Noometry

Model comparison

Grok-3 mini vs Llama 2-70B

Grok-3 mini is the stronger model overall, scoring 41.2 to 24.4 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Llama 2-70B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 7.4.
  • The biggest single-benchmark swing is MATH Level 5: 90.9% for Grok-3 mini and 3.3% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniLlama 2-70B
ProviderxAIMeta
Noometry Index41.224.4
Released2025-04-092023-07-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
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 2-70B: 31.4 (#286)

BenchmarkGrok-3 miniLlama 2-70B
LMArena Coding13791079
Aider Polyglot49.3%—
WeirdML42.6%—

Reasoning Too close to call

Grok-3 mini: 13.6 (#334), Llama 2-70B: 14.4 (#325)

BenchmarkGrok-3 miniLlama 2-70B
LMArena Hard Prompts13751073
Epoch Capabilities Index140.35113.79
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
DTBench—41.6%
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%
WinoGrande—80.2%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Llama 2-70B: 8.1 (#326)

BenchmarkGrok-3 miniLlama 2-70B
OTIS Mock AIME 2024-202577.8%0%
LMArena Math13861091
MATH Level 590.9%3.3%
Omni-MATH31.8%—
FrontierMath (Feb 2025 set)5.9%—
GSM8K—69.6%

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Llama 2-70B: 7.4 (#310)

BenchmarkGrok-3 miniLlama 2-70B
GPQA Diamond76.3%26.3%
LMArena Expert13951039
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Llama 2-70B: 27.7 (#274)

BenchmarkGrok-3 miniLlama 2-70B
LMArena Non-English13521045
LMArena Chinese1387995
LMArena French13571090
LMArena German13491041
LMArena Japanese1342927
LMArena Korean1335964
LMArena Russian13531083
LMArena Spanish13811143

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Llama 2-70B: 54.9 (#278)

BenchmarkGrok-3 miniLlama 2-70B
LMArena Instruction Following13571071
IFEval95.1%—

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Llama 2-70B: 32.3 (#270)

BenchmarkGrok-3 miniLlama 2-70B
LMArena Longer Query13721062
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Llama 2-70B: 32.3 (#279)

BenchmarkGrok-3 miniLlama 2-70B
LMArena Text13701115
LMArena Creative Writing13421075
LMArena Multi-Turn13551088
Short-Story Creative Writing73.5%—
WildBench65.1%—

Frequently asked questions

Is Grok-3 mini better than Llama 2-70B?

Grok-3 mini is the stronger model overall, scoring 41.2 to 24.4 on the Noometry Index.

Is Grok-3 mini or Llama 2-70B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 31.4 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Llama 2-70B share?

21 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper