Model comparison
Qwen3 32B vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 38.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Qwen3 32B scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 Max Preview leads 66.1 to 53.1.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Qwen3 32B | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.8 | 44.7 |
| Released | 2025-04 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| 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
Qwen3 32B: 37.3 (#184), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1358 | 1488 |
| Aider Polyglot | 40% | — |
| SciCode | 35.4% | — |
Agentic & Tool Use Not comparable
Qwen3 32B: 32.3 (#58), Qwen3.5 Max Preview: —
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 48.7% | — |
Reasoning Qwen3.5 Max Preview leads
Qwen3 32B: 19.6 (#233), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1483 |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 5% | — |
| DTBench | 67.5% | — |
| LMCA | 17.3% | — |
| Epoch Capabilities Index | 138.51 | — |
Math Too close to call
Qwen3 32B: 37.9 (#89), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1399 | 1473 |
| OTIS Mock AIME 2024-2025 | 66.9% | — |
Knowledge Qwen3.5 Max Preview leads
Qwen3 32B: 40.0 (#112), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1362 | 1489 |
| GPQA Diamond | 65.7% | — |
| Vectara Hallucination Rate | 5.9% | — |
Multilingual Qwen3.5 Max Preview leads
Qwen3 32B: 45.8 (#162), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1317 | 1465 |
| LMArena Chinese | 1357 | 1534 |
| LMArena German | 1341 | 1487 |
| LMArena Russian | 1311 | 1472 |
| LMArena French | — | 1483 |
| LMArena Japanese | — | 1497 |
| LMArena Korean | — | 1438 |
| LMArena Spanish | — | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Qwen3 32B: 69.1 (#174), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1305 | 1467 |
Long Context Qwen3.5 Max Preview leads
Qwen3 32B: 43.7 (#83), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1327 | 1477 |
| Fiction.LiveBench | 74.2% | — |
Writing & Preference Qwen3.5 Max Preview leads
Qwen3 32B: 53.1 (#158), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Qwen3 32B | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1340 | 1471 |
| LMArena Creative Writing | 1297 | 1464 |
| LMArena Multi-Turn | 1331 | 1478 |
Frequently asked questions
Is Qwen3 32B better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 38.8 on the Noometry Index.
Is Qwen3 32B or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 37.3 in the Noometry coding category.
How many benchmarks do Qwen3 32B and Qwen3.5 Max Preview share?
13 benchmarks have published results for both models. Qwen3 32B has 26 scored results on Noometry and Qwen3.5 Max Preview has 17.