# Qwen3.7 Plus vs Step 3

> Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 40.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-7-plus-vs-step-3
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Qwen3.7 Plus scores higher in 8 categories and Step 3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 36.8.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.7 Plus | Step 3 |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 45.3 | 40.5 |
| Rank | 72 | 149 |
| Context | 1M | — |
| Input $/M | $0.40 | — |
| Output $/M | $1.60 | — |
| Weights | Proprietary | Open |

## Coding

- Qwen3.7 Plus: 36.6 (#206)
- Step 3: 40.1 (#147)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Coding | 1473 | 1367 |
| FrontierCode | 10.2% | — |
| SciCode | 45.5% | — |

## Agentic & Tool Use

- Qwen3.7 Plus: 21.4 (#138)
- Step 3: —

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| OSWorld 2.0 | 2.8% | — |

## Reasoning

- Qwen3.7 Plus: 39.3 (#59)
- Step 3: 28.4 (#105)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1460 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 74.8% | — |
| CritPt | 9.1% | — |
| Chess Puzzles | 24% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 84% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 147.37 | — |

## Math

- Qwen3.7 Plus: 50.5 (#56)
- Step 3: 37.6 (#148)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Math | 1466 | 1366 |
| FrontierMath (Tiers 1-3) | 34.4% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |

## Knowledge

- Qwen3.7 Plus: 54.9 (#51)
- Step 3: 36.8 (#164)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Expert | 1467 | 1333 |
| GPQA Diamond | 87.9% | — |

## Multimodal

- Qwen3.7 Plus: 41.8 (#33)
- Step 3: 35.5 (#86)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Vision | 1279 | 1177 |
| LMArena Document | 1444 | — |

## Multilingual

- Qwen3.7 Plus: 54.8 (#38)
- Step 3: 46.3 (#159)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Non-English | 1445 | 1327 |
| LMArena Chinese | 1510 | 1397 |
| LMArena German | 1471 | 1371 |
| LMArena Korean | 1415 | 1269 |
| LMArena Russian | 1457 | 1331 |
| LMArena Spanish | 1457 | 1371 |
| LMArena French | 1473 | — |
| LMArena Japanese | 1413 | — |

## Instruction Following

- Qwen3.7 Plus: 75.8 (#52)
- Step 3: 70.4 (#164)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1440 | 1332 |

## Long Context

- Qwen3.7 Plus: 44.5 (#65)
- Step 3: 40.3 (#157)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Longer Query | 1455 | 1326 |

## Writing & Preference

- Qwen3.7 Plus: 64.3 (#56)
- Step 3: 54.3 (#151)

| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Text | 1455 | 1350 |
| LMArena Creative Writing | 1439 | 1321 |
| LMArena Multi-Turn | 1460 | 1341 |

## FAQ

### Is Qwen3.7 Plus better than Step 3?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 40.5 on the Noometry Index.

### Is Qwen3.7 Plus or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 36.6 in the Noometry coding category.

### How many benchmarks do Qwen3.7 Plus and Step 3 share?

16 benchmarks have published results for both models. Qwen3.7 Plus has 32 scored results on Noometry and Step 3 has 17.