Model comparison

Amazon Nova Lite vs Codellama 70b Instruct

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.9 on the Noometry Index.

Last verified . 4 shared benchmarks.

Amazon Nova Lite Amazon

31.9

Rank #265 Confirmed

Codellama 70b Instruct Meta

33.7

Rank #237 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Amazon Nova Lite scores higher in 3 categories and Codellama 70b Instruct in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Amazon Nova Lite leads 38.0 to 24.8.
  • Codellama 70b Instruct has downloadable open weights; the other is API-only.

Side by side

Amazon Nova Lite and Codellama 70b Instruct specifications
Amazon Nova LiteCodellama 70b Instruct
ProviderAmazonMeta
Noometry Index31.933.7
Released2024-12-03—
WeightsProprietaryOpen
Context window300K—
Max output10K—
Input $ / M tokens$0.06—
Output $ / M tokens$0.24—
Results tracked347

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

Category by category

Coding Codellama 70b Instruct leads

Amazon Nova Lite: 32.5 (#270), Codellama 70b Instruct: 37.6 (#193)

Coding benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
BigCodeBench Instruct—40.7%
LiveBench Coding27.5%—
LMArena Coding1239—
BigCodeBench Complete—49.6%
ALE-Bench236.25—
HumanEval+—65.9%

Reasoning Too close to call

Amazon Nova Lite: 19.3 (#260), Codellama 70b Instruct: 20.1 (#242)

Reasoning benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
LMArena Hard Prompts12201052
LiveBench Reasoning36.7%—
LiveBench Data Analysis37.2%—
LiveBench36.4%—

Math Not comparable

Amazon Nova Lite: 27.8 (#247), Codellama 70b Instruct: —

Math benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
Omni-MATH23.3%—
LiveBench Math36.7%—
LMArena Math1227—

Knowledge Not comparable

Amazon Nova Lite: 26.3 (#259), Codellama 70b Instruct: —

Knowledge benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
Humanity's Last Exam3.6%—
MMLU-Pro60%—
Vectara Hallucination Rate6.1%—
GPQA (HELM)39.7%—
LMArena Expert1201—
MMLU77%—

Multimodal Not comparable

Amazon Nova Lite: 25.5 (#123), Codellama 70b Instruct: —

Multimodal benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
LMArena Vision990—

Multilingual Amazon Nova Lite leads

Amazon Nova Lite: 38.0 (#232), Codellama 70b Instruct: 24.8 (#288)

Multilingual benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
LMArena Non-English1208992
LMArena Chinese1225—
LMArena French1237—
LMArena German1229—
LMArena Japanese1153—
LMArena Korean1153—
LMArena Russian1216—
LMArena Spanish1226—

Instruction Following Amazon Nova Lite leads

Amazon Nova Lite: 59.3 (#255), Codellama 70b Instruct: 51.9 (#293)

Instruction Following benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
LMArena Instruction Following12051024
LiveBench Instruction Following54.1%—
IFEval77.6%—

Long Context Not comparable

Amazon Nova Lite: 37.4 (#217), Codellama 70b Instruct: —

Long Context benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
LMArena Longer Query1234—

Writing & Preference Amazon Nova Lite leads

Amazon Nova Lite: 42.1 (#237), Codellama 70b Instruct: 33.4 (#277)

Writing & Preference benchmarks
BenchmarkAmazon Nova LiteCodellama 70b Instruct
LMArena Text12291057
LMArena Creative Writing1197—
WildBench75%—
LMArena Multi-Turn1199—
LiveBench Language25.9%—

Frequently asked questions

Is Amazon Nova Lite better than Codellama 70b Instruct?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.9 on the Noometry Index.

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

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 32.5 in the Noometry coding category.

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

4 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Codellama 70b Instruct has 7.

Related comparisons

Go deeper