Noometry

Model comparison

Grok-2 (Dec 2024) vs Mixtral 8x22B

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 27.1 on the Noometry Index.

Last verified . 22 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 6 categories and Mixtral 8x22B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 15.1.
  • The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 24.2% for Mixtral 8x22B.
  • Mixtral 8x22B has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Mixtral 8x22B
ProviderxAIMistral AI
Noometry Index33.727.1
Released2024-08-132024-04-17
WeightsProprietaryOpen
Context window—64K
Max output—64K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3434

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

Category by category

Coding Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 33.3 (#258), Mixtral 8x22B: 24.2 (#329)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
WeirdML22.2%3.2%
LMArena Coding12871166
BigCodeBench Instruct—40.6%
LiveBench Coding46.4%—
BigCodeBench Complete—50.2%
HumanEval+—72%
MBPP+—64.3%

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Mixtral 8x22B: 23.1 (#127)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
Cybench—7.5%

Reasoning Mixtral 8x22B leads

Grok-2 (Dec 2024): 16.9 (#299), Mixtral 8x22B: 19.9 (#248)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
LMArena Hard Prompts12721150
DTBench65.2%55.1%
Epoch Capabilities Index130.48122.03
SimpleBench22.7%—
LiveBench Reasoning54.8%—
LiveBench Data Analysis54.5%—
ForecastBench—56.3
LiveBench54.3%—

Math Mixtral 8x22B leads

Grok-2 (Dec 2024): 20.8 (#284), Mixtral 8x22B: 22.9 (#275)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
LMArena Math12831184
MATH Level 563.5%24.2%
OTIS Mock AIME 2024-202511.5%—
Omni-MATH—16.3%
LiveBench Math54.9%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 29.8 (#233), Mixtral 8x22B: 15.1 (#293)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
GPQA Diamond53.8%34.1%
LMArena Expert12541113
MMLU-Pro—46%
Confabulations20.1%—
GPQA (HELM)—33.4%
MMLU—77.8%

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.1 (#188), Mixtral 8x22B: 32.8 (#255)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
LMArena Non-English12821128
LMArena Chinese12891116
LMArena French13181166
LMArena German12871141
LMArena Japanese12441037
LMArena Korean12371057
LMArena Russian12861158
LMArena Spanish12811151

Instruction Following Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 66.9 (#202), Mixtral 8x22B: 57.7 (#266)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
LMArena Instruction Following12701147
LiveBench Instruction Following69.6%—
IFEval—72.4%

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.8 (#190), Mixtral 8x22B: 34.7 (#247)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
LMArena Longer Query12761144

Writing & Preference Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 48.6 (#198), Mixtral 8x22B: 36.9 (#262)

BenchmarkGrok-2 (Dec 2024)Mixtral 8x22B
LMArena Text13051162
LMArena Creative Writing12841141
LMArena Multi-Turn12901130
Short-Story Creative Writing63.6%—
WildBench—71.1%
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Mixtral 8x22B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 27.1 on the Noometry Index.

Is Grok-2 (Dec 2024) or Mixtral 8x22B better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 24.2 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Mixtral 8x22B share?

22 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Mixtral 8x22B has 34.

Related comparisons

Go deeper