Model comparison
Hy4 preview vs Qwen3.5 122B-A10B
Hy4 preview is the stronger model overall, scoring 45.3 to 42.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Hy4 preview scores higher in 3 categories and Qwen3.5 122B-A10B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 39.1.
- The biggest single-benchmark swing is NYT Connections (extended): 68.2% for Hy4 preview and 51.7% for Qwen3.5 122B-A10B.
- Both cost about the same: $0.75 input and $2.25 output per million tokens.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 45.3 | 42.1 |
| Released | 2026-08-28 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.75 | $0.40 |
| Output $ / M tokens | $2.25 | $3.20 |
| Results tracked | 3 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena WebDev | 1632 | 1360 |
| SciCode | — | 35.6% |
| LMArena Coding | — | 1436 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| NYT Connections (extended) | 68.2% | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| LMArena Hard Prompts | — | 1421 |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1432 |
Knowledge Not comparable
Hy4 preview: —, Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | — | 11.2% |
| LMArena Expert | — | 1432 |
Multimodal Not comparable
Hy4 preview: —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Not comparable
Hy4 preview: —, Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | — | 1400 |
| LMArena Chinese | — | 1462 |
| LMArena French | — | 1442 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1367 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1400 |
| LMArena Spanish | — | 1424 |
Instruction Following Not comparable
Hy4 preview: —, Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | — | 1399 |
Long Context Not comparable
Hy4 preview: —, Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | — | 1410 |
Writing & Preference Not comparable
Hy4 preview: —, Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Hy4 preview | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | — | 1417 |
| LMArena Creative Writing | — | 1368 |
| LMArena Multi-Turn | — | 1416 |
Frequently asked questions
Is Hy4 preview better than Qwen3.5 122B-A10B?
Hy4 preview is the stronger model overall, scoring 45.3 to 42.1 on the Noometry Index.
Which is cheaper, Hy4 preview or Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is cheaper. It lists at $0.40 per million input tokens and $3.20 per million output tokens; Hy4 preview lists at $0.75 and $2.25.
Is Hy4 preview or Qwen3.5 122B-A10B better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 262K.
How many benchmarks do Hy4 preview and Qwen3.5 122B-A10B share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen3.5 122B-A10B has 27.