Model comparison
Hy4 preview vs Qwen2-72B
Hy4 preview is the stronger model overall, scoring 45.3 to 30.0 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 30.2.
Side by side
| Hy4 preview | Qwen2-72B | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 45.3 | 30.0 |
| Released | 2026-08-28 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Qwen2-72B: 29.1 (#310)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| LMArena WebDev | 1632 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Hy4 preview: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Qwen2-72B: 23.2 (#181)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Qwen2-72B: 30.2 (#236)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
Hy4 preview: —, Qwen2-72B: 21.2 (#275)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Not comparable
Hy4 preview: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
Hy4 preview: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Hy4 preview: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
Hy4 preview: —, Qwen2-72B: 40.8 (#241)
| Benchmark | Hy4 preview | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Hy4 preview better than Qwen2-72B?
Hy4 preview is the stronger model overall, scoring 45.3 to 30.0 on the Noometry Index.
Is Hy4 preview or Qwen2-72B better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 29.1 in the Noometry coding category.
How many benchmarks do Hy4 preview and Qwen2-72B share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen2-72B has 26.