# Qwen1.5-14B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 42.3 to 32.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen1-5-14b-vs-step-3-5-flash
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Qwen1.5-14B scores higher in 0 categories and Step 3.5 Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 33.6.

## Snapshot

| | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 32.7 | 42.3 |
| Rank | 253 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Qwen1.5-14B: 33.1 (#263)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1138 | 1436 |

## Reasoning

- Qwen1.5-14B: 21.4 (#223)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1411 |
| NYT Connections (extended) | — | 28.4% |

## Math

- Qwen1.5-14B: 32.4 (#215)
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1125 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Qwen1.5-14B: 29.8 (#232)
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1094 | 1421 |
| MMLU | 68.6% | — |

## Multilingual

- Qwen1.5-14B: 30.7 (#262)
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1095 | 1385 |
| LMArena Chinese | 1147 | 1447 |
| LMArena French | 1116 | 1421 |
| LMArena German | 1043 | 1405 |
| LMArena Japanese | 1019 | 1354 |
| LMArena Russian | 1046 | 1385 |
| LMArena Spanish | 1085 | 1419 |
| LMArena Korean | — | 1352 |

## Instruction Following

- Qwen1.5-14B: 56.8 (#271)
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1102 | 1385 |

## Long Context

- Qwen1.5-14B: 33.7 (#257)
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1113 | 1402 |

## Writing & Preference

- Qwen1.5-14B: 33.6 (#276)
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Qwen1.5-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1128 | 1403 |
| LMArena Creative Writing | 1091 | 1357 |
| LMArena Multi-Turn | 1110 | 1405 |

## FAQ

### Is Qwen1.5-14B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 32.7 on the Noometry Index.

### Is Qwen1.5-14B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 33.1 in the Noometry coding category.

### How many benchmarks do Qwen1.5-14B and Step 3.5 Flash share?

16 benchmarks have published results for both models. Qwen1.5-14B has 17 scored results on Noometry and Step 3.5 Flash has 19.