Model comparison

Gemma 2 2b IT vs Hy4 preview

Hy4 preview is the stronger model overall, scoring 44.6 to 32.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

Gemma 2 2b IT Google

32.5

Rank #244 Confirmed

Hy4 preview Tencent

44.6

Rank #73 Reported

Summary

  • The widest gap is in math, where Hy4 preview leads 54.5 to 30.1.

Side by side

Gemma 2 2b IT and Hy4 preview specifications
Gemma 2 2b ITHy4 preview
ProviderGoogleTencent
Noometry Index32.544.6
Released—2026-08-28
WeightsOpenOpen
Context window—1.05M
Max output—64K
Input $ / M tokens—$0.83
Output $ / M tokens—$2.50
Results tracked173

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

Category by category

Coding Hy4 preview leads

Gemma 2 2b IT: 31.8 (#268), Hy4 preview: 51.4 (#36)

Coding benchmarks
BenchmarkGemma 2 2b ITHy4 preview
LMArena WebDev—1633
LMArena Coding1112—

Reasoning Hy4 preview leads

Gemma 2 2b IT: 20.5 (#219), Hy4 preview: 30.6 (#75)

Reasoning benchmarks
BenchmarkGemma 2 2b ITHy4 preview
NYT Connections (extended)—68.2%
LMArena Hard Prompts1113—

Math Hy4 preview leads

Gemma 2 2b IT: 30.1 (#212), Hy4 preview: 54.5 (#37)

Math benchmarks
BenchmarkGemma 2 2b ITHy4 preview
ProofBench—75%
LMArena Math1135—

Knowledge Not comparable

Gemma 2 2b IT: 29.3 (#229), Hy4 preview: —

Knowledge benchmarks
BenchmarkGemma 2 2b ITHy4 preview
LMArena Expert1096—

Multilingual Not comparable

Gemma 2 2b IT: 32.5 (#252), Hy4 preview: —

Multilingual benchmarks
BenchmarkGemma 2 2b ITHy4 preview
LMArena Non-English1121—
LMArena Chinese1132—
LMArena French1156—
LMArena German1114—
LMArena Japanese1083—
LMArena Korean1055—
LMArena Russian1118—
LMArena Spanish1140—

Instruction Following Not comparable

Gemma 2 2b IT: 58.1 (#258), Hy4 preview: —

Instruction Following benchmarks
BenchmarkGemma 2 2b ITHy4 preview
LMArena Instruction Following1118—

Long Context Not comparable

Gemma 2 2b IT: 34.2 (#245), Hy4 preview: —

Long Context benchmarks
BenchmarkGemma 2 2b ITHy4 preview
LMArena Longer Query1130—

Writing & Preference Not comparable

Gemma 2 2b IT: 36.6 (#258), Hy4 preview: —

Writing & Preference benchmarks
BenchmarkGemma 2 2b ITHy4 preview
LMArena Text1156—
LMArena Creative Writing1147—
LMArena Multi-Turn1118—

Frequently asked questions

Is Gemma 2 2b IT better than Hy4 preview?

Hy4 preview is the stronger model overall, scoring 44.6 to 32.5 on the Noometry Index.

Is Gemma 2 2b IT or Hy4 preview better for coding?

Hy4 preview scores higher on coding benchmarks: 51.4 versus 31.8 in the Noometry coding category.

How many benchmarks do Gemma 2 2b IT and Hy4 preview share?

0 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Hy4 preview has 3.

Related comparisons

Go deeper