Noometry

Model comparison

Gemma 3 4B vs Nova 2 Lite

Nova 2 Lite is the stronger model overall, scoring 39.7 to 28.1 on the Noometry Index. Gemma 3 4B costs 17× 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 4B Google

28.1

Rank #326 Confirmed

Nova 2 Lite Amazon

39.7

Rank #161 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Nova 2 Lite in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nova 2 Lite leads 43.0 to 11.8.
  • The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 19.6% for Gemma 3 4B and 27.1% for Nova 2 Lite.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 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 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4BNova 2 Lite
ProviderGoogleAmazon
Noometry Index28.139.7
Released2025-03-122025-12-01
WeightsOpenProprietary
Context window131K1M
Max output4K64K
Input $ / M tokens$0.04$0.30
Output $ / M tokens$0.08$2.50
Results tracked2219

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

Category by category

Coding Nova 2 Lite leads

Gemma 3 4B: 35.9 (#215), Nova 2 Lite: 40.7 (#134)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Coding12301385

Agentic & Tool Use Nova 2 Lite leads

Gemma 3 4B: 20.9 (#142), Nova 2 Lite: 24.1 (#121)

BenchmarkGemma 3 4BNova 2 Lite
Berkeley Function Calling Leaderboard19.6%27.1%

Reasoning Nova 2 Lite leads

Gemma 3 4B: 13.2 (#335), Nova 2 Lite: 27.5 (#118)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Hard Prompts12531364
Kagi LLM Benchmark25.2%—
Chess Puzzles0%—
DTBench50.9%—
LMCA2.8%—
Epoch Capabilities Index116.02—

Math Nova 2 Lite leads

Gemma 3 4B: 16.8 (#292), Nova 2 Lite: 37.5 (#156)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Math12391359
OTIS Mock AIME 2024-20257.5%—

Knowledge Nova 2 Lite leads

Gemma 3 4B: 11.8 (#299), Nova 2 Lite: 43.0 (#94)

BenchmarkGemma 3 4BNova 2 Lite
Vectara Hallucination Rate6.4%5.1%
LMArena Expert12231358
GPQA Diamond23.2%—

Multilingual Nova 2 Lite leads

Gemma 3 4B: 42.5 (#194), Nova 2 Lite: 47.1 (#153)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Non-English12731337
LMArena German12811343
LMArena Russian12941343
LMArena Chinese—1364
LMArena French—1381
LMArena Japanese—1271
LMArena Korean—1284
LMArena Spanish—1373

Instruction Following Nova 2 Lite leads

Gemma 3 4B: 65.2 (#225), Nova 2 Lite: 70.5 (#161)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Instruction Following12391335

Long Context Nova 2 Lite leads

Gemma 3 4B: 38.7 (#194), Nova 2 Lite: 40.6 (#150)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Longer Query12731335

Writing & Preference Nova 2 Lite leads

Gemma 3 4B: 42.0 (#239), Nova 2 Lite: 53.9 (#154)

BenchmarkGemma 3 4BNova 2 Lite
LMArena Text12911362
LMArena Creative Writing12711291
LMArena Multi-Turn12551338
EQ-Bench Creative Writing1068—

Frequently asked questions

Is Gemma 3 4B better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.7 to 28.1 on the Noometry Index. Gemma 3 4B costs 17× 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 4B or Nova 2 Lite?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.

Is Gemma 3 4B or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 35.9 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 4B and Nova 2 Lite share?

14 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Nova 2 Lite has 19.

Related comparisons

Go deeper