# Granite 4.2 30b vs Mistral Medium

> Granite 4.2 30b is the stronger model overall, scoring 41.8 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-30b-vs-mistral-medium
- 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 3 categories and Mistral Medium in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 30b leads 39.1 to 25.0.

## Snapshot

| | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 41.8 | 36.3 |
| Rank | 130 | 218 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- Granite 4.2 30b: 41.0 (#126)
- Mistral Medium: 34.2 (#243)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Coding | 1396 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |

## Agentic & Tool Use

- Granite 4.2 30b: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Granite 4.2 30b: 27.8 (#112)
- Mistral Medium: 24.0 (#167)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |

## Math

- Granite 4.2 30b: —
- Mistral Medium: 28.1 (#245)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| LMArena Math | — | 1408 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Granite 4.2 30b: 39.1 (#138)
- Mistral Medium: 25.0 (#265)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Expert | 1406 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |

## Multimodal

- Granite 4.2 30b: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Granite 4.2 30b: 47.3 (#151)
- Mistral Medium: 52.1 (#91)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1340 | 1408 |
| LMArena Chinese | 1414 | 1447 |
| LMArena Russian | 1343 | 1411 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Spanish | — | 1433 |

## Instruction Following

- Granite 4.2 30b: 71.2 (#155)
- Mistral Medium: 73.7 (#116)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1347 | 1398 |

## Long Context

- Granite 4.2 30b: 41.4 (#140)
- Mistral Medium: 42.9 (#114)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1359 | 1406 |

## Writing & Preference

- Granite 4.2 30b: 53.8 (#156)
- Mistral Medium: 60.0 (#103)

| Benchmark | Granite 4.2 30b | Mistral Medium |
|---|---|---|
| LMArena Text | 1361 | 1424 |
| LMArena Creative Writing | 1288 | 1391 |
| LMArena Multi-Turn | 1339 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

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

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 36.3 on the Noometry Index.

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

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 34.2 in the Noometry coding category.

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

11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Mistral Medium has 36.