# Qwen1.5 4b Chat vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen1-5-4b-chat-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Qwen1.5 4b Chat scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 23.8.

## Snapshot

| | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 28.8 | 40.5 |
| Rank | 322 | 149 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Qwen1.5 4b Chat: 29.1 (#308)
- Step 3: 40.1 (#147)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Coding | 999 | 1367 |

## Reasoning

- Qwen1.5 4b Chat: 18.5 (#279)
- Step 3: 28.4 (#105)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 976 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Qwen1.5 4b Chat: 30.4 (#234)
- Step 3: 37.6 (#148)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Math | 1026 | 1366 |

## Knowledge

- Qwen1.5 4b Chat: 26.7 (#255)
- Step 3: 36.8 (#164)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Expert | 980 | 1333 |

## Multimodal

- Qwen1.5 4b Chat: —
- Step 3: 35.5 (#86)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Qwen1.5 4b Chat: 24.1 (#290)
- Step 3: 46.3 (#159)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Non-English | 979 | 1327 |
| LMArena Chinese | 1024 | 1397 |
| LMArena German | 902 | 1371 |
| LMArena Russian | 952 | 1331 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- Qwen1.5 4b Chat: 49.0 (#300)
- Step 3: 70.4 (#164)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Instruction Following | 978 | 1332 |

## Long Context

- Qwen1.5 4b Chat: 30.1 (#290)
- Step 3: 40.3 (#157)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Longer Query | 988 | 1326 |

## Writing & Preference

- Qwen1.5 4b Chat: 23.8 (#309)
- Step 3: 54.3 (#151)

| Benchmark | Qwen1.5 4b Chat | Step 3 |
|---|---|---|
| LMArena Text | 997 | 1350 |
| LMArena Creative Writing | 969 | 1321 |
| LMArena Multi-Turn | 977 | 1341 |

## FAQ

### Is Qwen1.5 4b Chat better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 28.8 on the Noometry Index.

### Is Qwen1.5 4b Chat or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 29.1 in the Noometry coding category.

### How many benchmarks do Qwen1.5 4b Chat and Step 3 share?

13 benchmarks have published results for both models. Qwen1.5 4b Chat has 13 scored results on Noometry and Step 3 has 17.