Noometry

Model comparison

Grok-2 (Dec 2024) vs Llama 2-70B

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 24.4 on the Noometry Index.

Last verified . 22 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 7.4.
  • The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 3.3% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Llama 2-70B
ProviderxAIMeta
Noometry Index33.724.4
Released2024-08-132023-07-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3435

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), Llama 2-70B: 31.4 (#286)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
LMArena Coding12871079
WeirdML22.2%—
LiveBench Coding46.4%—

Reasoning Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 16.9 (#299), Llama 2-70B: 14.4 (#325)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
LMArena Hard Prompts12721073
DTBench65.2%41.6%
Epoch Capabilities Index130.48113.79
SimpleBench22.7%—
LiveBench Reasoning54.8%—
LiveBench Data Analysis54.5%—
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
LiveBench54.3%—
PIQA—82.8%
WinoGrande—80.2%

Math Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 20.8 (#284), Llama 2-70B: 8.1 (#326)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
OTIS Mock AIME 2024-202511.5%0%
LMArena Math12831091
MATH Level 563.5%3.3%
LiveBench Math54.9%—
FrontierMath (Feb 2025 set)0.7%—
GSM8K—69.6%

Knowledge Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 29.8 (#233), Llama 2-70B: 7.4 (#310)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
GPQA Diamond53.8%26.3%
LMArena Expert12541039
Confabulations20.1%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.1 (#188), Llama 2-70B: 27.7 (#274)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
LMArena Non-English12821045
LMArena Chinese1289995
LMArena French13181090
LMArena German12871041
LMArena Japanese1244927
LMArena Korean1237964
LMArena Russian12861083
LMArena Spanish12811143

Instruction Following Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 66.9 (#202), Llama 2-70B: 54.9 (#278)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
LMArena Instruction Following12701071
LiveBench Instruction Following69.6%—

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.8 (#190), Llama 2-70B: 32.3 (#270)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
LMArena Longer Query12761062

Writing & Preference Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 48.6 (#198), Llama 2-70B: 32.3 (#279)

BenchmarkGrok-2 (Dec 2024)Llama 2-70B
LMArena Text13051115
LMArena Creative Writing12841075
LMArena Multi-Turn12901088
Short-Story Creative Writing63.6%—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Llama 2-70B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 24.4 on the Noometry Index.

Is Grok-2 (Dec 2024) or Llama 2-70B better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 31.4 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Llama 2-70B share?

22 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper