Noometry

Model comparison

Grok-3 mini vs Llama 3-8B

Grok-3 mini is the stronger model overall, scoring 41.2 to 25.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Llama 3-8B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 7.8.
  • The biggest single-benchmark swing is MATH Level 5: 90.9% for Grok-3 mini and 6.1% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniLlama 3-8B
ProviderxAIMeta
Noometry Index41.225.5
Released2025-04-092024-04-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
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), Llama 3-8B: 31.0 (#289)

BenchmarkGrok-3 miniLlama 3-8B
LMArena Coding13791152
Aider Polyglot49.3%—
WeirdML42.6%—
BigCodeBench Instruct—31.9%
BigCodeBench Complete—36.9%
HumanEval+—56.7%
MBPP+—54.8%

Reasoning Too close to call

Grok-3 mini: 13.6 (#334), Llama 3-8B: 14.3 (#326)

BenchmarkGrok-3 miniLlama 3-8B
LMArena Hard Prompts13751133
Epoch Capabilities Index140.35116.45
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
Chess Puzzles—0%
DTBench—43.9%
Adversarial NLI—57.3%
ForecastBench—58.6
WinoGrande—75.7%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Llama 3-8B: 8.8 (#323)

BenchmarkGrok-3 miniLlama 3-8B
OTIS Mock AIME 2024-202577.8%1.9%
LMArena Math13861151
MATH Level 590.9%6.1%
Omni-MATH31.8%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Llama 3-8B: 7.8 (#308)

BenchmarkGrok-3 miniLlama 3-8B
GPQA Diamond76.3%26.1%
LMArena Expert13951113
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Llama 3-8B: 30.8 (#261)

BenchmarkGrok-3 miniLlama 3-8B
LMArena Non-English13521098
LMArena Chinese13871076
LMArena French13571159
LMArena German13491104
LMArena Japanese1342967
LMArena Korean13351004
LMArena Russian13531109
LMArena Spanish13811173

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Llama 3-8B: 58.4 (#260)

BenchmarkGrok-3 miniLlama 3-8B
LMArena Instruction Following13571127
IFEval95.1%—

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Llama 3-8B: 34.2 (#251)

BenchmarkGrok-3 miniLlama 3-8B
LMArena Longer Query13721128
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Llama 3-8B: 37.5 (#256)

BenchmarkGrok-3 miniLlama 3-8B
LMArena Text13701166
LMArena Creative Writing13421150
LMArena Multi-Turn13551152
Short-Story Creative Writing73.5%—
WildBench65.1%—

Frequently asked questions

Is Grok-3 mini better than Llama 3-8B?

Grok-3 mini is the stronger model overall, scoring 41.2 to 25.5 on the Noometry Index.

Is Grok-3 mini or Llama 3-8B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 31.0 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Llama 3-8B share?

21 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper