# Mistral Large 3 vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-3-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Mistral Large 3 scores higher in 4 categories and Step 3.5 Flash in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3.5 Flash leads 41.7 to 34.1.
- The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 256K.

## Snapshot

| | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 38.6 | 41.7 |
| Rank | 172 | 116 |
| Context | 262K | 256K |
| Input $/M | $0.25 | $0.10 |
| Output $/M | $0.75 | $0.30 |
| Weights | Open | Open |

## Coding

- Mistral Large 3: 34.1 (#230)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1447 | 1436 |
| LMArena WebDev | 1230 | — |

## Reasoning

- Mistral Large 3: 14.6 (#314)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 7.5% | 28.4% |
| LMArena Hard Prompts | 1429 | 1411 |
| Kagi LLM Benchmark | 50.9% | — |
| Thematic Generalization | 23% | — |

## Math

- Mistral Large 3: 36.0 (#131)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1415 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Mistral Large 3: 35.5 (#173)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1421 | 1422 |
| Vectara Hallucination Rate | 14.5% | — |

## Multimodal

- Mistral Large 3: 37.6 (#65)
- Step 3.5 Flash: —

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Large 3: 52.6 (#79)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1412 | 1386 |
| LMArena Chinese | 1448 | 1448 |
| LMArena French | 1456 | 1421 |
| LMArena German | 1438 | 1404 |
| LMArena Japanese | 1399 | 1353 |
| LMArena Korean | 1384 | 1350 |
| LMArena Russian | 1412 | 1385 |
| LMArena Spanish | 1437 | 1419 |

## Instruction Following

- Mistral Large 3: 74.1 (#104)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1402 | 1385 |

## Long Context

- Mistral Large 3: 43.1 (#102)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1413 | 1402 |

## Writing & Preference

- Mistral Large 3: 60.2 (#100)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Mistral Large 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1427 | 1403 |
| LMArena Creative Writing | 1385 | 1357 |
| LMArena Multi-Turn | 1429 | 1405 |
| EQ-Bench Creative Writing | 1412 | — |

## FAQ

### Is Mistral Large 3 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.6 on the Noometry Index.

### Which is cheaper, Mistral Large 3 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; Mistral Large 3 lists at $0.25 and $0.75.

### Is Mistral Large 3 or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 256K.

### How many benchmarks do Mistral Large 3 and Step 3.5 Flash share?

18 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Step 3.5 Flash has 19.