# Granite 4.0 H Small vs Mistral Large

> Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 31.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Granite 4.0 H Small scores higher in 6 categories and Mistral Large in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.0 H Small leads 29.3 to 17.1.
- The biggest single-benchmark swing is WildBench: 73.9% for Granite 4.0 H Small and 80.1% for Mistral Large.

## Snapshot

| | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 35.9 | 31.6 |
| Rank | 213 | 258 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Mistral Large: 33.8 (#240)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| LMArena Coding | 1247 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Granite 4.0 H Small: —
- Mistral Large: 28.4 (#83)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Mistral Large: 15.4 (#305)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1257 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Mistral Large: 17.1 (#285)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| Omni-MATH | 29.6% | 28.1% |
| LMArena Math | 1251 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Mistral Large: 30.0 (#224)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| MMLU-Pro | 56.9% | 59.9% |
| Vectara Hallucination Rate | 5.2% | 4.5% |
| GPQA (HELM) | 38.3% | 43.5% |
| LMArena Expert | 1244 | 1232 |
| GPQA Diamond | — | 51.3% |
| Confabulations | — | 21.4% |
| MMLU | — | 80% |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Mistral Large: 40.1 (#214)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| LMArena Non-English | 1216 | 1237 |
| LMArena Chinese | 1250 | 1240 |
| LMArena Russian | 1198 | 1257 |
| LMArena Spanish | 1258 | 1268 |
| LMArena French | — | 1324 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1187 |
| LMArena Korean | — | 1202 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Mistral Large: 68.1 (#186)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| IFEval | 89% | 87.7% |
| LMArena Instruction Following | 1221 | 1249 |
| LiveBench Instruction Following | — | 67.9% |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Mistral Large: 38.3 (#194)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1240 | 1262 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Mistral Large: 40.9 (#237)

| Benchmark | Granite 4.0 H Small | Mistral Large |
|---|---|---|
| LMArena Text | 1241 | 1266 |
| LMArena Creative Writing | 1210 | 1243 |
| WildBench | 73.9% | 80.1% |
| LMArena Multi-Turn | 1243 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| LiveBench Language | — | 39.4% |

## FAQ

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

Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 31.6 on the Noometry Index.

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

Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 33.8 in the Noometry coding category.

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

19 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Mistral Large has 51.