Noometry

Model comparison

Amazon Nova Micro vs Llama 3.2 3B

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 28.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Llama 3.2 3B Meta

28.9

Rank #321 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Amazon Nova Micro scores higher in 6 categories and Llama 3.2 3B in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Amazon Nova Micro leads 39.5 to 24.7.
  • Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
  • Llama 3.2 3B accepts more context: 131K tokens versus 128K.
  • Llama 3.2 3B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroLlama 3.2 3B
ProviderAmazonMeta
Noometry Index30.428.9
Released2024-12-032024-09-24
WeightsProprietaryOpen
Context window128K131K
Max output10K118K
Input $ / M tokens$0.035$0.05
Output $ / M tokens$0.14$0.33
Results tracked3218

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

Category by category

Coding Amazon Nova Micro leads

Amazon Nova Micro: 30.5 (#295), Llama 3.2 3B: 27.6 (#319)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Coding12181098
BigCodeBench Instruct—23.4%
LiveBench Coding20.2%—
BigCodeBench Complete—28.3%

Agentic & Tool Use Amazon Nova Micro leads

Amazon Nova Micro: 22.1 (#132), Llama 3.2 3B: 20.1 (#143)

BenchmarkAmazon Nova MicroLlama 3.2 3B
Berkeley Function Calling Leaderboard22.3%21.9%
BALROG—10.1%

Reasoning Llama 3.2 3B leads

Amazon Nova Micro: 17.4 (#294), Llama 3.2 3B: 21.0 (#228)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Hard Prompts11911095
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math Llama 3.2 3B leads

Amazon Nova Micro: 26.9 (#254), Llama 3.2 3B: 32.4 (#214)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Math12061126
Omni-MATH21.4%—
LiveBench Math34.5%—

Knowledge Too close to call

Amazon Nova Micro: 29.6 (#237), Llama 3.2 3B: 29.7 (#235)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Expert11841090
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
MMLU70.8%—

Multilingual Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#239), Llama 3.2 3B: 26.2 (#281)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Non-English11861019
LMArena Chinese12091017
LMArena German11921056
LMArena Russian1185949
LMArena French1238—
LMArena Japanese1154—
LMArena Korean1150—
LMArena Spanish1225—

Instruction Following Too close to call

Amazon Nova Micro: 56.3 (#272), Llama 3.2 3B: 56.0 (#275)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Instruction Following11741089
LiveBench Instruction Following48%—
IFEval76%—

Long Context Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#229), Llama 3.2 3B: 33.4 (#261)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Longer Query12051100

Writing & Preference Amazon Nova Micro leads

Amazon Nova Micro: 39.5 (#247), Llama 3.2 3B: 24.7 (#307)

BenchmarkAmazon Nova MicroLlama 3.2 3B
LMArena Text12081110
LMArena Creative Writing11721094
LMArena Multi-Turn11781105
EQ-Bench Creative Writing—595
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Llama 3.2 3B?

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 28.9 on the Noometry Index.

Which is cheaper, Amazon Nova Micro or Llama 3.2 3B?

Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

Is Amazon Nova Micro or Llama 3.2 3B better for coding?

Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 128K.

How many benchmarks do Amazon Nova Micro and Llama 3.2 3B share?

14 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Llama 3.2 3B has 18.

Related comparisons

Go deeper