# Qwen3.5 Max Preview vs Step 3

> Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 40.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-5-max-preview-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Qwen3.5 Max Preview scores higher in 8 categories and Step 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 Max Preview leads 66.0 to 54.3.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 45.3 | 40.5 |
| Rank | 71 | 149 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Qwen3.5 Max Preview: 44.0 (#77)
- Step 3: 40.1 (#147)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Coding | 1487 | 1367 |

## Reasoning

- Qwen3.5 Max Preview: 30.8 (#84)
- Step 3: 28.4 (#105)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Qwen3.5 Max Preview: 40.1 (#94)
- Step 3: 37.6 (#148)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Math | 1474 | 1366 |

## Knowledge

- Qwen3.5 Max Preview: 41.8 (#107)
- Step 3: 36.8 (#164)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Expert | 1489 | 1333 |

## Multimodal

- Qwen3.5 Max Preview: —
- Step 3: 35.5 (#86)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Qwen3.5 Max Preview: 56.2 (#22)
- Step 3: 46.3 (#159)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Non-English | 1465 | 1327 |
| LMArena Chinese | 1534 | 1397 |
| LMArena German | 1487 | 1371 |
| LMArena Korean | 1438 | 1269 |
| LMArena Russian | 1471 | 1331 |
| LMArena Spanish | 1470 | 1371 |
| LMArena French | 1484 | — |
| LMArena Japanese | 1495 | — |

## Instruction Following

- Qwen3.5 Max Preview: 77.0 (#31)
- Step 3: 70.4 (#164)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1467 | 1332 |

## Long Context

- Qwen3.5 Max Preview: 45.2 (#45)
- Step 3: 40.3 (#157)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Longer Query | 1476 | 1326 |

## Writing & Preference

- Qwen3.5 Max Preview: 66.0 (#41)
- Step 3: 54.3 (#151)

| Benchmark | Qwen3.5 Max Preview | Step 3 |
|---|---|---|
| LMArena Text | 1470 | 1350 |
| LMArena Creative Writing | 1464 | 1321 |
| LMArena Multi-Turn | 1478 | 1341 |

## FAQ

### Is Qwen3.5 Max Preview better than Step 3?

Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 40.5 on the Noometry Index.

### Is Qwen3.5 Max Preview or Step 3 better for coding?

Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.

### How many benchmarks do Qwen3.5 Max Preview and Step 3 share?

15 benchmarks have published results for both models. Qwen3.5 Max Preview has 17 scored results on Noometry and Step 3 has 17.