Model comparison
Hy4 preview vs Nova 2.0 Pro Preview
Hy4 preview is the stronger model overall, scoring 44.6 to 32.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
TencentSummary
- The widest gap is in coding, where Hy4 preview leads 51.4 to 40.2.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Nova 2.0 Pro Preview | |
|---|---|---|
| Provider | Tencent | Amazon |
| Noometry Index | 44.6 | 32.8 |
| Released | 2026-08-28 | 2025-12-02 |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $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
Hy4 preview: 51.4 (#36), Nova 2.0 Pro Preview: 40.2 (#130)
| Benchmark | Hy4 preview | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena WebDev | 1633 | — |
| SciCode | — | 42.7% |
Agentic & Tool Use Not comparable
Hy4 preview: —, Nova 2.0 Pro Preview: 21.9 (#127)
| Benchmark | Hy4 preview | Nova 2.0 Pro Preview |
|---|---|---|
| GDP.pdf | — | 2% |
Reasoning Hy4 preview leads
Hy4 preview: 30.6 (#75), Nova 2.0 Pro Preview: 21.7 (#189)
| Benchmark | Hy4 preview | Nova 2.0 Pro Preview |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 0% |
Math Not comparable
Hy4 preview: 54.5 (#37), Nova 2.0 Pro Preview: —
| Benchmark | Hy4 preview | Nova 2.0 Pro Preview |
|---|---|---|
| ProofBench | 75% | — |
Frequently asked questions
Is Hy4 preview better than Nova 2.0 Pro Preview?
Hy4 preview is the stronger model overall, scoring 44.6 to 32.8 on the Noometry Index.
Is Hy4 preview or Nova 2.0 Pro Preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 40.2 in the Noometry coding category.
How many benchmarks do Hy4 preview and Nova 2.0 Pro Preview share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Nova 2.0 Pro Preview has 3.