Noometry

Model comparison

Amazon Nova Pro vs Llama 3.2 90B

Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.5 on the Noometry Index.

Last verified . 3 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

Llama 3.2 90B Meta

27.5

Rank #331 Confirmed

Summary

  • They share 3 benchmarks with published results for both. Amazon Nova Pro scores higher in 2 categories and Llama 3.2 90B in 3 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Amazon Nova Pro leads 28.5 to 11.1.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova ProLlama 3.2 90B
ProviderAmazonMeta
Noometry Index31.027.5
Released2024-12-032024-09-24
WeightsProprietaryOpen
Context window300K—
Max output10K—
Input $ / M tokens$0.80—
Output $ / M tokens$3.20—
Results tracked389

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

Category by category

Coding Not comparable

Amazon Nova Pro: 35.1 (#229), Llama 3.2 90B: —

BenchmarkAmazon Nova ProLlama 3.2 90B
LiveBench Coding38.1%—
LMArena Coding1270—

Agentic & Tool Use Llama 3.2 90B leads

Amazon Nova Pro: 16.7 (#147), Llama 3.2 90B: 30.0 (#80)

BenchmarkAmazon Nova ProLlama 3.2 90B
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—
BALROG—27.3%

Reasoning Llama 3.2 90B leads

Amazon Nova Pro: 20.0 (#243), Llama 3.2 90B: 21.7 (#217)

BenchmarkAmazon Nova ProLlama 3.2 90B
Epoch Capabilities Index123.8125.5
EnigmaEval—0.4%
LiveBench Reasoning32.6%—
LMArena Hard Prompts1246—
LiveBench Data Analysis48.3%—
LiveBench43.5%—

Math Amazon Nova Pro leads

Amazon Nova Pro: 28.5 (#243), Llama 3.2 90B: 11.1 (#308)

BenchmarkAmazon Nova ProLlama 3.2 90B
OTIS Mock AIME 2024-2025—2.6%
Omni-MATH24.2%—
LiveBench Math38%—
LMArena Math1252—
MATH Level 5—39.4%

Knowledge Amazon Nova Pro leads

Amazon Nova Pro: 27.4 (#250), Llama 3.2 90B: 21.7 (#274)

BenchmarkAmazon Nova ProLlama 3.2 90B
MMLU82%80.3%
GPQA Diamond—41%
Humanity's Last Exam4.4%—
MMLU-Pro67.3%—
Confabulations30.1%—
Vectara Hallucination Rate5.1%—
GPQA (HELM)44.6%—
LMArena Expert1211—

Multimodal Too close to call

Amazon Nova Pro: 25.0 (#126), Llama 3.2 90B: 25.4 (#124)

BenchmarkAmazon Nova ProLlama 3.2 90B
LMArena Vision9801000
GeoBench—52%

Multilingual Not comparable

Amazon Nova Pro: 39.7 (#223), Llama 3.2 90B: —

BenchmarkAmazon Nova ProLlama 3.2 90B
LMArena Non-English1234—
LMArena Chinese1244—
LMArena French1271—
LMArena German1243—
LMArena Japanese1200—
LMArena Korean1203—
LMArena Russian1240—
LMArena Spanish1182—

Instruction Following Not comparable

Amazon Nova Pro: 64.9 (#226), Llama 3.2 90B: —

BenchmarkAmazon Nova ProLlama 3.2 90B
LiveBench Instruction Following67.1%—
IFEval81.5%—
LMArena Instruction Following1235—

Long Context Not comparable

Amazon Nova Pro: 38.1 (#205), Llama 3.2 90B: —

BenchmarkAmazon Nova ProLlama 3.2 90B
LMArena Longer Query1255—

Writing & Preference Not comparable

Amazon Nova Pro: 43.9 (#226), Llama 3.2 90B: —

BenchmarkAmazon Nova ProLlama 3.2 90B
LMArena Text1259—
LMArena Creative Writing1212—
Short-Story Creative Writing60.5%—
WildBench77.7%—
LMArena Multi-Turn1246—
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than Llama 3.2 90B?

Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.5 on the Noometry Index.

How many benchmarks do Amazon Nova Pro and Llama 3.2 90B share?

3 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper