Noometry

Model comparison

Gemma 3 12B vs Nova Premier 1.0

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 32.1 on the Noometry Index. Gemma 3 12B costs 67× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Nova Premier 1.0 Amazon

38.3

Rank #189 Confirmed

Summary

  • The widest gap is in math, where Nova Premier 1.0 leads 33.8 to 22.3.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
  • Nova Premier 1.0 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 Premier 1.0
ProviderGoogleAmazon
Noometry Index32.138.3
Released2025-03-122025-04-30
WeightsOpenProprietary
Context window131K1M
Max output8K10K
Input $ / M tokens$0.05$2.50
Output $ / M tokens$0.15$12.50
Results tracked246

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

Category by category

Coding Not comparable

Gemma 3 12B: 31.7 (#280), Nova Premier 1.0: —

BenchmarkGemma 3 12BNova Premier 1.0
SciCode17.4%—
LMArena Coding1281—

Agentic & Tool Use Not comparable

Gemma 3 12B: 25.5 (#108), Nova Premier 1.0: —

BenchmarkGemma 3 12BNova Premier 1.0
Berkeley Function Calling Leaderboard30.4%—

Reasoning Nova Premier 1.0 leads

Gemma 3 12B: 15.7 (#313), Nova Premier 1.0: 23.0 (#185)

BenchmarkGemma 3 12BNova Premier 1.0
Kagi LLM Benchmark—44.8%
CritPt0%—
Chess Puzzles0%—
LMArena Hard Prompts1309—
DTBench48.8%—
LMCA4.5%—
Epoch Capabilities Index123.5—

Math Nova Premier 1.0 leads

Gemma 3 12B: 22.3 (#279), Nova Premier 1.0: 33.8 (#199)

BenchmarkGemma 3 12BNova Premier 1.0
OTIS Mock AIME 2024-202516.7%—
Omni-MATH—35%
LMArena Math1307—

Knowledge Nova Premier 1.0 leads

Gemma 3 12B: 26.5 (#257), Nova Premier 1.0: 35.8 (#180)

BenchmarkGemma 3 12BNova Premier 1.0
GPQA Diamond39.5%—
MMLU-Pro—72.6%
Vectara Hallucination Rate4.4%—
GPQA (HELM)—51.8%
LMArena Expert1248—

Multimodal Not comparable

Gemma 3 12B: —, Nova Premier 1.0: —

BenchmarkGemma 3 12BNova Premier 1.0
MindCube46.7%—

Multilingual Not comparable

Gemma 3 12B: 45.7 (#165), Nova Premier 1.0: —

BenchmarkGemma 3 12BNova Premier 1.0
LMArena Non-English1318—
LMArena German1370—
LMArena Russian1335—

Instruction Following Gemma 3 12B leads

Gemma 3 12B: 68.6 (#186), Nova Premier 1.0: 66.8 (#204)

BenchmarkGemma 3 12BNova Premier 1.0
IFEval—80.3%
LMArena Instruction Following1299—

Long Context Not comparable

Gemma 3 12B: 40.0 (#162), Nova Premier 1.0: —

BenchmarkGemma 3 12BNova Premier 1.0
LMArena Longer Query1317—

Writing & Preference Nova Premier 1.0 leads

Gemma 3 12B: 47.5 (#209), Nova Premier 1.0: 51.0 (#178)

BenchmarkGemma 3 12BNova Premier 1.0
LMArena Text1334—
LMArena Creative Writing1331—
EQ-Bench Creative Writing1126—
WildBench—78.8%
LMArena Multi-Turn1334—

Frequently asked questions

Is Gemma 3 12B better than Nova Premier 1.0?

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 32.1 on the Noometry Index. Gemma 3 12B costs 67× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 12B or Nova Premier 1.0?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.

Which has the bigger context window?

Nova Premier 1.0 does, with 1M tokens against 131K.

How many benchmarks do Gemma 3 12B and Nova Premier 1.0 share?

0 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper