Model comparison
DeepSeek-V3.2-Speciale vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 39.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
TencentSummary
- The widest gap is in coding, where Hy4 preview leads 51.6 to 40.4.
- DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 128K.
Side by side
| DeepSeek-V3.2-Speciale | Hy4 preview | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 39.7 | 45.3 |
| Released | 2025-12-01 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 128K | 1.05M |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.58 | $0.83 |
| Output $ / M tokens | $1.68 | $2.50 |
| Results tracked | 3 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
DeepSeek-V3.2-Speciale: 40.4 (#140), Hy4 preview: 51.6 (#38)
| Benchmark | DeepSeek-V3.2-Speciale | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |
| WeirdML | 46.7% | — |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.9 (#73), Hy4 preview: 31.9 (#79)
| Benchmark | DeepSeek-V3.2-Speciale | Hy4 preview |
|---|---|---|
| SimpleBench | 52.6% | — |
| NYT Connections (extended) | — | 68.2% |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Hy4 preview: 55.7 (#42)
| Benchmark | DeepSeek-V3.2-Speciale | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
Writing & Preference Not comparable
DeepSeek-V3.2-Speciale: 46.0 (#222), Hy4 preview: —
| Benchmark | DeepSeek-V3.2-Speciale | Hy4 preview |
|---|---|---|
| EQ-Bench Creative Writing | 1276 | — |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 39.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Speciale or Hy4 preview?
DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is DeepSeek-V3.2-Speciale or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 40.4 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 128K.
How many benchmarks do DeepSeek-V3.2-Speciale and Hy4 preview share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Hy4 preview has 3.