Model comparison

Amazon Nova Micro vs Gemma 2 9B

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 25.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Amazon Nova Micro scores higher in 6 categories and Gemma 2 9B in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Amazon Nova Micro leads 29.6 to 9.7.
  • The biggest single-benchmark swing is LiveBench Math: 34.5% for Amazon Nova Micro and 19.8% for Gemma 2 9B.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova Micro and Gemma 2 9B specifications
Amazon Nova MicroGemma 2 9B
ProviderAmazonGoogle
Noometry Index30.425.9
Released2024-12-032024-06-24
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3235

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), Gemma 2 9B: 29.4 (#304)

Coding benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LiveBench Coding20.2%22.5%
LMArena Coding12181173
BigCodeBench Instruct—34.7%
BigCodeBench Complete—40.6%

Agentic & Tool Use Not comparable

Amazon Nova Micro: 22.1 (#132), Gemma 2 9B: —

Agentic & Tool Use benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
Berkeley Function Calling Leaderboard22.3%—

Reasoning Amazon Nova Micro leads

Amazon Nova Micro: 17.4 (#294), Gemma 2 9B: 15.9 (#309)

Reasoning benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LiveBench Reasoning25.1%15.2%
LMArena Hard Prompts11911171
LiveBench Data Analysis34%36.4%
LiveBench29.6%28.7%
Epoch Capabilities Index—119.83
PIQA—83.7%

Math Amazon Nova Micro leads

Amazon Nova Micro: 26.9 (#254), Gemma 2 9B: 9.9 (#318)

Math benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LiveBench Math34.5%19.8%
LMArena Math12061183
OTIS Mock AIME 2024-2025—0.6%
Omni-MATH21.4%—
MATH Level 5—21%
GSM8K—84.9%

Knowledge Amazon Nova Micro leads

Amazon Nova Micro: 29.6 (#237), Gemma 2 9B: 9.7 (#305)

Knowledge benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LMArena Expert11841147
MMLU70.8%72.1%
GPQA Diamond—27.5%
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
BoolQ—85.7%

Multilingual Too close to call

Amazon Nova Micro: 36.5 (#239), Gemma 2 9B: 36.6 (#238)

Multilingual benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LMArena Non-English11861188
LMArena Chinese12091185
LMArena French12381190
LMArena German11921186
LMArena Japanese11541144
LMArena Korean11501137
LMArena Russian11851200
LMArena Spanish12251200

Instruction Following Gemma 2 9B leads

Amazon Nova Micro: 56.3 (#272), Gemma 2 9B: 57.6 (#269)

Instruction Following benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LiveBench Instruction Following48%52.6%
LMArena Instruction Following11741178
IFEval76%—

Long Context Too close to call

Amazon Nova Micro: 36.5 (#229), Gemma 2 9B: 36.3 (#233)

Long Context benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LMArena Longer Query12051197

Writing & Preference Amazon Nova Micro leads

Amazon Nova Micro: 39.5 (#247), Gemma 2 9B: 32.1 (#281)

Writing & Preference benchmarks
BenchmarkAmazon Nova MicroGemma 2 9B
LMArena Text12081207
LMArena Creative Writing11721206
LMArena Multi-Turn11781193
LiveBench Language15.8%25.5%
EQ-Bench Creative Writing—841
WildBench74.3%—

Frequently asked questions

Is Amazon Nova Micro better than Gemma 2 9B?

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 25.9 on the Noometry Index.

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

Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 29.4 in the Noometry coding category.

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

25 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Gemma 2 9B has 35.

Related comparisons

Go deeper