Noometry

Model comparison

Gemma 4 31B IT vs Hy4 preview

Hy4 preview is the stronger model overall, scoring 45.3 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 7.4× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

Last verified . 2 shared benchmarks.

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

Hy4 preview Tencent

45.3

Rank #73 Reported

Summary

  • They share 2 benchmarks with published results for both. Gemma 4 31B IT scores higher in 0 categories and Hy4 preview in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hy4 preview leads 55.7 to 43.2.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.75 / $2.25 for Hy4 preview.
  • Hy4 preview accepts more context: 1.05M tokens versus 262K.

Side by side

Gemma 4 31B ITHy4 preview
ProviderGoogleTencent
Noometry Index43.545.3
Released2026-04-022026-08-28
WeightsOpenOpen
Context window262K1.05M
Max output33K64K
Input $ / M tokens$0.09$0.75
Output $ / M tokens$0.34$2.25
Results tracked353

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

Category by category

Coding Hy4 preview leads

Gemma 4 31B IT: 42.3 (#108), Hy4 preview: 51.6 (#38)

BenchmarkGemma 4 31B ITHy4 preview
LMArena WebDev13661632
SciCode43.4%—
WeirdML52.3%—
LMArena Coding1459—
ALE-Bench925.5—

Reasoning Hy4 preview leads

Gemma 4 31B IT: 27.2 (#122), Hy4 preview: 31.9 (#79)

BenchmarkGemma 4 31B ITHy4 preview
NYT Connections (extended)70.6%68.2%
Kagi LLM Benchmark63.5%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
LMArena Hard Prompts1448—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Hy4 preview leads

Gemma 4 31B IT: 43.2 (#81), Hy4 preview: 55.7 (#42)

BenchmarkGemma 4 31B ITHy4 preview
OTIS Mock AIME 2024-202573.3%—
ProofBench—75%
LMArena Math1465—

Knowledge Not comparable

Gemma 4 31B IT: 37.9 (#151), Hy4 preview: —

BenchmarkGemma 4 31B ITHy4 preview
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—
LMArena Expert1465—

Multimodal Not comparable

Gemma 4 31B IT: 41.6 (#34), Hy4 preview: —

BenchmarkGemma 4 31B ITHy4 preview
LMArena Vision1277—
LMArena Document1425—

Multilingual Not comparable

Gemma 4 31B IT: 53.8 (#57), Hy4 preview: —

BenchmarkGemma 4 31B ITHy4 preview
LMArena Non-English1431—
LMArena Chinese1476—
LMArena French1435—
LMArena Russian1460—
LMArena Spanish1444—

Instruction Following Not comparable

Gemma 4 31B IT: 75.5 (#61), Hy4 preview: —

BenchmarkGemma 4 31B ITHy4 preview
LMArena Instruction Following1433—

Long Context Not comparable

Gemma 4 31B IT: 44.2 (#71), Hy4 preview: —

BenchmarkGemma 4 31B ITHy4 preview
LMArena Longer Query1446—

Writing & Preference Not comparable

Gemma 4 31B IT: 60.5 (#96), Hy4 preview: —

BenchmarkGemma 4 31B ITHy4 preview
LMArena Text1443—
LMArena Creative Writing1415—
EQ-Bench Creative Writing1368—
EQ-Bench 41120—
LMArena Multi-Turn1452—

Frequently asked questions

Is Gemma 4 31B IT better than Hy4 preview?

Hy4 preview is the stronger model overall, scoring 45.3 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 7.4× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

Which is cheaper, Gemma 4 31B IT or Hy4 preview?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Hy4 preview lists at $0.75 and $2.25.

Is Gemma 4 31B IT or Hy4 preview better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.3 in the Noometry coding category.

Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 262K.

How many benchmarks do Gemma 4 31B IT and Hy4 preview share?

2 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Hy4 preview has 3.

Related comparisons

Go deeper