Model comparison
Hy3 vs Qwen-14B
Hy3 is the stronger model overall, scoring 44.2 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Hy3 scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 27.6.
Side by side
| Hy3 | Qwen-14B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 31.4 |
| Released | 2026-07-06 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen-14B: 31.2 (#288)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1464 | 1071 |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Qwen-14B: 19.6 (#257)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1027 |
| NYT Connections (extended) | 41.2% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Hy3 leads
Hy3: 40.1 (#93), Qwen-14B: 31.2 (#227)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Math | 1475 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Hy3: 40.8 (#114), Qwen-14B: —
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Expert | 1460 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen-14B: 27.5 (#275)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1426 | 1041 |
| LMArena Chinese | 1493 | 1077 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Russian | 1432 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen-14B: 52.4 (#289)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1031 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen-14B: 31.3 (#280)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1442 | 1028 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen-14B: 27.6 (#299)
| Benchmark | Hy3 | Qwen-14B |
|---|---|---|
| LMArena Text | 1439 | 1051 |
| LMArena Creative Writing | 1402 | 1028 |
| LMArena Multi-Turn | 1436 | 1022 |
Frequently asked questions
Is Hy3 better than Qwen-14B?
Hy3 is the stronger model overall, scoring 44.2 to 31.4 on the Noometry Index.
Is Hy3 or Qwen-14B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 31.2 in the Noometry coding category.
How many benchmarks do Hy3 and Qwen-14B share?
10 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen-14B has 18.