Model comparison
Hy3 vs Qwen1.5-110B
Hy3 is the stronger model overall, scoring 44.2 to 34.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Qwen1.5-110B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 38.0.
Side by side
| Hy3 | Qwen1.5-110B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 34.2 |
| Released | 2026-07-06 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 19 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1464 | 1184 |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1168 |
| NYT Connections (extended) | 41.2% | — |
| ForecastBench | — | 57.7 |
Math Hy3 leads
Hy3: 40.1 (#93), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1475 | 1185 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1460 | 1144 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1426 | 1142 |
| LMArena Chinese | 1493 | 1206 |
| LMArena French | 1461 | 1151 |
| LMArena German | 1439 | 1123 |
| LMArena Japanese | 1392 | 1074 |
| LMArena Korean | 1395 | 1044 |
| LMArena Russian | 1432 | 1118 |
| LMArena Spanish | 1456 | 1142 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1158 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1442 | 1157 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Hy3 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1439 | 1175 |
| LMArena Creative Writing | 1402 | 1148 |
| LMArena Multi-Turn | 1436 | 1160 |
Frequently asked questions
Is Hy3 better than Qwen1.5-110B?
Hy3 is the stronger model overall, scoring 44.2 to 34.2 on the Noometry Index.
Is Hy3 or Qwen1.5-110B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 33.0 in the Noometry coding category.
How many benchmarks do Hy3 and Qwen1.5-110B share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen1.5-110B has 20.