Model comparison
Qwen2-72B vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.5 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 Max Preview leads 66.1 to 41.0.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Qwen2-72B | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.5 | 44.7 |
| Released | 2024-06-07 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Qwen2-72B: 28.7 (#303), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1196 | 1488 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 16.9 (#138), Qwen3.5 Max Preview: —
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Qwen3.5 Max Preview leads
Qwen2-72B: 22.2 (#184), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1483 |
| Epoch Capabilities Index | 125.27 | — |
Math Qwen3.5 Max Preview leads
Qwen2-72B: 27.9 (#232), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1235 | 1473 |
| MATH Level 5 | 39.1% | — |
Knowledge Qwen3.5 Max Preview leads
Qwen2-72B: 21.2 (#270), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1171 | 1489 |
| GPQA Diamond | 40.8% | — |
| MMLU | 82.4% | — |
Multilingual Qwen3.5 Max Preview leads
Qwen2-72B: 36.0 (#239), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1176 | 1465 |
| LMArena Chinese | 1240 | 1534 |
| LMArena French | 1169 | 1483 |
| LMArena German | 1151 | 1487 |
| LMArena Japanese | 1111 | 1497 |
| LMArena Korean | 1083 | 1438 |
| LMArena Russian | 1169 | 1472 |
| LMArena Spanish | 1168 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Qwen2-72B: 62.0 (#236), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1181 | 1467 |
Long Context Qwen3.5 Max Preview leads
Qwen2-72B: 36.1 (#230), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1193 | 1477 |
Writing & Preference Qwen3.5 Max Preview leads
Qwen2-72B: 41.0 (#236), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Qwen2-72B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1203 | 1471 |
| LMArena Creative Writing | 1181 | 1464 |
| LMArena Multi-Turn | 1195 | 1478 |
Frequently asked questions
Is Qwen2-72B better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 29.5 on the Noometry Index.
Is Qwen2-72B or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 28.7 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.5 Max Preview has 17.