Model comparison
Hy3 vs Qwen3.5 122B-A10B
Hy3 is the stronger model overall, scoring 44.2 to 42.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Hy3 scores higher in 7 categories and Qwen3.5 122B-A10B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 39.1.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 51.7% for Qwen3.5 122B-A10B.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
Side by side
| Hy3 | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 42.1 |
| Released | 2026-07-06 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.0825 | $0.40 |
| Output $ / M tokens | $0.33 | $3.20 |
| Results tracked | 19 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena WebDev | 1508 | 1360 |
| LMArena Coding | 1464 | 1436 |
| SciCode | — | 35.6% |
Reasoning Qwen3.5 122B-A10B leads
Hy3: 26.1 (#136), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| NYT Connections (extended) | 41.2% | 51.7% |
| LMArena Hard Prompts | 1447 | 1421 |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
Math Too close to call
Hy3: 40.1 (#93), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1475 | 1432 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1460 | 1432 |
| Vectara Hallucination Rate | — | 11.2% |
Multimodal Not comparable
Hy3: —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1426 | 1400 |
| LMArena Chinese | 1493 | 1462 |
| LMArena French | 1461 | 1442 |
| LMArena German | 1439 | 1426 |
| LMArena Japanese | 1392 | 1367 |
| LMArena Korean | 1395 | 1352 |
| LMArena Russian | 1432 | 1400 |
| LMArena Spanish | 1456 | 1424 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1399 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1442 | 1410 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Hy3 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1439 | 1417 |
| LMArena Creative Writing | 1402 | 1368 |
| LMArena Multi-Turn | 1436 | 1416 |
Frequently asked questions
Is Hy3 better than Qwen3.5 122B-A10B?
Hy3 is the stronger model overall, scoring 44.2 to 42.1 on the Noometry Index.
Which is cheaper, Hy3 or Qwen3.5 122B-A10B?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Hy3 or Qwen3.5 122B-A10B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Qwen3.5 122B-A10B share?
19 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen3.5 122B-A10B has 27.