Model comparison
Hy3 vs Qwen1.5-72B
Hy3 is the stronger model overall, scoring 44.2 to 30.8 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 Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 11.5.
Side by side
| Hy3 | Qwen1.5-72B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 30.8 |
| Released | 2026-07-06 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1464 | 1165 |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1148 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1475 | 1164 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1460 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1426 | 1135 |
| LMArena Chinese | 1493 | 1186 |
| LMArena French | 1461 | 1159 |
| LMArena German | 1439 | 1084 |
| LMArena Japanese | 1392 | 1061 |
| LMArena Korean | 1395 | 1050 |
| LMArena Russian | 1432 | 1104 |
| LMArena Spanish | 1456 | 1110 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1141 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1442 | 1157 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1439 | 1166 |
| LMArena Creative Writing | 1402 | 1137 |
| LMArena Multi-Turn | 1436 | 1160 |
Frequently asked questions
Is Hy3 better than Qwen1.5-72B?
Hy3 is the stronger model overall, scoring 44.2 to 30.8 on the Noometry Index.
Is Hy3 or Qwen1.5-72B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 31.9 in the Noometry coding category.
How many benchmarks do Hy3 and Qwen1.5-72B share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen1.5-72B has 22.