Noometry

Model comparison

Gemma 4 31B IT vs Nova Premier 1.0

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 37.7 on the Noometry Index.

Last verified . 1 shared benchmarks.

Gemma 4 31B IT Google

43.2

Rank #85 Confirmed

Nova Premier 1.0 Amazon

37.7

Rank #185 Confirmed

Summary

  • They share 1 benchmark with published results for both. Gemma 4 31B IT scores higher in 5 categories and Nova Premier 1.0 in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 31.5.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 44.8% for Nova Premier 1.0.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 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 262K.
  • Gemma 4 31B IT has downloadable open weights; the other is API-only.

Side by side

Gemma 4 31B ITNova Premier 1.0
ProviderGoogleAmazon
Noometry Index43.237.7
Released2026-04-022025-04-30
WeightsOpenProprietary
Context window262K1M
Max output33K10K
Input $ / M tokens$0.09$2.50
Output $ / M tokens$0.34$12.50
Results tracked356

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

Category by category

Coding Not comparable

Gemma 4 31B IT: 41.9 (#98), Nova Premier 1.0: —

BenchmarkGemma 4 31B ITNova Premier 1.0
LMArena WebDev1364—
SciCode43.4%—
WeirdML52.3%—
LMArena Coding1459—
ALE-Bench925.5—

Reasoning Gemma 4 31B IT leads

Gemma 4 31B IT: 26.4 (#119), Nova Premier 1.0: 22.3 (#182)

BenchmarkGemma 4 31B ITNova Premier 1.0
Kagi LLM Benchmark63.5%44.8%
NYT Connections (extended)70.6%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
LMArena Hard Prompts1448—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Gemma 4 31B IT leads

Gemma 4 31B IT: 41.3 (#72), Nova Premier 1.0: 31.5 (#194)

BenchmarkGemma 4 31B ITNova Premier 1.0
OTIS Mock AIME 2024-202573.3%—
Omni-MATH—35%
LMArena Math1464—

Knowledge Gemma 4 31B IT leads

Gemma 4 31B IT: 37.9 (#141), Nova Premier 1.0: 35.4 (#176)

BenchmarkGemma 4 31B ITNova Premier 1.0
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
MMLU-Pro—72.6%
Vectara Hallucination Rate7.4%—
GPQA (HELM)—51.8%
LMArena Expert1465—

Multimodal Not comparable

Gemma 4 31B IT: 41.0 (#32), Nova Premier 1.0: —

BenchmarkGemma 4 31B ITNova Premier 1.0
LMArena Vision1278—
LMArena Document1425—

Multilingual Not comparable

Gemma 4 31B IT: 54.0 (#52), Nova Premier 1.0: —

BenchmarkGemma 4 31B ITNova Premier 1.0
LMArena Non-English1431—
LMArena Chinese1478—
LMArena French1436—
LMArena Russian1462—
LMArena Spanish1443—

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.6 (#58), Nova Premier 1.0: 66.9 (#201)

BenchmarkGemma 4 31B ITNova Premier 1.0
IFEval—80.3%
LMArena Instruction Following1433—

Long Context Not comparable

Gemma 4 31B IT: 44.2 (#67), Nova Premier 1.0: —

BenchmarkGemma 4 31B ITNova Premier 1.0
LMArena Longer Query1446—

Writing & Preference Gemma 4 31B IT leads

Gemma 4 31B IT: 60.7 (#92), Nova Premier 1.0: 51.0 (#174)

BenchmarkGemma 4 31B ITNova Premier 1.0
LMArena Text1443—
LMArena Creative Writing1416—
EQ-Bench Creative Writing1368—
WildBench—78.8%
EQ-Bench 41120—
LMArena Multi-Turn1452—

Frequently asked questions

Is Gemma 4 31B IT better than Nova Premier 1.0?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 37.7 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or Nova Premier 1.0?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 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 262K.

How many benchmarks do Gemma 4 31B IT and Nova Premier 1.0 share?

1 benchmark has published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper