Model comparison
Hy4 preview vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 45.3 on the Noometry Index.
Last verified . 3 shared benchmarks.
TencentSummary
- They share 3 benchmarks with published results for both. Hy4 preview scores higher in 1 category and Kimi K2.6 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 31.9.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 16% for Kimi K2.6.
- Hy4 preview is cheaper at $0.83 / $2.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Kimi K2.6 | |
|---|---|---|
| Provider | Tencent | Moonshot AI |
| Noometry Index | 45.3 | 47.7 |
| Released | 2026-08-28 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 262K |
| Input $ / M tokens | $0.83 | $0.95 |
| Output $ / M tokens | $2.50 | $4 |
| Results tracked | 3 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Hy4 preview: 51.6 (#38), Kimi K2.6: 50.7 (#43)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1632 | 1509 |
| SWE-bench Verified | — | 76.7% |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| LMArena Coding | — | 1488 |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Not comparable
Hy4 preview: —, Kimi K2.6: 21.9 (#137)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Hy4 preview: 31.9 (#79), Kimi K2.6: 40.5 (#55)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 68.2% | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| LMArena Hard Prompts | — | 1470 |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Epoch Capabilities Index | — | 151.05 |
Math Kimi K2.6 leads
Hy4 preview: 55.7 (#42), Kimi K2.6: 57.0 (#41)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| ProofBench | 75% | 16% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| LMArena Math | — | 1475 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
Hy4 preview: —, Kimi K2.6: 54.0 (#54)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
| LMArena Expert | — | 1491 |
Multimodal Not comparable
Hy4 preview: —, Kimi K2.6: 31.6 (#103)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Not comparable
Hy4 preview: —, Kimi K2.6: 54.9 (#37)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | — | 1446 |
| LMArena Chinese | — | 1521 |
| LMArena French | — | 1471 |
| LMArena German | — | 1450 |
| LMArena Japanese | — | 1443 |
| LMArena Korean | — | 1427 |
| LMArena Russian | — | 1446 |
| LMArena Spanish | — | 1464 |
Instruction Following Not comparable
Hy4 preview: —, Kimi K2.6: 76.3 (#43)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | — | 1451 |
Long Context Not comparable
Hy4 preview: —, Kimi K2.6: 44.9 (#52)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | — | 1468 |
Writing & Preference Not comparable
Hy4 preview: —, Kimi K2.6: 68.5 (#26)
| Benchmark | Hy4 preview | Kimi K2.6 |
|---|---|---|
| LMArena Text | — | 1455 |
| LMArena Creative Writing | — | 1434 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
| LMArena Multi-Turn | — | 1453 |
Frequently asked questions
Is Hy4 preview better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 45.3 on the Noometry Index.
Which is cheaper, Hy4 preview or Kimi K2.6?
Hy4 preview is cheaper. It lists at $0.83 per million input tokens and $2.50 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Hy4 preview or Kimi K2.6 better for coding?
They score almost the same on coding (51.6 vs 50.7); test both on your own repository before choosing.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 262K.
How many benchmarks do Hy4 preview and Kimi K2.6 share?
3 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Kimi K2.6 has 51.