Noometry

Model comparison

Gemma 2 27B vs Nova 2 Lite

Nova 2 Lite is the stronger model overall, scoring 39.7 to 29.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Nova 2 Lite Amazon

39.7

Rank #161 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Nova 2 Lite in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Nova 2 Lite leads 37.5 to 10.7.
  • Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
  • Nova 2 Lite 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 2 Lite
ProviderGoogleAmazon
Noometry Index29.439.7
Released2024-06-242025-12-01
WeightsOpenProprietary
Context window8K1M
Max output2K64K
Input $ / M tokens$0.65$0.30
Output $ / M tokens$0.65$2.50
Results tracked3419

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

Category by category

Coding Nova 2 Lite leads

Gemma 2 27B: 34.1 (#246), Nova 2 Lite: 40.7 (#134)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Coding12111385
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—

Agentic & Tool Use Not comparable

Gemma 2 27B: —, Nova 2 Lite: 24.1 (#121)

BenchmarkGemma 2 27BNova 2 Lite
Berkeley Function Calling Leaderboard—27.1%

Reasoning Nova 2 Lite leads

Gemma 2 27B: 15.3 (#315), Nova 2 Lite: 27.5 (#118)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Hard Prompts11981364
LiveBench Reasoning28.1%—
DTBench48%—
LiveBench Data Analysis47.9%—
LMCA7.1%—
Epoch Capabilities Index122.08—
LiveBench38.2%—

Math Nova 2 Lite leads

Gemma 2 27B: 10.7 (#311), Nova 2 Lite: 37.5 (#156)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Math12121359
OTIS Mock AIME 2024-20251.4%—
LiveBench Math26.5%—
MATH Level 527.9%—

Knowledge Nova 2 Lite leads

Gemma 2 27B: 19.0 (#280), Nova 2 Lite: 43.0 (#94)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Expert11721358
GPQA Diamond36.5%—
Confabulations27.1%—
Vectara Hallucination Rate—5.1%
MMLU75.7%—

Multilingual Nova 2 Lite leads

Gemma 2 27B: 38.6 (#226), Nova 2 Lite: 47.1 (#153)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Non-English12171337
LMArena Chinese12211364
LMArena French12471381
LMArena German12091343
LMArena Japanese11751271
LMArena Korean11741284
LMArena Russian12341343
LMArena Spanish12281373

Instruction Following Nova 2 Lite leads

Gemma 2 27B: 60.5 (#249), Nova 2 Lite: 70.5 (#161)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Instruction Following12061335
LiveBench Instruction Following58.1%—

Long Context Nova 2 Lite leads

Gemma 2 27B: 37.3 (#218), Nova 2 Lite: 40.6 (#150)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Longer Query12311335

Writing & Preference Nova 2 Lite leads

Gemma 2 27B: 44.2 (#225), Nova 2 Lite: 53.9 (#154)

BenchmarkGemma 2 27BNova 2 Lite
LMArena Text12311362
LMArena Creative Writing12411291
LMArena Multi-Turn12241338
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.7 to 29.4 on the Noometry Index.

Which is cheaper, Gemma 2 27B or Nova 2 Lite?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.

Is Gemma 2 27B or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 8K.

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

17 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Nova 2 Lite has 19.

Related comparisons

Go deeper