# Qwen2.5-VL 72B Instruct vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 42.3 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-vl-72b-instruct-vs-step-3-5-flash
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.

## Snapshot

| | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 29.9 | 42.3 |
| Rank | 302 | 116 |
| Context | 131K | 256K |
| Input $/M | $2.80 | $0.10 |
| Output $/M | $8.40 | $0.30 |
| Weights | Open | Open |

## Coding

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | — | 1436 |

## Agentic & Tool Use

- Qwen2.5-VL 72B Instruct: 18.6 (#144)
- Step 3.5 Flash: —

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| OSWorld | 5% | — |

## Reasoning

- Qwen2.5-VL 72B Instruct: 20.7 (#233)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| Kagi LLM Benchmark | 36% | — |
| NYT Connections (extended) | — | 28.4% |
| LMArena Hard Prompts | — | 1411 |

## Math

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |

## Knowledge

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1421 |

## Multimodal

- Qwen2.5-VL 72B Instruct: 33.5 (#97)
- Step 3.5 Flash: —

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1107 | — |
| Video-MME | 73.5% | — |
| GeoBench | 62% | — |
| SpatialViz-Bench | 33.3% | — |

## Multilingual

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |

## Long Context

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |

## Writing & Preference

- Qwen2.5-VL 72B Instruct: —
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Qwen2.5-VL 72B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |

## FAQ

### Is Qwen2.5-VL 72B Instruct better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 29.9 on the Noometry Index.

### Which is cheaper, Qwen2.5-VL 72B Instruct or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 131K.

### How many benchmarks do Qwen2.5-VL 72B Instruct and Step 3.5 Flash share?

0 benchmarks have published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and Step 3.5 Flash has 19.