# Granite 4.2 30b vs Mistral Large

> Granite 4.2 30b is the stronger model overall, scoring 41.4 to 31.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-30b-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 7 categories and Mistral Large in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.2 30b leads 54.3 to 40.9.

## Snapshot

| | Granite 4.2 30b | Mistral Large |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 41.4 | 31.6 |
| Rank | 126 | 258 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Granite 4.2 30b: 40.4 (#127)
- Mistral Large: 33.8 (#240)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Coding | 1394 | 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 4.2 30b: —
- Mistral Large: 28.4 (#83)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- Granite 4.2 30b: 26.7 (#114)
- Mistral Large: 15.4 (#305)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1375 | 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 4.2 30b: —
- Mistral Large: 17.1 (#285)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| LMArena Math | — | 1262 |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Granite 4.2 30b: 38.5 (#134)
- Mistral Large: 30.0 (#224)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Expert | 1405 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multilingual

- Granite 4.2 30b: 47.4 (#146)
- Mistral Large: 40.1 (#214)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Non-English | 1340 | 1237 |
| LMArena Chinese | 1415 | 1240 |
| LMArena Russian | 1342 | 1257 |
| LMArena French | — | 1324 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1187 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |

## Instruction Following

- Granite 4.2 30b: 71.3 (#150)
- Mistral Large: 68.1 (#186)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1346 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Granite 4.2 30b: 41.4 (#135)
- Mistral Large: 38.3 (#194)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1359 | 1262 |

## Writing & Preference

- Granite 4.2 30b: 54.3 (#147)
- Mistral Large: 40.9 (#237)

| Benchmark | Granite 4.2 30b | Mistral Large |
|---|---|---|
| LMArena Text | 1363 | 1266 |
| LMArena Creative Writing | 1294 | 1243 |
| LMArena Multi-Turn | 1340 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

### Is Granite 4.2 30b better than Mistral Large?

Granite 4.2 30b is the stronger model overall, scoring 41.4 to 31.6 on the Noometry Index.

### Is Granite 4.2 30b or Mistral Large better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 40.4 versus 33.8 in the Noometry coding category.

### How many benchmarks do Granite 4.2 30b and Mistral Large share?

11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Mistral Large has 51.