# Pixtral Large vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 32.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/pixtral-large-vs-step-5-preview
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Pixtral Large scores higher in 0 categories and Step 5 Preview in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 32.9.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- Pixtral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Pixtral Large | Step 5 Preview |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 32.2 | 47.9 |
| Rank | 259 | 58 |
| Context | 128K | 1.02M |
| Input $/M | $2 | $1 |
| Output $/M | $6 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Pixtral Large: —
- Step 5 Preview: 51.8 (#36)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |

## Reasoning

- Pixtral Large: 21.7 (#218)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| EnigmaEval | 0.8% | — |
| LMArena Hard Prompts | — | 1465 |

## Math

- Pixtral Large: —
- Step 5 Preview: 46.1 (#72)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |

## Knowledge

- Pixtral Large: —
- Step 5 Preview: 41.2 (#112)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |

## Multimodal

- Pixtral Large: 30.6 (#111)
- Step 5 Preview: 41.0 (#41)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1089 | 1267 |

## Multilingual

- Pixtral Large: —
- Step 5 Preview: 53.8 (#54)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |

## Instruction Following

- Pixtral Large: —
- Step 5 Preview: 76.0 (#50)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |

## Long Context

- Pixtral Large: —
- Step 5 Preview: 44.5 (#64)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |

## Writing & Preference

- Pixtral Large: 32.9 (#278)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Pixtral Large | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| EQ-Bench Creative Writing | 988 | — |
| LMArena Multi-Turn | — | 1447 |

## FAQ

### Is Pixtral Large better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 32.2 on the Noometry Index.

### Which is cheaper, Pixtral Large or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Pixtral Large lists at $2 and $6.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 128K.

### How many benchmarks do Pixtral Large and Step 5 Preview share?

1 benchmark has published results for both models. Pixtral Large has 3 scored results on Noometry and Step 5 Preview has 18.