Noometry

Model comparison

Grok-2 (Dec 2024) vs Llama 3-8B

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 25.3 on the Noometry Index.

Last verified . 22 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.4

Rank #233 Confirmed

Llama 3-8B Meta

25.3

Rank #338 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 8 categories and Llama 3-8B 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 7.8.
  • The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 6.1% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Llama 3-8B
ProviderxAIMeta
Noometry Index33.425.3
Released2024-08-132024-04-18
WeightsProprietaryOpen
Context window—8K
Max output—8K
Input $ / M tokens—$0.14
Output $ / M tokens—$0.14
Results tracked3434

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 3-8B: 30.5 (#285)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
LMArena Coding12881152
WeirdML22.2%—
BigCodeBench Instruct—31.9%
LiveBench Coding46.4%—
BigCodeBench Complete—36.9%
HumanEval+—56.7%
MBPP+—54.8%

Reasoning Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 16.4 (#294), Llama 3-8B: 13.8 (#321)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
LMArena Hard Prompts12721133
DTBench65.2%43.9%
Epoch Capabilities Index130.48116.33
SimpleBench22.7%—
Chess Puzzles—0%
LiveBench Reasoning54.8%—
LiveBench Data Analysis54.5%—
Adversarial NLI—57.3%
ForecastBench—58.6
LiveBench54.3%—
WinoGrande—75.7%

Math Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 19.6 (#278), Llama 3-8B: 8.3 (#317)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
OTIS Mock AIME 2024-202511.5%1.9%
LMArena Math12831151
MATH Level 563.5%6.1%
LiveBench Math54.9%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 29.8 (#225), Llama 3-8B: 7.8 (#303)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
GPQA Diamond53.8%26.1%
LMArena Expert12541113
Confabulations20.1%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.3 (#183), Llama 3-8B: 31.0 (#256)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
LMArena Non-English12821098
LMArena Chinese12891076
LMArena French13171158
LMArena German12871104
LMArena Japanese1244967
LMArena Korean12371003
LMArena Russian12861109
LMArena Spanish12811172

Instruction Following Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 67.1 (#197), Llama 3-8B: 58.7 (#255)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
LMArena Instruction Following12701127
LiveBench Instruction Following69.6%—

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.7 (#186), Llama 3-8B: 34.2 (#246)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
LMArena Longer Query12761128

Writing & Preference Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 48.8 (#192), Llama 3-8B: 37.7 (#251)

BenchmarkGrok-2 (Dec 2024)Llama 3-8B
LMArena Text13051166
LMArena Creative Writing12841150
LMArena Multi-Turn12901152
Short-Story Creative Writing63.6%—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Llama 3-8B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 25.3 on the Noometry Index.

Is Grok-2 (Dec 2024) or Llama 3-8B better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 32.9 versus 30.5 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Llama 3-8B share?

22 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper