Model comparison

Hy4 preview vs Kimi K2.5 Instant

Hy4 preview is the stronger model overall, scoring 45.3 to 43.6 on the Noometry Index.

Last verified . 1 shared benchmarks.

Hy4 preview Tencent

45.3

Rank #73 Reported

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Summary

  • They share 1 benchmark with published results for both. Hy4 preview scores higher in 3 categories and Kimi K2.5 Instant in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hy4 preview leads 55.7 to 39.4.

Side by side

Hy4 preview and Kimi K2.5 Instant specifications
Hy4 previewKimi K2.5 Instant
ProviderTencentMoonshot AI
Noometry Index45.343.6
Released2026-08-28—
WeightsOpenOpen
Context window1.05M—
Max output64K—
Input $ / M tokens$0.83—
Output $ / M tokens$2.50—
Results tracked318

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

Category by category

Coding Hy4 preview leads

Hy4 preview: 51.6 (#38), Kimi K2.5 Instant: 42.6 (#97)

Coding benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena WebDev16321404
LMArena Coding—1484

Reasoning Hy4 preview leads

Hy4 preview: 31.9 (#79), Kimi K2.5 Instant: 29.7 (#90)

Reasoning benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
NYT Connections (extended)68.2%—
LMArena Hard Prompts—1443

Math Hy4 preview leads

Hy4 preview: 55.7 (#42), Kimi K2.5 Instant: 39.4 (#105)

Math benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
ProofBench75%—
LMArena Math—1442

Knowledge Not comparable

Hy4 preview: —, Kimi K2.5 Instant: 40.2 (#123)

Knowledge benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena Expert—1440

Multimodal Not comparable

Hy4 preview: —, Kimi K2.5 Instant: 40.2 (#50)

Multimodal benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena Vision—1254

Multilingual Not comparable

Hy4 preview: —, Kimi K2.5 Instant: 52.0 (#94)

Multilingual benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena Non-English—1406
LMArena Chinese—1449
LMArena French—1403
LMArena German—1413
LMArena Korean—1378
LMArena Russian—1404
LMArena Spanish—1447

Instruction Following Not comparable

Hy4 preview: —, Kimi K2.5 Instant: 75.3 (#65)

Instruction Following benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena Instruction Following—1430

Long Context Not comparable

Hy4 preview: —, Kimi K2.5 Instant: 43.9 (#83)

Long Context benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena Longer Query—1435

Writing & Preference Not comparable

Hy4 preview: —, Kimi K2.5 Instant: 60.6 (#95)

Writing & Preference benchmarks
BenchmarkHy4 previewKimi K2.5 Instant
LMArena Text—1420
LMArena Creative Writing—1381
LMArena Multi-Turn—1427

Frequently asked questions

Is Hy4 preview better than Kimi K2.5 Instant?

Hy4 preview is the stronger model overall, scoring 45.3 to 43.6 on the Noometry Index.

Is Hy4 preview or Kimi K2.5 Instant better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.6 in the Noometry coding category.

How many benchmarks do Hy4 preview and Kimi K2.5 Instant share?

1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Kimi K2.5 Instant has 18.

Related comparisons

Go deeper