Model comparison

Hy4 preview vs Yi-Lightning

Hy4 preview is the stronger model overall, scoring 45.3 to 37.1 on the Noometry Index.

Last verified . 0 shared benchmarks.

Hy4 preview Tencent

45.3

Rank #73 Reported

Yi-Lightning 01.AI

37.1

Rank #209 Confirmed

Summary

  • The widest gap is in coding, where Hy4 preview leads 51.6 to 27.4.
  • Hy4 preview has downloadable open weights; the other is API-only.

Side by side

Hy4 preview and Yi-Lightning specifications
Hy4 previewYi-Lightning
ProviderTencent01.AI
Noometry Index45.337.1
Released2026-08-282024-12-02
WeightsOpenProprietary
Context window1.05M—
Max output64K—
Input $ / M tokens$0.75—
Output $ / M tokens$2.25—
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), Yi-Lightning: 27.4 (#320)

Coding benchmarks
BenchmarkHy4 previewYi-Lightning
Aider Polyglot—12.9%
LMArena WebDev1632—
LMArena Coding—1312

Reasoning Hy4 preview leads

Hy4 preview: 31.9 (#79), Yi-Lightning: 25.9 (#139)

Reasoning benchmarks
BenchmarkHy4 previewYi-Lightning
NYT Connections (extended)68.2%—
LMArena Hard Prompts—1302

Math Hy4 preview leads

Hy4 preview: 55.7 (#42), Yi-Lightning: 36.2 (#172)

Math benchmarks
BenchmarkHy4 previewYi-Lightning
ProofBench75%—
LMArena Math—1300

Knowledge Not comparable

Hy4 preview: —, Yi-Lightning: 35.4 (#185)

Knowledge benchmarks
BenchmarkHy4 previewYi-Lightning
LMArena Expert—1286

Multilingual Not comparable

Hy4 preview: —, Yi-Lightning: 42.2 (#196)

Multilingual benchmarks
BenchmarkHy4 previewYi-Lightning
LMArena Non-English—1269
LMArena Chinese—1320
LMArena French—1305
LMArena German—1267
LMArena Japanese—1228
LMArena Korean—1192
LMArena Russian—1255
LMArena Spanish—1315

Instruction Following Not comparable

Hy4 preview: —, Yi-Lightning: 67.4 (#196)

Instruction Following benchmarks
BenchmarkHy4 previewYi-Lightning
LMArena Instruction Following—1278

Long Context Not comparable

Hy4 preview: —, Yi-Lightning: 39.4 (#181)

Long Context benchmarks
BenchmarkHy4 previewYi-Lightning
LMArena Longer Query—1297

Writing & Preference Not comparable

Hy4 preview: —, Yi-Lightning: 50.2 (#184)

Writing & Preference benchmarks
BenchmarkHy4 previewYi-Lightning
LMArena Text—1302
LMArena Creative Writing—1280
LMArena Multi-Turn—1311

Frequently asked questions

Is Hy4 preview better than Yi-Lightning?

Hy4 preview is the stronger model overall, scoring 45.3 to 37.1 on the Noometry Index.

Is Hy4 preview or Yi-Lightning better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 27.4 in the Noometry coding category.

How many benchmarks do Hy4 preview and Yi-Lightning share?

0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Yi-Lightning has 18.

Related comparisons

Go deeper