Noometry

Model comparison

Grok-3 mini vs Llama 3.1-70B

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.6 on the Noometry Index.

Last verified . 27 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Llama 3.1-70B Meta

29.6

Rank #308 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Llama 3.1-70B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 42.1 to 13.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 3.6% for Llama 3.1-70B.
  • Llama 3.1-70B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniLlama 3.1-70B
ProviderxAIMeta
Noometry Index41.229.6
Released2025-04-092024-07-23
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.40
Output $ / M tokens—$0.40
Results tracked3535

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 3.1-70B: 30.3 (#296)

BenchmarkGrok-3 miniLlama 3.1-70B
WeirdML42.6%9%
LMArena Coding13791260
Aider Polyglot49.3%—
BigCodeBench Instruct—46.1%
BigCodeBench Complete—54.8%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Llama 3.1-70B: 25.1 (#112)

BenchmarkGrok-3 miniLlama 3.1-70B
TheAgentCompany—6.9%
BALROG—27.9%

Reasoning Llama 3.1-70B leads

Grok-3 mini: 13.6 (#334), Llama 3.1-70B: 21.6 (#220)

BenchmarkGrok-3 miniLlama 3.1-70B
LMArena Hard Prompts13751241
Epoch Capabilities Index140.35125.92
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
DTBench—60%
LMCA—14.8%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Llama 3.1-70B: 13.5 (#304)

BenchmarkGrok-3 miniLlama 3.1-70B
OTIS Mock AIME 2024-202577.8%3.6%
Omni-MATH31.8%21%
LMArena Math13861252
MATH Level 590.9%36.7%
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Llama 3.1-70B: 24.2 (#269)

BenchmarkGrok-3 miniLlama 3.1-70B
GPQA Diamond76.3%44.2%
MMLU-Pro79.9%65.3%
GPQA (HELM)67.5%42.6%
LMArena Expert13951209
Confabulations10.8%—
MMLU—80.1%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Llama 3.1-70B: 38.8 (#225)

BenchmarkGrok-3 miniLlama 3.1-70B
LMArena Non-English13521219
LMArena Chinese13871215
LMArena French13571261
LMArena German13491222
LMArena Japanese13421132
LMArena Korean13351140
LMArena Russian13531234
LMArena Spanish13811253

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Llama 3.1-70B: 65.3 (#223)

BenchmarkGrok-3 miniLlama 3.1-70B
IFEval95.1%82.1%
LMArena Instruction Following13571231

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Llama 3.1-70B: 37.6 (#214)

BenchmarkGrok-3 miniLlama 3.1-70B
LMArena Longer Query13721241
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Llama 3.1-70B: 35.4 (#267)

BenchmarkGrok-3 miniLlama 3.1-70B
LMArena Text13701261
LMArena Creative Writing13421232
WildBench65.1%75.8%
LMArena Multi-Turn13551256
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing—784

Frequently asked questions

Is Grok-3 mini better than Llama 3.1-70B?

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.6 on the Noometry Index.

Is Grok-3 mini or Llama 3.1-70B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 30.3 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Llama 3.1-70B share?

27 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper