# Granite 4.0 H Small vs Mistral

> Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-mistral
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Granite 4.0 H Small scores higher in 8 categories and Mistral in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.7 to 52.6.
- The biggest single-benchmark swing is IFEval: 89% for Granite 4.0 H Small and 56.8% for Mistral.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 H Small | Mistral |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 36.5 | 29.9 |
| Rank | 214 | 303 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 H Small: 36.4 (#209)
- Mistral: 33.8 (#250)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| LMArena Coding | 1249 | 1162 |

## Reasoning

- Granite 4.0 H Small: 24.4 (#163)
- Mistral: 22.2 (#200)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1149 |

## Math

- Granite 4.0 H Small: 31.4 (#223)
- Mistral: 22.3 (#278)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| Omni-MATH | 29.6% | 7.2% |
| LMArena Math | 1247 | 1180 |

## Knowledge

- Granite 4.0 H Small: 32.0 (#215)
- Mistral: 16.6 (#288)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| MMLU-Pro | 56.9% | 27.7% |
| GPQA (HELM) | 38.3% | 30.3% |
| LMArena Expert | 1251 | 1125 |
| Vectara Hallucination Rate | 5.2% | — |

## Multilingual

- Granite 4.0 H Small: 38.6 (#228)
- Mistral: 32.8 (#254)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| LMArena Non-English | 1216 | 1129 |
| LMArena Chinese | 1249 | 1109 |
| LMArena Russian | 1201 | 1168 |
| LMArena Spanish | 1258 | 1143 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |

## Instruction Following

- Granite 4.0 H Small: 68.7 (#183)
- Mistral: 52.6 (#288)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| IFEval | 89% | 56.8% |
| LMArena Instruction Following | 1222 | 1152 |

## Long Context

- Granite 4.0 H Small: 37.7 (#213)
- Mistral: 35.0 (#245)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| LMArena Longer Query | 1242 | 1153 |

## Writing & Preference

- Granite 4.0 H Small: 43.8 (#227)
- Mistral: 37.0 (#260)

| Benchmark | Granite 4.0 H Small | Mistral |
|---|---|---|
| LMArena Text | 1241 | 1165 |
| LMArena Creative Writing | 1211 | 1158 |
| WildBench | 73.9% | 66% |
| LMArena Multi-Turn | 1242 | 1147 |

## FAQ

### Is Granite 4.0 H Small better than Mistral?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.9 on the Noometry Index.

### Is Granite 4.0 H Small or Mistral better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 33.8 in the Noometry coding category.

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

18 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Mistral has 22.