# Codestral vs Granite 4.2 3b

> Granite 4.2 3b is the stronger model overall, scoring 39.0 to 30.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-granite-4-2-3b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Granite 4.2 3b leads 39.4 to 26.9.

## Snapshot

| | Codestral | Granite 4.2 3b |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.1 | 39.0 |
| Rank | 287 | 163 |
| Context | 256K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- Granite 4.2 3b: 39.4 (#146)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1363 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.1 (#244)
- Granite 4.2 3b: 25.0 (#136)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1308 |

## Knowledge

- Codestral: —
- Granite 4.2 3b: 35.6 (#169)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| LMArena Expert | — | 1313 |

## Multilingual

- Codestral: —
- Granite 4.2 3b: 42.4 (#193)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| LMArena Non-English | — | 1268 |
| LMArena Chinese | — | 1268 |
| LMArena Russian | — | 1249 |

## Instruction Following

- Codestral: —
- Granite 4.2 3b: 67.2 (#195)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| LMArena Instruction Following | — | 1271 |

## Long Context

- Codestral: —
- Granite 4.2 3b: 39.3 (#179)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| LMArena Longer Query | — | 1293 |

## Writing & Preference

- Codestral: —
- Granite 4.2 3b: 47.9 (#202)

| Benchmark | Codestral | Granite 4.2 3b |
|---|---|---|
| LMArena Text | — | 1295 |
| LMArena Creative Writing | — | 1215 |
| LMArena Multi-Turn | — | 1293 |

## FAQ

### Is Codestral better than Granite 4.2 3b?

Granite 4.2 3b is the stronger model overall, scoring 39.0 to 30.1 on the Noometry Index.

### Is Codestral or Granite 4.2 3b better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 26.9 in the Noometry coding category.

### How many benchmarks do Codestral and Granite 4.2 3b share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 4.2 3b has 11.