Noometry

Model comparison

Gemma 2 27B vs Nova Premier 1.0

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 29.4 on the Noometry Index. Gemma 2 27B costs 7.7× 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 2 27B Google

29.4

Rank #312 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 10.7.
  • Gemma 2 27B is cheaper at $0.65 / $0.65 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 8K.
  • Gemma 2 27B has downloadable open weights; the other is API-only.

Side by side

Gemma 2 27BNova Premier 1.0
ProviderGoogleAmazon
Noometry Index29.438.3
Released2024-06-242025-04-30
WeightsOpenProprietary
Context window8K1M
Max output2K10K
Input $ / M tokens$0.65$2.50
Output $ / M tokens$0.65$12.50
Results tracked346

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

Category by category

Coding Not comparable

Gemma 2 27B: 34.1 (#246), Nova Premier 1.0: —

BenchmarkGemma 2 27BNova Premier 1.0
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
LMArena Coding1211—
BigCodeBench Complete52.5%—

Reasoning Nova Premier 1.0 leads

Gemma 2 27B: 15.3 (#315), Nova Premier 1.0: 23.0 (#185)

BenchmarkGemma 2 27BNova Premier 1.0
Kagi LLM Benchmark—44.8%
LiveBench Reasoning28.1%—
LMArena Hard Prompts1198—
DTBench48%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
Epoch Capabilities Index122.08—
LiveBench38.2%—

Math Nova Premier 1.0 leads

Gemma 2 27B: 10.7 (#311), Nova Premier 1.0: 33.8 (#199)

BenchmarkGemma 2 27BNova Premier 1.0
OTIS Mock AIME 2024-20251.4%—
Omni-MATH—35%
LiveBench Math26.5%—
LMArena Math1212—
MATH Level 527.9%—

Knowledge Nova Premier 1.0 leads

Gemma 2 27B: 19.0 (#280), Nova Premier 1.0: 35.8 (#180)

BenchmarkGemma 2 27BNova Premier 1.0
GPQA Diamond36.5%—
MMLU-Pro—72.6%
Confabulations27.1%—
GPQA (HELM)—51.8%
LMArena Expert1172—
MMLU75.7%—

Multilingual Not comparable

Gemma 2 27B: 38.6 (#226), Nova Premier 1.0: —

BenchmarkGemma 2 27BNova Premier 1.0
LMArena Non-English1217—
LMArena Chinese1221—
LMArena French1247—
LMArena German1209—
LMArena Japanese1175—
LMArena Korean1174—
LMArena Russian1234—
LMArena Spanish1228—

Instruction Following Nova Premier 1.0 leads

Gemma 2 27B: 60.5 (#249), Nova Premier 1.0: 66.8 (#204)

BenchmarkGemma 2 27BNova Premier 1.0
LiveBench Instruction Following58.1%—
IFEval—80.3%
LMArena Instruction Following1206—

Long Context Not comparable

Gemma 2 27B: 37.3 (#218), Nova Premier 1.0: —

BenchmarkGemma 2 27BNova Premier 1.0
LMArena Longer Query1231—

Writing & Preference Nova Premier 1.0 leads

Gemma 2 27B: 44.2 (#225), Nova Premier 1.0: 51.0 (#178)

BenchmarkGemma 2 27BNova Premier 1.0
LMArena Text1231—
LMArena Creative Writing1241—
WildBench—78.8%
LMArena Multi-Turn1224—
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than Nova Premier 1.0?

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 29.4 on the Noometry Index. Gemma 2 27B costs 7.7× 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 2 27B or Nova Premier 1.0?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 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 8K.

How many benchmarks do Gemma 2 27B and Nova Premier 1.0 share?

0 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper