Model comparison

Hy4 preview vs Kimi K2 Thinking Turbo

Hy4 preview and Kimi K2 Thinking Turbo score almost the same on the Noometry Index (45.3 vs 45.8), so choose on price, context window or the category you care about most.

Last verified . 1 shared benchmarks.

Hy4 preview Tencent

45.3

Rank #73 Reported

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 1 benchmark with published results for both. Hy4 preview scores higher in 2 categories and Kimi K2 Thinking Turbo in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Hy4 preview leads 51.6 to 38.4.

Side by side

Hy4 preview and Kimi K2 Thinking Turbo specifications
Hy4 previewKimi K2 Thinking Turbo
ProviderTencentMoonshot AI
Noometry Index45.345.8
Released2026-08-282025-11-06
WeightsOpenOpen
Context window1.05M—
Max output64K—
Input $ / M tokens$0.75—
Output $ / M tokens$2.25—
Results tracked321

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 Thinking Turbo: 38.4 (#178)

Coding benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
LMArena WebDev16321322
LMArena Coding—1454

Reasoning Too close to call

Hy4 preview: 31.9 (#79), Kimi K2 Thinking Turbo: 32.5 (#75)

Reasoning benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
NYT Connections (extended)68.2%—
Chess Puzzles—20%
LMArena Hard Prompts—1428

Math Hy4 preview leads

Hy4 preview: 55.7 (#42), Kimi K2 Thinking Turbo: 47.4 (#68)

Math benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
OTIS Mock AIME 2024-2025—83.1%
ProofBench75%—
LMArena Math—1429

Knowledge Not comparable

Hy4 preview: —, Kimi K2 Thinking Turbo: 50.9 (#69)

Knowledge benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
GPQA Diamond—84.2%
LMArena Expert—1439

Multilingual Not comparable

Hy4 preview: —, Kimi K2 Thinking Turbo: 51.4 (#109)

Multilingual benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
LMArena Non-English—1398
LMArena Chinese—1456
LMArena French—1425
LMArena German—1390
LMArena Japanese—1357
LMArena Korean—1330
LMArena Russian—1391
LMArena Spanish—1406

Instruction Following Not comparable

Hy4 preview: —, Kimi K2 Thinking Turbo: 74.0 (#109)

Instruction Following benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
LMArena Instruction Following—1403

Long Context Not comparable

Hy4 preview: —, Kimi K2 Thinking Turbo: 43.2 (#102)

Long Context benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
LMArena Longer Query—1415

Writing & Preference Not comparable

Hy4 preview: —, Kimi K2 Thinking Turbo: 60.0 (#104)

Writing & Preference benchmarks
BenchmarkHy4 previewKimi K2 Thinking Turbo
LMArena Text—1415
LMArena Creative Writing—1374
LMArena Multi-Turn—1414

Frequently asked questions

Is Hy4 preview better than Kimi K2 Thinking Turbo?

Hy4 preview and Kimi K2 Thinking Turbo score almost the same on the Noometry Index (45.3 vs 45.8), so choose on price, context window or the category you care about most.

Is Hy4 preview or Kimi K2 Thinking Turbo better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 38.4 in the Noometry coding category.

How many benchmarks do Hy4 preview and Kimi K2 Thinking Turbo share?

1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper