# Qwen2.5 72B Instruct vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-72b-instruct-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 19.3.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.9 | 47.9 |
| Rank | 267 | 58 |
| Context | 131K | 1.02M |
| Input $/M | $1.40 | $1 |
| Output $/M | $5.60 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Qwen2.5 72B Instruct: 33.2 (#260)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1292 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |

## Agentic & Tool Use

- Qwen2.5 72B Instruct: 22.1 (#133)
- Step 5 Preview: —

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |

## Reasoning

- Qwen2.5 72B Instruct: 22.3 (#199)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1465 |
| CritPt | — | 20.9% |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |

## Math

- Qwen2.5 72B Instruct: 19.3 (#287)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1283 | 1470 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| ProofBench | — | 42% |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |

## Knowledge

- Qwen2.5 72B Instruct: 27.0 (#253)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1245 | 1470 |
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |

## Multimodal

- Qwen2.5 72B Instruct: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Qwen2.5 72B Instruct: 41.0 (#213)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1252 | 1432 |
| LMArena Chinese | 1272 | 1519 |
| LMArena Russian | 1264 | 1436 |
| LMArena Spanish | 1256 | 1439 |
| LMArena French | 1280 | — |
| LMArena German | 1234 | — |
| LMArena Japanese | 1180 | — |
| LMArena Korean | 1188 | — |

## Instruction Following

- Qwen2.5 72B Instruct: 65.5 (#221)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1254 | 1444 |
| IFEval | 80.6% | — |

## Long Context

- Qwen2.5 72B Instruct: 38.9 (#188)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1282 | 1455 |

## Writing & Preference

- Qwen2.5 72B Instruct: 46.7 (#215)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1269 | 1442 |
| LMArena Creative Writing | 1221 | 1410 |
| LMArena Multi-Turn | 1272 | 1447 |
| WildBench | 80.2% | — |

## FAQ

### Is Qwen2.5 72B Instruct better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 31.9 on the Noometry Index.

### Which is cheaper, Qwen2.5 72B Instruct or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is Qwen2.5 72B Instruct or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 131K.

### How many benchmarks do Qwen2.5 72B Instruct and Step 5 Preview share?

13 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Step 5 Preview has 18.