# Granite 4.2 3b vs Pixtral Large

> Granite 4.2 3b is the stronger model overall, scoring 39.4 to 32.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-pixtral-large
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where Granite 4.2 3b leads 47.2 to 32.9.

## Snapshot

| | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 39.4 | 32.2 |
| Rank | 169 | 259 |
| Context | — | 128K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 40.0 (#151)
- Pixtral Large: —

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Coding | 1361 | — |

## Reasoning

- Granite 4.2 3b: 26.0 (#138)
- Pixtral Large: 21.7 (#218)

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 1306 | — |

## Knowledge

- Granite 4.2 3b: 36.3 (#171)
- Pixtral Large: —

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Expert | 1315 | — |

## Multimodal

- Granite 4.2 3b: —
- Pixtral Large: 30.6 (#111)

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |

## Multilingual

- Granite 4.2 3b: 42.1 (#198)
- Pixtral Large: —

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1269 | — |
| LMArena Russian | 1249 | — |

## Instruction Following

- Granite 4.2 3b: 67.1 (#200)
- Pixtral Large: —

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Instruction Following | 1273 | — |

## Long Context

- Granite 4.2 3b: 39.2 (#185)
- Pixtral Large: —

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1291 | — |

## Writing & Preference

- Granite 4.2 3b: 47.2 (#212)
- Pixtral Large: 32.9 (#278)

| Benchmark | Granite 4.2 3b | Pixtral Large |
|---|---|---|
| LMArena Text | 1293 | — |
| LMArena Creative Writing | 1205 | — |
| EQ-Bench Creative Writing | — | 988 |
| LMArena Multi-Turn | 1290 | — |

## FAQ

### Is Granite 4.2 3b better than Pixtral Large?

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 32.2 on the Noometry Index.

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

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