Model comparison
Qwen Max vs Qwen1.5-32B
Qwen Max is the stronger model overall, scoring 34.7 to 30.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen Max scores higher in 6 categories and Qwen1.5-32B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 56.1% for Qwen Max and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Qwen Max | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.7 | 30.5 |
| Released | 2024-04-03 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | 33K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.60 | — |
| Output $ / M tokens | $6.40 | — |
| Results tracked | 23 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen Max: 30.7 (#292), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1288 | 1155 |
| Aider Polyglot | 21.8% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen Max leads
Qwen Max: 25.1 (#151), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1130 |
Math Qwen1.5-32B leads
Qwen Max: 22.3 (#276), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1275 | 1155 |
| OTIS Mock AIME 2024-2025 | 16.1% | — |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Qwen Max leads
Qwen Max: 30.3 (#228), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 56.1% | 30.7% |
| LMArena Expert | 1248 | 1126 |
| MMLU | — | 74.4% |
Multilingual Qwen Max leads
Qwen Max: 41.8 (#202), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1263 | 1106 |
| LMArena Chinese | 1254 | 1177 |
| LMArena French | 1330 | 1101 |
| LMArena German | 1254 | 1058 |
| LMArena Japanese | 1205 | 1027 |
| LMArena Korean | 1142 | 1008 |
| LMArena Russian | 1274 | 1073 |
| LMArena Spanish | 1290 | 1089 |
Instruction Following Qwen Max leads
Qwen Max: 66.5 (#208), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1262 | 1116 |
Long Context Qwen Max leads
Qwen Max: 39.4 (#180), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1288 | 1146 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Qwen Max leads
Qwen Max: 47.8 (#205), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Qwen Max | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1282 | 1137 |
| LMArena Creative Writing | 1248 | 1083 |
| LMArena Multi-Turn | 1277 | 1140 |
Frequently asked questions
Is Qwen Max better than Qwen1.5-32B?
Qwen Max is the stronger model overall, scoring 34.7 to 30.5 on the Noometry Index.
Is Qwen Max or Qwen1.5-32B better for coding?
They score almost the same on coding (30.7 vs 31.7); test both on your own repository before choosing.
How many benchmarks do Qwen Max and Qwen1.5-32B share?
18 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen1.5-32B has 21.