Model comparison
Hy4 preview vs Kimi K2.7 Code
Hy4 preview is the stronger model overall, scoring 45.3 to 43.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
TencentSummary
- They share 1 benchmark with published results for both. Hy4 preview scores higher in 2 categories and Kimi K2.7 Code in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy4 preview leads 51.6 to 42.9.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Kimi K2.7 Code | |
|---|---|---|
| Provider | Tencent | Moonshot AI |
| Noometry Index | 45.3 | 43.3 |
| Released | 2026-08-28 | 2026-06-12 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 262K |
| Input $ / M tokens | $0.75 | $0.95 |
| Output $ / M tokens | $2.25 | $4 |
| Results tracked | 3 | 19 |
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 K2.7 Code: 42.9 (#95)
| Benchmark | Hy4 preview | Kimi K2.7 Code |
|---|---|---|
| LMArena WebDev | 1632 | 1473 |
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| SciCode | — | 47.5% |
| WeirdML | — | 54.1% |
| ALE-Bench | — | 886.23 |
Agentic & Tool Use Not comparable
Hy4 preview: —, Kimi K2.7 Code: 24.0 (#122)
| Benchmark | Hy4 preview | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | — | 37.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |
Reasoning Kimi K2.7 Code leads
Hy4 preview: 31.9 (#79), Kimi K2.7 Code: 39.0 (#61)
| Benchmark | Hy4 preview | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | — | 57.9% |
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 10% |
| Chess Puzzles | — | 21% |
| Surface Evolver Bench | — | 48.8% |
| Epoch Capabilities Index | — | 149.97 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Kimi K2.7 Code: 52.9 (#48)
| Benchmark | Hy4 preview | Kimi K2.7 Code |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | 75% | — |
Knowledge Not comparable
Hy4 preview: —, Kimi K2.7 Code: 53.5 (#57)
| Benchmark | Hy4 preview | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | — | 87.9% |
| SimpleQA Verified | — | 36.5% |
Frequently asked questions
Is Hy4 preview better than Kimi K2.7 Code?
Hy4 preview is the stronger model overall, scoring 45.3 to 43.3 on the Noometry Index.
Which is cheaper, Hy4 preview or Kimi K2.7 Code?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is Hy4 preview or Kimi K2.7 Code better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.9 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 262K.
How many benchmarks do Hy4 preview and Kimi K2.7 Code share?
1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Kimi K2.7 Code has 19.