Noometry

Model comparison

Amazon Nova Lite vs Gemma 3 27B

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 30.8 on the Noometry Index.

Last verified . 26 shared benchmarks.

Amazon Nova Lite Amazon

31.9

Rank #265 Confirmed

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Amazon Nova Lite scores higher in 5 categories and Gemma 3 27B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Gemma 3 27B leads 70.6 to 59.3.
  • The biggest single-benchmark swing is LiveBench Instruction Following: 54.1% for Amazon Nova Lite and 74.9% for Gemma 3 27B.
  • Both cost about the same: $0.06 input and $0.24 output per million tokens.
  • Amazon Nova Lite accepts more context: 300K tokens versus 131K.
  • Gemma 3 27B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova LiteGemma 3 27B
ProviderAmazonGoogle
Noometry Index31.930.8
Released2024-12-032025-03-11
WeightsProprietaryOpen
Context window300K131K
Max output10K8K
Input $ / M tokens$0.06$0.08
Output $ / M tokens$0.24$0.16
Results tracked3443

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 3 27B: 22.5 (#334)

BenchmarkAmazon Nova LiteGemma 3 27B
LiveBench Coding27.5%39.9%
LMArena Coding12391322
Aider Polyglot—4.9%
SciCode—21.2%
ALE-Bench236.25—

Agentic & Tool Use Not comparable

Amazon Nova Lite: —, Gemma 3 27B: 25.1 (#110)

BenchmarkAmazon Nova LiteGemma 3 27B
Berkeley Function Calling Leaderboard—29.5%

Reasoning Amazon Nova Lite leads

Amazon Nova Lite: 19.3 (#260), Gemma 3 27B: 16.7 (#301)

BenchmarkAmazon Nova LiteGemma 3 27B
LiveBench Reasoning36.7%43.8%
LMArena Hard Prompts12201340
LiveBench Data Analysis37.2%51.5%
LiveBench36.4%50%
Kagi LLM Benchmark—40.4%
CritPt—0%
Chess Puzzles—0%
DTBench—52.5%
LMCA—12.3%
Epoch Capabilities Index—130.04

Math Amazon Nova Lite leads

Amazon Nova Lite: 27.8 (#247), Gemma 3 27B: 25.9 (#265)

BenchmarkAmazon Nova LiteGemma 3 27B
LiveBench Math36.7%55.4%
LMArena Math12271312
OTIS Mock AIME 2024-2025—22.5%
Omni-MATH23.3%—
MATH Level 5—74%

Knowledge Too close to call

Amazon Nova Lite: 26.3 (#259), Gemma 3 27B: 25.5 (#261)

BenchmarkAmazon Nova LiteGemma 3 27B
Vectara Hallucination Rate6.1%7.4%
LMArena Expert12011304
GPQA Diamond—47.7%
Humanity's Last Exam3.6%—
MMLU-Pro60%—
Confabulations—40.3%
GPQA (HELM)39.7%—
MMLU77%—

Multimodal Gemma 3 27B leads

Amazon Nova Lite: 25.5 (#123), Gemma 3 27B: 32.6 (#100)

BenchmarkAmazon Nova LiteGemma 3 27B
LMArena Vision9901164
GeoBench—52%

Multilingual Gemma 3 27B leads

Amazon Nova Lite: 38.0 (#232), Gemma 3 27B: 46.9 (#155)

BenchmarkAmazon Nova LiteGemma 3 27B
LMArena Non-English12081334
LMArena Chinese12251346
LMArena French12371368
LMArena German12291362
LMArena Japanese11531287
LMArena Korean11531308
LMArena Russian12161349
LMArena Spanish12261349

Instruction Following Gemma 3 27B leads

Amazon Nova Lite: 59.3 (#255), Gemma 3 27B: 70.6 (#160)

BenchmarkAmazon Nova LiteGemma 3 27B
LiveBench Instruction Following54.1%74.9%
LMArena Instruction Following12051321
IFEval77.6%—

Long Context Amazon Nova Lite leads

Amazon Nova Lite: 37.4 (#217), Gemma 3 27B: 27.6 (#293)

BenchmarkAmazon Nova LiteGemma 3 27B
LMArena Longer Query12341333
Fiction.LiveBench—33.3%

Writing & Preference Gemma 3 27B leads

Amazon Nova Lite: 42.1 (#237), Gemma 3 27B: 52.5 (#168)

BenchmarkAmazon Nova LiteGemma 3 27B
LMArena Text12291358
LMArena Creative Writing11971346
LMArena Multi-Turn11991345
LiveBench Language25.9%34.6%
Short-Story Creative Writing—79.9%
EQ-Bench Creative Writing—1266
WildBench75%—

Frequently asked questions

Is Amazon Nova Lite better than Gemma 3 27B?

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 30.8 on the Noometry Index.

Which is cheaper, Amazon Nova Lite or Gemma 3 27B?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Amazon Nova Lite lists at $0.06 and $0.24.

Is Amazon Nova Lite or Gemma 3 27B better for coding?

Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 22.5 in the Noometry coding category.

Which has the bigger context window?

Amazon Nova Lite does, with 300K tokens against 131K.

How many benchmarks do Amazon Nova Lite and Gemma 3 27B share?

26 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Gemma 3 27B has 43.

Related comparisons

Go deeper