Model comparison
Qwen Max vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 34.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen Max 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 48.0.
Side by side
| Qwen Max | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.4 | 44.7 |
| Released | 2024-04-03 | — |
| Weights | Proprietary | Proprietary |
| Context window | 33K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.60 | — |
| Output $ / M tokens | $6.40 | — |
| Results tracked | 23 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Qwen Max: 30.3 (#288), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1288 | 1488 |
| Aider Polyglot | 21.8% | — |
Reasoning Qwen3.5 Max Preview leads
Qwen Max: 24.1 (#154), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1270 | 1483 |
Math Qwen3.5 Max Preview leads
Qwen Max: 21.0 (#272), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1275 | 1473 |
| OTIS Mock AIME 2024-2025 | 16.1% | — |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Qwen3.5 Max Preview leads
Qwen Max: 30.3 (#222), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1248 | 1489 |
| GPQA Diamond | 56.1% | — |
Multilingual Qwen3.5 Max Preview leads
Qwen Max: 42.0 (#197), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1263 | 1465 |
| LMArena Chinese | 1254 | 1534 |
| LMArena French | 1329 | 1483 |
| LMArena German | 1254 | 1487 |
| LMArena Japanese | 1205 | 1497 |
| LMArena Korean | 1141 | 1438 |
| LMArena Russian | 1274 | 1472 |
| LMArena Spanish | 1290 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Qwen Max: 66.7 (#203), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1262 | 1467 |
Long Context Qwen3.5 Max Preview leads
Qwen Max: 39.4 (#175), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1289 | 1477 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Qwen3.5 Max Preview leads
Qwen Max: 48.0 (#200), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Qwen Max | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1282 | 1471 |
| LMArena Creative Writing | 1248 | 1464 |
| LMArena Multi-Turn | 1277 | 1478 |
Frequently asked questions
Is Qwen Max better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 34.4 on the Noometry Index.
Is Qwen Max or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 30.3 in the Noometry coding category.
How many benchmarks do Qwen Max and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen3.5 Max Preview has 17.