Model comparison
Hy4 preview vs Qwen-14B
Hy4 preview is the stronger model overall, scoring 45.3 to 31.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- The widest gap is in math, where Hy4 preview leads 55.7 to 31.2.
Side by side
| Hy4 preview | Qwen-14B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 45.3 | 31.4 |
| Released | 2026-08-28 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Qwen-14B: 31.2 (#288)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1071 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Qwen-14B: 19.6 (#257)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Qwen-14B: 31.2 (#227)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Hy4 preview: —, Qwen-14B: —
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Not comparable
Hy4 preview: —, Qwen-14B: 27.5 (#275)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Hy4 preview: —, Qwen-14B: 52.4 (#289)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Hy4 preview: —, Qwen-14B: 31.3 (#280)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Not comparable
Hy4 preview: —, Qwen-14B: 27.6 (#299)
| Benchmark | Hy4 preview | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Hy4 preview better than Qwen-14B?
Hy4 preview is the stronger model overall, scoring 45.3 to 31.4 on the Noometry Index.
Is Hy4 preview or Qwen-14B better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 31.2 in the Noometry coding category.
How many benchmarks do Hy4 preview and Qwen-14B share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen-14B has 18.