildBench65.1%67.3%
LMArena Multi-Turn13551115
Short-Story Creative Writing73.5%—

Frequently asked questions

Is Grok-3 mini better than Mixtral 8x7B?

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

Is Grok-3 mini or Mixtral 8x7B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 32.8 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Mixtral 8x7B share?

25 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Mixtral 8x7B has 38.

Related comparisons

Go deeper