Model comparison
Hy4 preview vs Qwen3.5 35B-A3B
Hy4 preview is the stronger model overall, scoring 44.6 to 41.7 on the Noometry Index. Qwen3.5 35B-A3B costs 1.8× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Hy4 preview scores higher in 3 categories and Qwen3.5 35B-A3B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy4 preview leads 51.4 to 33.5.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.6 | 41.7 |
| Released | 2026-08-28 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.83 | $0.25 |
| Output $ / M tokens | $2.50 | $2 |
| Results tracked | 3 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.4 (#36), Qwen3.5 35B-A3B: 33.5 (#244)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1633 | 1254 |
| SciCode | — | 29.3% |
| LMArena Coding | — | 1410 |
Reasoning Hy4 preview leads
Hy4 preview: 30.6 (#75), Qwen3.5 35B-A3B: 23.9 (#158)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| LMArena Hard Prompts | — | 1400 |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
Math Hy4 preview leads
Hy4 preview: 54.5 (#37), Qwen3.5 35B-A3B: 38.4 (#86)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| ProofBench | 75% | — |
| LMArena Math | — | 1404 |
Knowledge Not comparable
Hy4 preview: —, Qwen3.5 35B-A3B: 47.7 (#73)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | — | 83.5% |
| Vectara Hallucination Rate | — | 10.5% |
| LMArena Expert | — | 1408 |
Multilingual Not comparable
Hy4 preview: —, Qwen3.5 35B-A3B: 50.2 (#122)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | — | 1379 |
| LMArena Chinese | — | 1458 |
| LMArena French | — | 1412 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1326 |
| LMArena Korean | — | 1354 |
| LMArena Russian | — | 1377 |
| LMArena Spanish | — | 1390 |
Instruction Following Not comparable
Hy4 preview: —, Qwen3.5 35B-A3B: 73.0 (#123)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1379 |
Long Context Not comparable
Hy4 preview: —, Qwen3.5 35B-A3B: 42.4 (#122)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | — | 1390 |
Writing & Preference Not comparable
Hy4 preview: —, Qwen3.5 35B-A3B: 58.1 (#118)
| Benchmark | Hy4 preview | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | — | 1395 |
| LMArena Creative Writing | — | 1347 |
| LMArena Multi-Turn | — | 1391 |
Frequently asked questions
Is Hy4 preview better than Qwen3.5 35B-A3B?
Hy4 preview is the stronger model overall, scoring 44.6 to 41.7 on the Noometry Index. Qwen3.5 35B-A3B costs 1.8× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is Hy4 preview or Qwen3.5 35B-A3B better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 33.5 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 35B-A3B share?
1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen3.5 35B-A3B has 28.