Model comparison
Hy4 preview vs Qwen3-1.7B
Hy4 preview is the stronger model overall, scoring 45.3 to 26.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- The widest gap is in math, where Hy4 preview leads 55.7 to 16.3.
Side by side
| Hy4 preview | Qwen3-1.7B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 45.3 | 26.6 |
| Released | 2026-08-28 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Hy4 preview: 51.6 (#38), Qwen3-1.7B: —
| Benchmark | Hy4 preview | Qwen3-1.7B |
|---|---|---|
| LMArena WebDev | 1632 | — |
Agentic & Tool Use Not comparable
Hy4 preview: —, Qwen3-1.7B: 24.7 (#115)
| Benchmark | Hy4 preview | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Qwen3-1.7B: 19.2 (#267)
| Benchmark | Hy4 preview | Qwen3-1.7B |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| Chess Puzzles | — | 0% |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Qwen3-1.7B: 16.3 (#294)
| Benchmark | Hy4 preview | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| ProofBench | 75% | — |
Knowledge Not comparable
Hy4 preview: —, Qwen3-1.7B: 19.6 (#278)
| Benchmark | Hy4 preview | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
Frequently asked questions
Is Hy4 preview better than Qwen3-1.7B?
Hy4 preview is the stronger model overall, scoring 45.3 to 26.6 on the Noometry Index.
How many benchmarks do Hy4 preview and Qwen3-1.7B share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen3-1.7B has 4.