Noometry

Model comparison

Grok-2 (Dec 2024) vs Llama 3.2 90B

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 27.5 on the Noometry Index.

Last verified . 4 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Llama 3.2 90B Meta

27.5

Rank #331 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 2 categories and Llama 3.2 90B in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-2 (Dec 2024) leads 20.8 to 11.1.
  • The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 39.4% for Llama 3.2 90B.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Llama 3.2 90B
ProviderxAIMeta
Noometry Index33.727.5
Released2024-08-132024-09-24
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked349

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Grok-2 (Dec 2024): 33.3 (#258), Llama 3.2 90B: —

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
WeirdML22.2%—
LiveBench Coding46.4%—
LMArena Coding1287—

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Llama 3.2 90B: 30.0 (#80)

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
BALROG—27.3%

Reasoning Llama 3.2 90B leads

Grok-2 (Dec 2024): 16.9 (#299), Llama 3.2 90B: 21.7 (#217)

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
Epoch Capabilities Index130.48125.5
SimpleBench22.7%—
EnigmaEval—0.4%
LiveBench Reasoning54.8%—
LMArena Hard Prompts1272—
DTBench65.2%—
LiveBench Data Analysis54.5%—
LiveBench54.3%—

Math Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 20.8 (#284), Llama 3.2 90B: 11.1 (#308)

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
OTIS Mock AIME 2024-202511.5%2.6%
MATH Level 563.5%39.4%
LiveBench Math54.9%—
LMArena Math1283—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 29.8 (#233), Llama 3.2 90B: 21.7 (#274)

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
GPQA Diamond53.8%41%
Confabulations20.1%—
LMArena Expert1254—
MMLU—80.3%

Multimodal Not comparable

Grok-2 (Dec 2024): —, Llama 3.2 90B: 25.4 (#124)

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
LMArena Vision—1000
GeoBench—52%

Multilingual Not comparable

Grok-2 (Dec 2024): 43.1 (#188), Llama 3.2 90B: —

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
LMArena Non-English1282—
LMArena Chinese1289—
LMArena French1318—
LMArena German1287—
LMArena Japanese1244—
LMArena Korean1237—
LMArena Russian1286—
LMArena Spanish1281—

Instruction Following Not comparable

Grok-2 (Dec 2024): 66.9 (#202), Llama 3.2 90B: —

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
LiveBench Instruction Following69.6%—
LMArena Instruction Following1270—

Long Context Not comparable

Grok-2 (Dec 2024): 38.8 (#190), Llama 3.2 90B: —

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
LMArena Longer Query1276—

Writing & Preference Not comparable

Grok-2 (Dec 2024): 48.6 (#198), Llama 3.2 90B: —

BenchmarkGrok-2 (Dec 2024)Llama 3.2 90B
LMArena Text1305—
LMArena Creative Writing1284—
Short-Story Creative Writing63.6%—
LMArena Multi-Turn1290—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Llama 3.2 90B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 27.5 on the Noometry Index.

How many benchmarks do Grok-2 (Dec 2024) and Llama 3.2 90B share?

4 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper