Model comparison
Hy3 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 43.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Hy3 scores higher in 2 categories and Qwen3.5 Max Preview in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 29.6 to 25.0.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 43.6 | 44.7 |
| Released | 2026-07-06 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1465 | 1488 |
| LMArena WebDev | 1509 | — |
Reasoning Qwen3.5 Max Preview leads
Hy3: 25.0 (#134), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1483 |
| NYT Connections (extended) | 41.2% | — |
Math Too close to call
Hy3: 37.4 (#98), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1475 | 1473 |
Knowledge Too close to call
Hy3: 40.2 (#108), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1461 | 1489 |
Multilingual Qwen3.5 Max Preview leads
Hy3: 53.7 (#60), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1427 | 1465 |
| LMArena Chinese | 1496 | 1534 |
| LMArena French | 1461 | 1483 |
| LMArena Korean | 1390 | 1438 |
| LMArena Russian | 1435 | 1472 |
| LMArena Spanish | 1448 | 1470 |
| LMArena German | — | 1487 |
| LMArena Japanese | — | 1497 |
Instruction Following Qwen3.5 Max Preview leads
Hy3: 75.3 (#68), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1425 | 1467 |
Long Context Qwen3.5 Max Preview leads
Hy3: 44.1 (#70), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1443 | 1477 |
Writing & Preference Qwen3.5 Max Preview leads
Hy3: 62.5 (#75), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Hy3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1442 | 1471 |
| LMArena Creative Writing | 1399 | 1464 |
| LMArena Multi-Turn | 1436 | 1478 |
Frequently asked questions
Is Hy3 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 43.6 on the Noometry Index.
Is Hy3 or Qwen3.5 Max Preview better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 43.4 in the Noometry coding category.
How many benchmarks do Hy3 and Qwen3.5 Max Preview share?
15 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Qwen3.5 Max Preview has 17.