# Magistral Medium vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3.5 Flash leads 21.2 to 8.7.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Step 3.5 Flash accepts more context: 256K tokens versus 128K.

## Snapshot

| | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 34.8 | 41.7 |
| Rank | 224 | 116 |
| Context | 128K | 256K |
| Input $/M | $2 | $0.10 |
| Output $/M | $5 | $0.30 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1319 | 1436 |
| SciCode | 39.2% | — |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1411 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |

## Math

- Magistral Medium: 32.4 (#187)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1249 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1222 | 1422 |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1232 | 1386 |
| LMArena Chinese | 1225 | 1448 |
| LMArena French | 1268 | 1421 |
| LMArena German | 1248 | 1404 |
| LMArena Japanese | 1176 | 1353 |
| LMArena Korean | 1125 | 1350 |
| LMArena Russian | 1224 | 1385 |
| LMArena Spanish | 1269 | 1419 |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1254 | 1385 |

## Long Context

- Magistral Medium: 39.3 (#178)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1295 | 1402 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Magistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1255 | 1403 |
| LMArena Creative Writing | 1245 | 1357 |
| LMArena Multi-Turn | 1275 | 1405 |

## FAQ

### Is Magistral Medium better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 34.8 on the Noometry Index.

### Which is cheaper, Magistral Medium 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; Magistral Medium lists at $2 and $5.

### Is Magistral Medium or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 38.6 in the Noometry coding category.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 128K.

### How many benchmarks do Magistral Medium and Step 3.5 Flash share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Step 3.5 Flash has 19.