Noometry

Model comparison

Amazon Nova Micro vs Llama 3-70B

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 28.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 5 categories and Llama 3-70B in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Amazon Nova Micro leads 26.9 to 12.8.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroLlama 3-70B
ProviderAmazonMeta
Noometry Index30.428.8
Released2024-12-032024-04-18
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3231

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

Category by category

Coding Llama 3-70B leads

Amazon Nova Micro: 30.5 (#295), Llama 3-70B: 35.8 (#218)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Coding12181206
BigCodeBench Instruct—43.6%
LiveBench Coding20.2%—
BigCodeBench Complete—54.5%
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use Too close to call

Amazon Nova Micro: 22.1 (#132), Llama 3-70B: 21.1 (#139)

BenchmarkAmazon Nova MicroLlama 3-70B
Berkeley Function Calling Leaderboard22.3%—
Cybench—5%

Reasoning Too close to call

Amazon Nova Micro: 17.4 (#294), Llama 3-70B: 18.0 (#288)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Hard Prompts11911195
Kagi LLM Benchmark—35.1%
LiveBench Reasoning25.1%—
DTBench—54.2%
LiveBench Data Analysis34%—
Epoch Capabilities Index—122.93
ForecastBench—57.1
LiveBench29.6%—
WinoGrande—83.5%

Math Amazon Nova Micro leads

Amazon Nova Micro: 26.9 (#254), Llama 3-70B: 12.8 (#305)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Math12061218
OTIS Mock AIME 2024-2025—4.3%
Omni-MATH21.4%—
LiveBench Math34.5%—
MATH Level 5—22.6%

Knowledge Amazon Nova Micro leads

Amazon Nova Micro: 29.6 (#237), Llama 3-70B: 20.8 (#277)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Expert11841149
MMLU70.8%79.3%
GPQA Diamond—40.6%
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—

Multilingual Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#239), Llama 3-70B: 33.6 (#251)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Non-English11861142
LMArena Chinese12091114
LMArena French12381232
LMArena German11921169
LMArena Japanese11541017
LMArena Korean11501017
LMArena Russian11851159
LMArena Spanish12251241

Instruction Following Llama 3-70B leads

Amazon Nova Micro: 56.3 (#272), Llama 3-70B: 62.5 (#238)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Instruction Following11741194
LiveBench Instruction Following48%—
IFEval76%—

Long Context Too close to call

Amazon Nova Micro: 36.5 (#229), Llama 3-70B: 35.6 (#240)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Longer Query12051174

Writing & Preference Llama 3-70B leads

Amazon Nova Micro: 39.5 (#247), Llama 3-70B: 42.8 (#231)

BenchmarkAmazon Nova MicroLlama 3-70B
LMArena Text12081221
LMArena Creative Writing11721210
LMArena Multi-Turn11781223
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Llama 3-70B?

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 28.8 on the Noometry Index.

Is Amazon Nova Micro or Llama 3-70B better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.8 versus 30.5 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Llama 3-70B share?

18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper