# Qwen3.5 Plus vs Step 3

> Qwen3.5 Plus is the stronger model overall, scoring 42.9 to 40.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-5-plus-vs-step-3
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Qwen3.5 Plus leads 49.6 to 37.6.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.5 Plus | Step 3 |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 42.9 | 40.5 |
| Rank | 106 | 149 |
| Context | 1M | — |
| Input $/M | $0.40 | — |
| Output $/M | $2.40 | — |
| Weights | Proprietary | Open |

## Coding

- Qwen3.5 Plus: —
- Step 3: 40.1 (#147)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
| ALE-Bench | 621.92 | — |

## Agentic & Tool Use

- Qwen3.5 Plus: —
- Step 3: —

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| Vending-Bench 2 | 0.54 | — |

## Reasoning

- Qwen3.5 Plus: 32.8 (#74)
- Step 3: 28.4 (#105)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 22% | — |
| LMArena Hard Prompts | — | 1355 |
| Mystery Game Puzzles | 17% | — |
| DTBench | 80.5% | — |
| LMCA | 36.4% | — |
| Epoch Capabilities Index | 146.78 | — |

## Math

- Qwen3.5 Plus: 49.6 (#61)
- Step 3: 37.6 (#148)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| LMArena Math | — | 1366 |
| FrontierMath (Feb 2025 set) | 21% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Qwen3.5 Plus: 46.0 (#83)
- Step 3: 36.8 (#164)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| GPQA Diamond | 84.8% | — |
| SimpleQA Verified | 25.4% | — |
| Vectara Hallucination Rate | 10.7% | — |
| LMArena Expert | — | 1333 |

## Multimodal

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

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

## Multilingual

- Qwen3.5 Plus: —
- Step 3: 46.3 (#159)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- Qwen3.5 Plus: —
- Step 3: 70.4 (#164)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |

## Long Context

- Qwen3.5 Plus: 43.0 (#113)
- Step 3: 40.3 (#157)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| CL-bench | 19.8% | — |
| CL-bench Life | 12.4% | — |
| LMArena Longer Query | — | 1326 |

## Writing & Preference

- Qwen3.5 Plus: —
- Step 3: 54.3 (#151)

| Benchmark | Qwen3.5 Plus | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |

## FAQ

### Is Qwen3.5 Plus better than Step 3?

Qwen3.5 Plus is the stronger model overall, scoring 42.9 to 40.5 on the Noometry Index.

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

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