Model comparison
Hy3 vs Qwen1.5-72B
Hy3 is the stronger model overall, scoring 43.6 to 30.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 15 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 40.2 to 11.5.
Side by side
| Hy3 | Qwen1.5-72B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 43.6 | 30.3 |
| Released | 2026-07-06 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Qwen1.5-72B: 31.4 (#272)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1465 | 1166 |
| LMArena WebDev | 1509 | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Hy3 leads
Hy3: 25.0 (#134), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1148 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 37.4 (#98), Qwen1.5-72B: 30.7 (#205)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1475 | 1164 |
Knowledge Hy3 leads
Hy3: 40.2 (#108), Qwen1.5-72B: 11.5 (#295)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1461 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Qwen1.5-72B: 33.4 (#248)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1427 | 1135 |
| LMArena Chinese | 1496 | 1186 |
| LMArena French | 1461 | 1158 |
| LMArena Korean | 1390 | 1049 |
| LMArena Russian | 1435 | 1104 |
| LMArena Spanish | 1448 | 1110 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Qwen1.5-72B: 59.6 (#251)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1425 | 1142 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Qwen1.5-72B: 35.0 (#238)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1443 | 1157 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Qwen1.5-72B: 37.4 (#253)
| Benchmark | Hy3 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1442 | 1166 |
| LMArena Creative Writing | 1399 | 1137 |
| LMArena Multi-Turn | 1436 | 1160 |
Frequently asked questions
Is Hy3 better than Qwen1.5-72B?
Hy3 is the stronger model overall, scoring 43.6 to 30.3 on the Noometry Index.
Is Hy3 or Qwen1.5-72B better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 31.4 in the Noometry coding category.
How many benchmarks do Hy3 and Qwen1.5-72B share?
15 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Qwen1.5-72B has 22.