Noometry

Model comparison

Gemma 3 12B vs Nova 2 Lite

Nova 2 Lite is the stronger model overall, scoring 39.0 to 31.8 on the Noometry Index. Gemma 3 12B costs 11× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

Last verified . 14 shared benchmarks.

Gemma 3 12B Google

31.8

Rank #255 Confirmed

Nova 2 Lite Amazon

39.0

Rank #161 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Nova 2 Lite in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nova 2 Lite leads 42.5 to 26.5.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
  • Nova 2 Lite accepts more context: 1M tokens versus 131K.
  • Gemma 3 12B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 12BNova 2 Lite
ProviderGoogleAmazon
Noometry Index31.839.0
Released2025-03-122025-12-01
WeightsOpenProprietary
Context window131K1M
Max output8K64K
Input $ / M tokens$0.05$0.30
Output $ / M tokens$0.15$2.50
Results tracked2419

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

Category by category

Coding Nova 2 Lite leads

Gemma 3 12B: 31.2 (#276), Nova 2 Lite: 40.1 (#131)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Coding12811386
SciCode17.4%—

Agentic & Tool Use Gemma 3 12B leads

Gemma 3 12B: 25.3 (#101), Nova 2 Lite: 23.9 (#114)

BenchmarkGemma 3 12BNova 2 Lite
Berkeley Function Calling Leaderboard30.4%27.1%

Reasoning Nova 2 Lite leads

Gemma 3 12B: 15.2 (#307), Nova 2 Lite: 26.4 (#120)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Hard Prompts13091364
CritPt0%—
Chess Puzzles0%—
DTBench48.8%—
LMCA4.5%—
Epoch Capabilities Index123.49—

Math Nova 2 Lite leads

Gemma 3 12B: 21.0 (#273), Nova 2 Lite: 34.8 (#154)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Math13071359
OTIS Mock AIME 2024-202516.7%—

Knowledge Nova 2 Lite leads

Gemma 3 12B: 26.5 (#250), Nova 2 Lite: 42.5 (#88)

BenchmarkGemma 3 12BNova 2 Lite
Vectara Hallucination Rate4.4%5.1%
LMArena Expert12481360
GPQA Diamond39.5%—

Multimodal Not comparable

Gemma 3 12B: —, Nova 2 Lite: —

BenchmarkGemma 3 12BNova 2 Lite
MindCube46.7%—

Multilingual Nova 2 Lite leads

Gemma 3 12B: 45.9 (#160), Nova 2 Lite: 47.3 (#148)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Non-English13181337
LMArena German13701343
LMArena Russian13351343
LMArena Chinese—1364
LMArena French—1381
LMArena Japanese—1273
LMArena Korean—1284
LMArena Spanish—1372

Instruction Following Nova 2 Lite leads

Gemma 3 12B: 68.8 (#179), Nova 2 Lite: 70.7 (#156)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Instruction Following12991335

Long Context Too close to call

Gemma 3 12B: 40.0 (#157), Nova 2 Lite: 40.6 (#145)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Longer Query13171335

Writing & Preference Nova 2 Lite leads

Gemma 3 12B: 47.7 (#205), Nova 2 Lite: 54.1 (#150)

BenchmarkGemma 3 12BNova 2 Lite
LMArena Text13341362
LMArena Creative Writing13311291
LMArena Multi-Turn13341338
EQ-Bench Creative Writing1126—

Frequently asked questions

Is Gemma 3 12B better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.0 to 31.8 on the Noometry Index. Gemma 3 12B costs 11× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 12B or Nova 2 Lite?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.

Is Gemma 3 12B or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 131K.

How many benchmarks do Gemma 3 12B and Nova 2 Lite share?

14 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Nova 2 Lite has 19.

Related comparisons

Go deeper