# Granite 4.2 3b vs Magistral Medium

> Granite 4.2 3b is the stronger model overall, scoring 39.0 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 6 categories and Magistral Medium in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.2 3b leads 25.0 to 8.7.

## Snapshot

| | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 39.0 | 34.8 |
| Rank | 163 | 224 |
| Context | — | 128K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 39.4 (#146)
- Magistral Medium: 38.6 (#161)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Coding | 1363 | 1319 |
| SciCode | — | 39.2% |

## Reasoning

- Granite 4.2 3b: 25.0 (#136)
- Magistral Medium: 8.7 (#342)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |

## Math

- Granite 4.2 3b: —
- Magistral Medium: 32.4 (#187)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Math | — | 1249 |

## Knowledge

- Granite 4.2 3b: 35.6 (#169)
- Magistral Medium: 32.9 (#199)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Expert | 1313 | 1222 |

## Multilingual

- Granite 4.2 3b: 42.4 (#193)
- Magistral Medium: 39.8 (#219)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1268 | 1232 |
| LMArena Chinese | 1268 | 1225 |
| LMArena Russian | 1249 | 1224 |
| LMArena French | — | 1268 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1176 |
| LMArena Korean | — | 1125 |
| LMArena Spanish | — | 1269 |

## Instruction Following

- Granite 4.2 3b: 67.2 (#195)
- Magistral Medium: 66.2 (#207)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1271 | 1254 |

## Long Context

- Granite 4.2 3b: 39.3 (#179)
- Magistral Medium: 39.3 (#178)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1293 | 1295 |

## Writing & Preference

- Granite 4.2 3b: 47.9 (#202)
- Magistral Medium: 46.5 (#214)

| Benchmark | Granite 4.2 3b | Magistral Medium |
|---|---|---|
| LMArena Text | 1295 | 1255 |
| LMArena Creative Writing | 1215 | 1245 |
| LMArena Multi-Turn | 1293 | 1275 |

## FAQ

### Is Granite 4.2 3b better than Magistral Medium?

Granite 4.2 3b is the stronger model overall, scoring 39.0 to 34.8 on the Noometry Index.

### Is Granite 4.2 3b or Magistral Medium better for coding?

They score almost the same on coding (39.4 vs 38.6); test both on your own repository before choosing.

### How many benchmarks do Granite 4.2 3b and Magistral Medium share?

11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Magistral Medium has 22.