Model comparison
Hy3 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 44.2 on the Noometry Index. Hy3 costs 20× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Hy3 scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 to 40.8.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 74.1% for Qwen3.6 Max Preview.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 51.5 |
| Released | 2026-07-06 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.0825 | $1.30 |
| Output $ / M tokens | $0.33 | $7.80 |
| Results tracked | 19 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Hy3: 46.8 (#63), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1508 | 1482 |
| LMArena Coding | 1464 | 1471 |
| SWE-bench Verified | — | 76.7% |
Agentic & Tool Use Not comparable
Hy3: —, Qwen3.6 Max Preview: —
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Hy3: 26.1 (#136), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| NYT Connections (extended) | 41.2% | 74.1% |
| LMArena Hard Prompts | 1447 | 1457 |
| SimpleBench | — | 63% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.24 |
Math Qwen3.6 Max Preview leads
Hy3: 40.1 (#93), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1475 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Hy3: 40.8 (#114), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1460 | 1478 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
Multilingual Too close to call
Hy3: 53.5 (#65), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1426 | 1437 |
| LMArena Chinese | 1493 | 1487 |
| LMArena French | 1461 | 1449 |
| LMArena Russian | 1432 | 1445 |
| LMArena Spanish | 1456 | 1454 |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
Instruction Following Too close to call
Hy3: 75.1 (#70), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1426 | 1438 |
Long Context Too close to call
Hy3: 44.1 (#75), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1442 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Hy3: 62.2 (#81), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Hy3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1439 | 1447 |
| LMArena Creative Writing | 1402 | 1435 |
| LMArena Multi-Turn | 1436 | 1456 |
Frequently asked questions
Is Hy3 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 44.2 on the Noometry Index. Hy3 costs 20× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Hy3 or Qwen3.6 Max Preview?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Hy3 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Qwen3.6 Max Preview share?
16 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen3.6 Max Preview has 29.