# Qwen1.5-72B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen1-5-72b-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Qwen1.5-72B scores higher in 1 category and Step 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3.5 Flash leads 39.0 to 11.5.

## Snapshot

| | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 30.3 | 41.7 |
| Rank | 282 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Qwen1.5-72B: 31.4 (#272)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1166 | 1436 |
| BigCodeBench Instruct | 33.2% | — |
| BigCodeBench Complete | 40.3% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |

## Reasoning

- Qwen1.5-72B: 21.2 (#201)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1148 | 1411 |
| NYT Connections (extended) | — | 28.4% |

## Math

- Qwen1.5-72B: 30.7 (#205)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1164 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Qwen1.5-72B: 11.5 (#295)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1136 | 1422 |
| GPQA Diamond | 28.8% | — |

## Multilingual

- Qwen1.5-72B: 33.4 (#248)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1135 | 1386 |
| LMArena Chinese | 1186 | 1448 |
| LMArena French | 1158 | 1421 |
| LMArena German | 1084 | 1404 |
| LMArena Japanese | 1061 | 1353 |
| LMArena Korean | 1049 | 1350 |
| LMArena Russian | 1104 | 1385 |
| LMArena Spanish | 1110 | 1419 |

## Instruction Following

- Qwen1.5-72B: 59.6 (#251)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1142 | 1385 |

## Long Context

- Qwen1.5-72B: 35.0 (#238)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1157 | 1402 |

## Writing & Preference

- Qwen1.5-72B: 37.4 (#253)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Qwen1.5-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1166 | 1403 |
| LMArena Creative Writing | 1137 | 1357 |
| LMArena Multi-Turn | 1160 | 1405 |

## FAQ

### Is Qwen1.5-72B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 30.3 on the Noometry Index.

### Is Qwen1.5-72B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 31.4 in the Noometry coding category.

### How many benchmarks do Qwen1.5-72B and Step 3.5 Flash share?

17 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Step 3.5 Flash has 19.
