# Qwen3.6 Max Preview vs Step 3

> Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 40.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-6-max-preview-vs-step-3
- Last updated: 2026-10-11
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Qwen3.6 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 knowledge, where Qwen3.6 Max Preview leads 57.6 to 36.8.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 51.5 | 40.5 |
| Rank | 43 | 149 |
| Context | 262K | — |
| Input $/M | $1.30 | — |
| Output $/M | $7.80 | — |
| Weights | Proprietary | Open |

## Coding

- Qwen3.6 Max Preview: 48.7 (#54)
- Step 3: 40.1 (#147)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Coding | 1471 | 1367 |
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1482 | — |

## Agentic & Tool Use

- Qwen3.6 Max Preview: —
- Step 3: —

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| Vending-Bench 2 | 4,254 | — |

## Reasoning

- Qwen3.6 Max Preview: 41.7 (#53)
- Step 3: 28.4 (#105)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1355 |
| SimpleBench | 63% | — |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 74.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 87.2% | — |
| LMCA | 42.5% | — |
| Epoch Capabilities Index | 149.24 | — |

## Math

- Qwen3.6 Max Preview: 54.1 (#46)
- Step 3: 37.6 (#148)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Math | 1465 | 1366 |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| FrontierMath (Feb 2025 set) | 23.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Qwen3.6 Max Preview: 57.6 (#39)
- Step 3: 36.8 (#164)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Expert | 1478 | 1333 |
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 52% | — |

## Multimodal

- Qwen3.6 Max Preview: —
- Step 3: 35.5 (#86)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Qwen3.6 Max Preview: 54.2 (#48)
- Step 3: 46.3 (#159)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Non-English | 1437 | 1327 |
| LMArena Chinese | 1487 | 1397 |
| LMArena Russian | 1445 | 1331 |
| LMArena Spanish | 1454 | 1371 |
| LMArena French | 1449 | — |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |

## Instruction Following

- Qwen3.6 Max Preview: 75.7 (#55)
- Step 3: 70.4 (#164)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1438 | 1332 |

## Long Context

- Qwen3.6 Max Preview: 44.6 (#61)
- Step 3: 40.3 (#157)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Longer Query | 1457 | 1326 |

## Writing & Preference

- Qwen3.6 Max Preview: 63.8 (#60)
- Step 3: 54.3 (#151)

| Benchmark | Qwen3.6 Max Preview | Step 3 |
|---|---|---|
| LMArena Text | 1447 | 1350 |
| LMArena Creative Writing | 1435 | 1321 |
| LMArena Multi-Turn | 1456 | 1341 |

## FAQ

### Is Qwen3.6 Max Preview better than Step 3?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 40.5 on the Noometry Index.

### Is Qwen3.6 Max Preview or Step 3 better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 40.1 in the Noometry coding category.

### How many benchmarks do Qwen3.6 Max Preview and Step 3 share?

13 benchmarks have published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and Step 3 has 17.