# Granite 3.0 2b Instruct vs Ministral 3B

> Granite 3.0 2b Instruct is the stronger model overall, scoring 30.8 to 26.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-ministral-3b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Granite 3.0 2b Instruct leads 29.0 to 10.4.

## Snapshot

| | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 30.8 | 26.2 |
| Rank | 286 | 338 |
| Context | — | 131K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.10 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 28.3 (#316)
- Ministral 3B: —

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| BigCodeBench Instruct | 20.5% | — |
| LMArena Coding | 1090 | — |

## Reasoning

- Granite 3.0 2b Instruct: 20.5 (#235)
- Ministral 3B: 18.4 (#282)

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| LMArena Hard Prompts | 1073 | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 118.1 |

## Math

- Granite 3.0 2b Instruct: 32.2 (#217)
- Ministral 3B: 26.6 (#258)

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| LMArena Math | 1117 | — |
| MATH Level 5 | — | 14.4% |

## Knowledge

- Granite 3.0 2b Instruct: 29.0 (#241)
- Ministral 3B: 10.4 (#302)

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| GPQA Diamond | — | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1064 | — |

## Multilingual

- Granite 3.0 2b Instruct: 27.0 (#278)
- Ministral 3B: —

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1033 | — |
| LMArena Chinese | 1070 | — |
| LMArena Russian | 1045 | — |

## Instruction Following

- Granite 3.0 2b Instruct: 53.9 (#284)
- Ministral 3B: —

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1056 | — |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#268)
- Ministral 3B: —

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1070 | — |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.6 (#292)
- Ministral 3B: —

| Benchmark | Granite 3.0 2b Instruct | Ministral 3B |
|---|---|---|
| LMArena Text | 1080 | — |
| LMArena Creative Writing | 1046 | — |
| LMArena Multi-Turn | 1053 | — |

## FAQ

### Is Granite 3.0 2b Instruct better than Ministral 3B?

Granite 3.0 2b Instruct is the stronger model overall, scoring 30.8 to 26.2 on the Noometry Index.

### How many benchmarks do Granite 3.0 2b Instruct and Ministral 3B share?

0 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Ministral 3B has 6.