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.
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 | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Tencent | Moonshot AI |
| Noometry Index | 45.3 | 43.6 |
| Released | 2026-08-28 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 18 |
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)
| Benchmark | Hy4 preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena WebDev | 1632 | 1404 |
| LMArena Coding | — | 1484 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | Hy4 preview | Kimi 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)
| Benchmark | Hy4 preview | Kimi K2.5 Instant |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1442 |
Knowledge Not comparable
Hy4 preview: —, Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | Hy4 preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | — | 1440 |
Multimodal Not comparable
Hy4 preview: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | Hy4 preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Not comparable
Hy4 preview: —, Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | Hy4 preview | Kimi 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)
| Benchmark | Hy4 preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | — | 1430 |
Long Context Not comparable
Hy4 preview: —, Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | Hy4 preview | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | — | 1435 |
Writing & Preference Not comparable
Hy4 preview: —, Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | Hy4 preview | Kimi 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.