# Granite 3.0 2b Instruct vs Pixtral Large

> Pixtral Large is the stronger model overall, scoring 32.2 to 30.8 on the Noometry Index.

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

## Summary

- The widest gap is in writing & preference, where Pixtral Large leads 32.9 to 29.6.

## Snapshot

| | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 30.8 | 32.2 |
| Rank | 286 | 259 |
| Context | — | 128K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 28.3 (#316)
- Pixtral Large: —

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| BigCodeBench Instruct | 20.5% | — |
| LMArena Coding | 1090 | — |

## Reasoning

- Granite 3.0 2b Instruct: 20.5 (#235)
- Pixtral Large: 21.7 (#218)

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 1073 | — |

## Math

- Granite 3.0 2b Instruct: 32.2 (#217)
- Pixtral Large: —

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Math | 1117 | — |

## Knowledge

- Granite 3.0 2b Instruct: 29.0 (#241)
- Pixtral Large: —

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Expert | 1064 | — |

## Multimodal

- Granite 3.0 2b Instruct: —
- Pixtral Large: 30.6 (#111)

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |

## Multilingual

- Granite 3.0 2b Instruct: 27.0 (#278)
- Pixtral Large: —

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1033 | — |
| LMArena Chinese | 1070 | — |
| LMArena Russian | 1045 | — |

## Instruction Following

- Granite 3.0 2b Instruct: 53.9 (#284)
- Pixtral Large: —

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Instruction Following | 1056 | — |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#268)
- Pixtral Large: —

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1070 | — |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.6 (#292)
- Pixtral Large: 32.9 (#278)

| Benchmark | Granite 3.0 2b Instruct | Pixtral Large |
|---|---|---|
| LMArena Text | 1080 | — |
| LMArena Creative Writing | 1046 | — |
| EQ-Bench Creative Writing | — | 988 |
| LMArena Multi-Turn | 1053 | — |

## FAQ

### Is Granite 3.0 2b Instruct better than Pixtral Large?

Pixtral Large is the stronger model overall, scoring 32.2 to 30.8 on the Noometry Index.

### How many benchmarks do Granite 3.0 2b Instruct and Pixtral Large share?

0 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Pixtral Large has 3.