Noometry

Model comparison

Grok-2 (Dec 2024) vs Llama 2-13B

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 29.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.4

Rank #233 Confirmed

Llama 2-13B Meta

29.1

Rank #304 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 7 categories and Llama 2-13B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.8 to 30.0.
  • The biggest single-benchmark swing is DTBench: 65.2% for Grok-2 (Dec 2024) and 42.2% for Llama 2-13B.
  • Llama 2-13B has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Llama 2-13B
ProviderxAIMeta
Noometry Index33.429.1
Released2024-08-132023-07-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3432

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): 32.9 (#254), Llama 2-13B: 30.4 (#287)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Coding12881062
WeirdML22.2%—
LiveBench Coding46.4%—

Reasoning Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 16.4 (#294), Llama 2-13B: 12.3 (#333)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Hard Prompts12721051
DTBench65.2%42.2%
Epoch Capabilities Index130.48105.8
SimpleBench22.7%—
Chess Puzzles—0%
LiveBench Reasoning54.8%—
LiveBench Data Analysis54.5%—
BIG-Bench Hard—58.2%
HellaSwag—80.7%
LAMBADA—76.5%
LiveBench54.3%—
PIQA—80.8%
WinoGrande—72.8%

Math Llama 2-13B leads

Grok-2 (Dec 2024): 19.6 (#278), Llama 2-13B: 28.7 (#226)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Math12831065
OTIS Mock AIME 2024-202511.5%—
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—
GSM8K—36.9%

Knowledge Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 29.8 (#225), Llama 2-13B: 27.5 (#244)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Expert12541030
GPQA Diamond53.8%—
Confabulations20.1%—
ARC (AI2) Challenge—60.3%
BoolQ—82.4%
MMLU—55.6%
OpenBookQA—57%
TriviaQA—79.6%

Multimodal Not comparable

Grok-2 (Dec 2024): —, Llama 2-13B: —

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
ScienceQA—55.8%

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.3 (#183), Llama 2-13B: 26.7 (#274)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Non-English12821024
LMArena Chinese12891001
LMArena French13171043
LMArena German12871009
LMArena Japanese1244894
LMArena Korean1237953
LMArena Russian12861055
LMArena Spanish12811086

Instruction Following Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 67.1 (#197), Llama 2-13B: 53.5 (#282)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Instruction Following12701046
LiveBench Instruction Following69.6%—

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.7 (#186), Llama 2-13B: 32.3 (#264)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Longer Query12761064

Writing & Preference Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 48.8 (#192), Llama 2-13B: 30.0 (#284)

BenchmarkGrok-2 (Dec 2024)Llama 2-13B
LMArena Text13051085
LMArena Creative Writing12841047
LMArena Multi-Turn12901050
Short-Story Creative Writing63.6%—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Llama 2-13B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 29.1 on the Noometry Index.

Is Grok-2 (Dec 2024) or Llama 2-13B better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 32.9 versus 30.4 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Llama 2-13B share?

19 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Llama 2-13B has 32.

Related comparisons

Go deeper