# Qwen2.5-Coder-32B vs Step 3

> Step 3 is the stronger model overall, scoring 39.9 to 32.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-coder-32b-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3 leads 39.5 to 22.4.

## Snapshot

| | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 32.9 | 39.9 |
| Rank | 239 | 145 |
| Context | 33K | — |
| Input $/M | $0.66 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- Qwen2.5-Coder-32B: 22.4 (#328)
- Step 3: 39.5 (#144)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Coding | 1276 | 1367 |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |

## Reasoning

- Qwen2.5-Coder-32B: 20.4 (#220)
- Step 3: 27.6 (#102)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 42.1% | — |
| LiveBench Data Analysis | 49.9% | — |
| Epoch Capabilities Index | 119.41 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |

## Math

- Qwen2.5-Coder-32B: 30.8 (#203)
- Step 3: 34.9 (#148)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Math | 1251 | 1366 |
| LiveBench Math | 46.6% | — |
| GSM8K | 93% | — |

## Knowledge

- Qwen2.5-Coder-32B: 32.9 (#200)
- Step 3: 36.2 (#161)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Expert | 1221 | 1333 |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |

## Multimodal

- Qwen2.5-Coder-32B: —
- Step 3: 34.9 (#81)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |

## Multilingual

- Qwen2.5-Coder-32B: 38.0 (#230)
- Step 3: 46.5 (#154)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Non-English | 1205 | 1327 |
| LMArena Chinese | 1222 | 1396 |
| LMArena Russian | 1228 | 1331 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Spanish | — | 1372 |

## Instruction Following

- Qwen2.5-Coder-32B: 61.6 (#240)
- Step 3: 70.6 (#159)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1223 | 1332 |
| LiveBench Instruction Following | 58.7% | — |

## Long Context

- Qwen2.5-Coder-32B: 37.9 (#204)
- Step 3: 40.3 (#152)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1251 | 1326 |

## Writing & Preference

- Qwen2.5-Coder-32B: 41.8 (#235)
- Step 3: 54.5 (#146)

| Benchmark | Qwen2.5-Coder-32B | Step 3 |
|---|---|---|
| LMArena Text | 1230 | 1351 |
| LMArena Creative Writing | 1174 | 1322 |
| LMArena Multi-Turn | 1222 | 1340 |
| LiveBench Language | 23.3% | — |

## FAQ

### Is Qwen2.5-Coder-32B better than Step 3?

Step 3 is the stronger model overall, scoring 39.9 to 32.9 on the Noometry Index.

### Is Qwen2.5-Coder-32B or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 39.5 versus 22.4 in the Noometry coding category.

### How many benchmarks do Qwen2.5-Coder-32B and Step 3 share?

12 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Step 3 has 17.