# Codestral vs Granite 4.2 30b

> Granite 4.2 30b is the stronger model overall, scoring 41.8 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-granite-4-2-30b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Granite 4.2 30b leads 41.0 to 27.3.
- Granite 4.2 30b has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | Granite 4.2 30b |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.6 | 41.8 |
| Rank | 290 | 130 |
| Context | 256K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Proprietary | Open |

## Coding

- Codestral: 27.3 (#321)
- Granite 4.2 30b: 41.0 (#126)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1396 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.8 (#251)
- Granite 4.2 30b: 27.8 (#112)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1374 |

## Knowledge

- Codestral: —
- Granite 4.2 30b: 39.1 (#138)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| LMArena Expert | — | 1406 |

## Multilingual

- Codestral: —
- Granite 4.2 30b: 47.3 (#151)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | — | 1340 |
| LMArena Chinese | — | 1414 |
| LMArena Russian | — | 1343 |

## Instruction Following

- Codestral: —
- Granite 4.2 30b: 71.2 (#155)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | — | 1347 |

## Long Context

- Codestral: —
- Granite 4.2 30b: 41.4 (#140)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | — | 1359 |

## Writing & Preference

- Codestral: —
- Granite 4.2 30b: 53.8 (#156)

| Benchmark | Codestral | Granite 4.2 30b |
|---|---|---|
| LMArena Text | — | 1361 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1339 |

## FAQ

### Is Codestral better than Granite 4.2 30b?

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 30.6 on the Noometry Index.

### Is Codestral or Granite 4.2 30b better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 27.3 in the Noometry coding category.

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

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 4.2 30b has 11.