# Hy4 preview vs Magistral Medium

> Hy4 preview is the stronger model overall, scoring 45.3 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy4-preview-vs-magistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Hy4 preview leads 31.9 to 8.6.
- Hy4 preview is cheaper at $0.83 / $2.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | Hy4 preview | Magistral Medium |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 45.3 | 35.2 |
| Rank | 73 | 227 |
| Context | 1.05M | 262K |
| Input $/M | $0.83 | $2 |
| Output $/M | $2.50 | $5 |
| Weights | Open | Open |

## Coding

- Hy4 preview: 51.6 (#38)
- Magistral Medium: 39.1 (#161)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| LMArena WebDev | 1632 | — |
| SciCode | — | 39.2% |
| LMArena Coding | — | 1319 |

## Reasoning

- Hy4 preview: 31.9 (#79)
- Magistral Medium: 8.6 (#348)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 68.2% | — |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| LMArena Hard Prompts | — | 1267 |

## Math

- Hy4 preview: 55.7 (#42)
- Magistral Medium: 35.1 (#189)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1250 |

## Knowledge

- Hy4 preview: —
- Magistral Medium: 33.5 (#202)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| LMArena Expert | — | 1223 |

## Multilingual

- Hy4 preview: —
- Magistral Medium: 39.6 (#224)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| LMArena Non-English | — | 1232 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Russian | — | 1224 |
| LMArena Spanish | — | 1271 |

## Instruction Following

- Hy4 preview: —
- Magistral Medium: 66.0 (#211)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1254 |

## Long Context

- Hy4 preview: —
- Magistral Medium: 39.3 (#183)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1295 |

## Writing & Preference

- Hy4 preview: —
- Magistral Medium: 46.3 (#219)

| Benchmark | Hy4 preview | Magistral Medium |
|---|---|---|
| LMArena Text | — | 1255 |
| LMArena Creative Writing | — | 1245 |
| LMArena Multi-Turn | — | 1275 |

## FAQ

### Is Hy4 preview better than Magistral Medium?

Hy4 preview is the stronger model overall, scoring 45.3 to 35.2 on the Noometry Index.

### Which is cheaper, Hy4 preview or Magistral Medium?

Hy4 preview is cheaper. It lists at $0.83 per million input tokens and $2.50 per million output tokens; Magistral Medium lists at $2 and $5.

### Is Hy4 preview or Magistral Medium better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 262K.

### How many benchmarks do Hy4 preview and Magistral Medium share?

0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Magistral Medium has 22.