# Mistral Large 4 vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 43.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-4-vs-step-5-preview
- Last updated: 2026-10-11
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Mistral Large 4 scores higher in 0 categories and Step 5 Preview in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 22.5.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Mistral Large 4 accepts more context: 1.05M tokens versus 1.02M.

## Snapshot

| | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 43.1 | 47.9 |
| Rank | 99 | 58 |
| Context | 1.05M | 1.02M |
| Input $/M | $0.68 | $1 |
| Output $/M | $2.09 | $2.70 |
| Weights | Proprietary | Proprietary |

## Coding

- Mistral Large 4: 48.6 (#57)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1541 | 1564 |
| LMArena Coding | 1475 | 1480 |
| SciCode | — | 58.9% |

## Reasoning

- Mistral Large 4: 22.5 (#192)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1465 |
| NYT Connections (extended) | 27.4% | — |
| CritPt | — | 20.9% |

## Math

- Mistral Large 4: 40.4 (#91)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1488 | 1470 |
| ProofBench | — | 42% |

## Knowledge

- Mistral Large 4: 36.6 (#166)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1447 | 1470 |
| SimpleQA Verified | 20% | — |

## Multimodal

- Mistral Large 4: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Mistral Large 4: 52.6 (#82)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1415 | 1432 |
| LMArena Chinese | 1491 | 1519 |
| LMArena Russian | 1414 | 1436 |
| LMArena Spanish | — | 1439 |

## Instruction Following

- Mistral Large 4: 75.0 (#76)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1424 | 1444 |

## Long Context

- Mistral Large 4: 43.6 (#89)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1429 | 1455 |

## Writing & Preference

- Mistral Large 4: 60.4 (#97)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1427 | 1442 |
| LMArena Creative Writing | 1361 | 1410 |
| LMArena Multi-Turn | 1424 | 1447 |

## FAQ

### Is Mistral Large 4 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 43.1 on the Noometry Index.

### Which is cheaper, Mistral Large 4 or Step 5 Preview?

Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is Mistral Large 4 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 48.6 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 1.02M.

### How many benchmarks do Mistral Large 4 and Step 5 Preview share?

13 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Step 5 Preview has 18.