Model comparison
Hy3 vs Qwen Max
Hy3 is the stronger model overall, scoring 44.2 to 34.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 22.3.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Hy3 accepts more context: 262K tokens versus 33K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Qwen Max | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 34.7 |
| Released | 2026-07-06 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 262K | 33K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.13 | $1.60 |
| Output $ / M tokens | $0.53 | $6.40 |
| Results tracked | 19 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen Max: 30.7 (#292)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Coding | 1464 | 1288 |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Qwen Max: 25.1 (#151)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1269 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Qwen Max: 22.3 (#276)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Math | 1475 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Qwen Max: 30.3 (#228)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Expert | 1460 | 1248 |
| GPQA Diamond | — | 56.1% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen Max: 41.8 (#202)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1426 | 1263 |
| LMArena Chinese | 1493 | 1254 |
| LMArena French | 1461 | 1330 |
| LMArena German | 1439 | 1254 |
| LMArena Japanese | 1392 | 1205 |
| LMArena Korean | 1395 | 1142 |
| LMArena Russian | 1432 | 1274 |
| LMArena Spanish | 1456 | 1290 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen Max: 66.5 (#208)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1426 | 1262 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen Max: 39.4 (#180)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1442 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen Max: 47.8 (#205)
| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Text | 1439 | 1282 |
| LMArena Creative Writing | 1402 | 1248 |
| LMArena Multi-Turn | 1436 | 1277 |
Frequently asked questions
Is Hy3 better than Qwen Max?
Hy3 is the stronger model overall, scoring 44.2 to 34.7 on the Noometry Index.
Which is cheaper, Hy3 or Qwen Max?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Hy3 or Qwen Max better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 33K.
How many benchmarks do Hy3 and Qwen Max share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen Max has 23.