Model comparison

Amazon Nova Micro vs Codellama 70b Instruct

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.4 on the Noometry Index.

Last verified . 4 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Codellama 70b Instruct Meta

33.7

Rank #237 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Amazon Nova Micro scores higher in 3 categories and Codellama 70b Instruct in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Amazon Nova Micro leads 36.5 to 24.8.
  • Codellama 70b Instruct has downloadable open weights; the other is API-only.

Side by side

Amazon Nova Micro and Codellama 70b Instruct specifications
Amazon Nova MicroCodellama 70b Instruct
ProviderAmazonMeta
Noometry Index30.433.7
Released2024-12-03—
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked327

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

Category by category

Coding Codellama 70b Instruct leads

Amazon Nova Micro: 30.5 (#295), Codellama 70b Instruct: 37.6 (#193)

Coding benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
BigCodeBench Instruct—40.7%
LiveBench Coding20.2%—
LMArena Coding1218—
BigCodeBench Complete—49.6%
HumanEval+—65.9%

Agentic & Tool Use Not comparable

Amazon Nova Micro: 22.1 (#132), Codellama 70b Instruct: —

Agentic & Tool Use benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
Berkeley Function Calling Leaderboard22.3%—

Reasoning Codellama 70b Instruct leads

Amazon Nova Micro: 17.4 (#294), Codellama 70b Instruct: 20.1 (#242)

Reasoning benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
LMArena Hard Prompts11911052
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math Not comparable

Amazon Nova Micro: 26.9 (#254), Codellama 70b Instruct: —

Math benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
Omni-MATH21.4%—
LiveBench Math34.5%—
LMArena Math1206—

Knowledge Not comparable

Amazon Nova Micro: 29.6 (#237), Codellama 70b Instruct: —

Knowledge benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
LMArena Expert1184—
MMLU70.8%—

Multilingual Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#239), Codellama 70b Instruct: 24.8 (#288)

Multilingual benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
LMArena Non-English1186992
LMArena Chinese1209—
LMArena French1238—
LMArena German1192—
LMArena Japanese1154—
LMArena Korean1150—
LMArena Russian1185—
LMArena Spanish1225—

Instruction Following Amazon Nova Micro leads

Amazon Nova Micro: 56.3 (#272), Codellama 70b Instruct: 51.9 (#293)

Instruction Following benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
LMArena Instruction Following11741024
LiveBench Instruction Following48%—
IFEval76%—

Long Context Not comparable

Amazon Nova Micro: 36.5 (#229), Codellama 70b Instruct: —

Long Context benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
LMArena Longer Query1205—

Writing & Preference Amazon Nova Micro leads

Amazon Nova Micro: 39.5 (#247), Codellama 70b Instruct: 33.4 (#277)

Writing & Preference benchmarks
BenchmarkAmazon Nova MicroCodellama 70b Instruct
LMArena Text12081057
LMArena Creative Writing1172—
WildBench74.3%—
LMArena Multi-Turn1178—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Codellama 70b Instruct?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.4 on the Noometry Index.

Is Amazon Nova Micro or Codellama 70b Instruct better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 30.5 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Codellama 70b Instruct share?

4 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Codellama 70b Instruct has 7.

Related comparisons

Go deeper