Noometry

Model comparison

Amazon Nova Lite vs Gemma 2 9B

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 25.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Amazon Nova Lite Amazon

31.9

Rank #265 Confirmed

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Amazon Nova Lite scores higher in 8 categories and Gemma 2 9B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Amazon Nova Lite leads 27.8 to 9.9.
  • The biggest single-benchmark swing is LiveBench Reasoning: 36.7% for Amazon Nova Lite and 15.2% for Gemma 2 9B.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova LiteGemma 2 9B
ProviderAmazonGoogle
Noometry Index31.925.9
Released2024-12-032024-06-24
WeightsProprietaryOpen
Context window300K—
Max output10K—
Input $ / M tokens$0.06—
Output $ / M tokens$0.24—
Results tracked3435

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

Category by category

Coding Amazon Nova Lite leads

Amazon Nova Lite: 32.5 (#270), Gemma 2 9B: 29.4 (#304)

BenchmarkAmazon Nova LiteGemma 2 9B
LiveBench Coding27.5%22.5%
LMArena Coding12391173
BigCodeBench Instruct—34.7%
BigCodeBench Complete—40.6%
ALE-Bench236.25—

Reasoning Amazon Nova Lite leads

Amazon Nova Lite: 19.3 (#260), Gemma 2 9B: 15.9 (#309)

BenchmarkAmazon Nova LiteGemma 2 9B
LiveBench Reasoning36.7%15.2%
LMArena Hard Prompts12201171
LiveBench Data Analysis37.2%36.4%
LiveBench36.4%28.7%
Epoch Capabilities Index—119.83
PIQA—83.7%

Math Amazon Nova Lite leads

Amazon Nova Lite: 27.8 (#247), Gemma 2 9B: 9.9 (#318)

BenchmarkAmazon Nova LiteGemma 2 9B
LiveBench Math36.7%19.8%
LMArena Math12271183
OTIS Mock AIME 2024-2025—0.6%
Omni-MATH23.3%—
MATH Level 5—21%
GSM8K—84.9%

Knowledge Amazon Nova Lite leads

Amazon Nova Lite: 26.3 (#259), Gemma 2 9B: 9.7 (#305)

BenchmarkAmazon Nova LiteGemma 2 9B
LMArena Expert12011147
MMLU77%72.1%
GPQA Diamond—27.5%
Humanity's Last Exam3.6%—
MMLU-Pro60%—
Vectara Hallucination Rate6.1%—
GPQA (HELM)39.7%—
BoolQ—85.7%

Multimodal Not comparable

Amazon Nova Lite: 25.5 (#123), Gemma 2 9B: —

BenchmarkAmazon Nova LiteGemma 2 9B
LMArena Vision990—

Multilingual Amazon Nova Lite leads

Amazon Nova Lite: 38.0 (#232), Gemma 2 9B: 36.6 (#238)

BenchmarkAmazon Nova LiteGemma 2 9B
LMArena Non-English12081188
LMArena Chinese12251185
LMArena French12371190
LMArena German12291186
LMArena Japanese11531144
LMArena Korean11531137
LMArena Russian12161200
LMArena Spanish12261200

Instruction Following Amazon Nova Lite leads

Amazon Nova Lite: 59.3 (#255), Gemma 2 9B: 57.6 (#269)

BenchmarkAmazon Nova LiteGemma 2 9B
LiveBench Instruction Following54.1%52.6%
LMArena Instruction Following12051178
IFEval77.6%—

Long Context Amazon Nova Lite leads

Amazon Nova Lite: 37.4 (#217), Gemma 2 9B: 36.3 (#233)

BenchmarkAmazon Nova LiteGemma 2 9B
LMArena Longer Query12341197

Writing & Preference Amazon Nova Lite leads

Amazon Nova Lite: 42.1 (#237), Gemma 2 9B: 32.1 (#281)

BenchmarkAmazon Nova LiteGemma 2 9B
LMArena Text12291207
LMArena Creative Writing11971206
LMArena Multi-Turn11991193
LiveBench Language25.9%25.5%
EQ-Bench Creative Writing—841
WildBench75%—

Frequently asked questions

Is Amazon Nova Lite better than Gemma 2 9B?

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 25.9 on the Noometry Index.

Is Amazon Nova Lite or Gemma 2 9B better for coding?

Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 29.4 in the Noometry coding category.

How many benchmarks do Amazon Nova Lite and Gemma 2 9B share?

25 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Gemma 2 9B has 35.

Related comparisons

Go deeper