# Granite 4.0 H Small vs Magistral Medium

> Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-magistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 2 categories and Magistral Medium in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.0 H Small leads 24.4 to 8.6.

## Snapshot

| | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 36.5 | 35.2 |
| Rank | 214 | 227 |
| Context | — | 262K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 36.4 (#209)
- Magistral Medium: 39.1 (#161)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Coding | 1249 | 1319 |
| SciCode | — | 39.2% |

## Reasoning

- Granite 4.0 H Small: 24.4 (#163)
- Magistral Medium: 8.6 (#348)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |

## Math

- Granite 4.0 H Small: 31.4 (#223)
- Magistral Medium: 35.1 (#189)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Math | 1247 | 1250 |
| Omni-MATH | 29.6% | — |

## Knowledge

- Granite 4.0 H Small: 32.0 (#215)
- Magistral Medium: 33.5 (#202)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Expert | 1251 | 1223 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |

## Multilingual

- Granite 4.0 H Small: 38.6 (#228)
- Magistral Medium: 39.6 (#224)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1216 | 1232 |
| LMArena Chinese | 1249 | 1227 |
| LMArena Russian | 1201 | 1224 |
| LMArena Spanish | 1258 | 1271 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |

## Instruction Following

- Granite 4.0 H Small: 68.7 (#183)
- Magistral Medium: 66.0 (#211)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1222 | 1254 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.7 (#213)
- Magistral Medium: 39.3 (#183)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1242 | 1295 |

## Writing & Preference

- Granite 4.0 H Small: 43.8 (#227)
- Magistral Medium: 46.3 (#219)

| Benchmark | Granite 4.0 H Small | Magistral Medium |
|---|---|---|
| LMArena Text | 1241 | 1255 |
| LMArena Creative Writing | 1211 | 1245 |
| LMArena Multi-Turn | 1242 | 1275 |
| WildBench | 73.9% | — |

## FAQ

### Is Granite 4.0 H Small better than Magistral Medium?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 35.2 on the Noometry Index.

### Is Granite 4.0 H Small or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 36.4 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Magistral Medium share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Magistral Medium has 22.