Model comparison
Hy4 preview vs Qwen3.5 397B-A17B
Hy4 preview and Qwen3.5 397B-A17B score almost the same on the Noometry Index (45.3 vs 46.0), so choose on price, context window or the category you care about most.
Last verified . 2 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Hy4 preview scores higher in 2 categories and Qwen3.5 397B-A17B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy4 preview leads 51.6 to 42.0.
- The biggest single-benchmark swing is NYT Connections (extended): 68.2% for Hy4 preview and 58.9% for Qwen3.5 397B-A17B.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy4 preview | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 45.3 | 46.0 |
| Released | 2026-08-28 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.75 | $0.60 |
| Output $ / M tokens | $2.25 | $3.60 |
| Results tracked | 3 | 36 |
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 397B-A17B: 42.0 (#114)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1632 | 1400 |
| LMArena Coding | — | 1465 |
Agentic & Tool Use Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Hy4 preview: 31.9 (#79), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| NYT Connections (extended) | 68.2% | 58.9% |
| Kagi LLM Benchmark | — | 73.7% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | 75% | — |
| LMArena Math | — | 1454 |
Knowledge Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | — | 86.4% |
| LMArena Expert | — | 1462 |
Multimodal Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1500 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1441 |
Instruction Following Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | — | 1424 |
Long Context Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Not comparable
Hy4 preview: —, Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Hy4 preview | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | — | 1438 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1446 |
Frequently asked questions
Is Hy4 preview better than Qwen3.5 397B-A17B?
Hy4 preview and Qwen3.5 397B-A17B score almost the same on the Noometry Index (45.3 vs 46.0), so choose on price, context window or the category you care about most.
Which is cheaper, Hy4 preview or Qwen3.5 397B-A17B?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Hy4 preview or Qwen3.5 397B-A17B better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.0 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 397B-A17B share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen3.5 397B-A17B has 36.