Model comparison
Hy4 preview vs Qwen Max
Hy4 preview is the stronger model overall, scoring 45.3 to 34.7 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 22.3.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Hy4 preview accepts more context: 1.05M tokens versus 33K.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Qwen Max | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 45.3 | 34.7 |
| Released | 2026-08-28 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 33K |
| Max output | 64K | 8K |
| Input $ / M tokens | $0.75 | $1.60 |
| Output $ / M tokens | $2.25 | $6.40 |
| Results tracked | 3 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Qwen Max: 30.7 (#292)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1288 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Qwen Max: 25.1 (#151)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1269 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Qwen Max: 22.3 (#276)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| ProofBench | 75% | — |
| LMArena Math | — | 1275 |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Not comparable
Hy4 preview: —, Qwen Max: 30.3 (#228)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1248 |
Multilingual Not comparable
Hy4 preview: —, Qwen Max: 41.8 (#202)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| LMArena Non-English | — | 1263 |
| LMArena Chinese | — | 1254 |
| LMArena French | — | 1330 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Russian | — | 1274 |
| LMArena Spanish | — | 1290 |
Instruction Following Not comparable
Hy4 preview: —, Qwen Max: 66.5 (#208)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| LMArena Instruction Following | — | 1262 |
Long Context Not comparable
Hy4 preview: —, Qwen Max: 39.4 (#180)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1288 |
Writing & Preference Not comparable
Hy4 preview: —, Qwen Max: 47.8 (#205)
| Benchmark | Hy4 preview | Qwen Max |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1248 |
| LMArena Multi-Turn | — | 1277 |
Frequently asked questions
Is Hy4 preview better than Qwen Max?
Hy4 preview is the stronger model overall, scoring 45.3 to 34.7 on the Noometry Index.
Which is cheaper, Hy4 preview or Qwen Max?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Hy4 preview or Qwen Max better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 33K.
How many benchmarks do Hy4 preview and Qwen Max share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen Max has 23.