# Granite 3.1 2b Instruct vs Magistral Medium

> Magistral Medium is the stronger model overall, scoring 34.8 to 32.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-2b-instruct-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 3.1 2b Instruct leads 21.0 to 8.7.

## Snapshot

| | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 32.6 | 34.8 |
| Rank | 243 | 224 |
| Context | — | 128K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- Granite 3.1 2b Instruct: 32.9 (#255)
- Magistral Medium: 38.6 (#161)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Coding | 1149 | 1319 |
| SciCode | — | 39.2% |

## Reasoning

- Granite 3.1 2b Instruct: 21.0 (#206)
- Magistral Medium: 8.7 (#342)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |

## Math

- Granite 3.1 2b Instruct: 30.6 (#206)
- Magistral Medium: 32.4 (#187)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Math | 1159 | 1249 |

## Knowledge

- Granite 3.1 2b Instruct: 30.3 (#223)
- Magistral Medium: 32.9 (#199)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Expert | 1131 | 1222 |

## Multilingual

- Granite 3.1 2b Instruct: 29.2 (#264)
- Magistral Medium: 39.8 (#219)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1068 | 1232 |
| LMArena Chinese | 1138 | 1225 |
| LMArena Russian | 1063 | 1224 |
| LMArena French | — | 1268 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1176 |
| LMArena Korean | — | 1125 |
| LMArena Spanish | — | 1269 |

## Instruction Following

- Granite 3.1 2b Instruct: 58.0 (#259)
- Magistral Medium: 66.2 (#207)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1116 | 1254 |

## Long Context

- Granite 3.1 2b Instruct: 35.0 (#239)
- Magistral Medium: 39.3 (#178)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1155 | 1295 |

## Writing & Preference

- Granite 3.1 2b Instruct: 34.3 (#269)
- Magistral Medium: 46.5 (#214)

| Benchmark | Granite 3.1 2b Instruct | Magistral Medium |
|---|---|---|
| LMArena Text | 1127 | 1255 |
| LMArena Creative Writing | 1116 | 1245 |
| LMArena Multi-Turn | 1099 | 1275 |

## FAQ

### Is Granite 3.1 2b Instruct better than Magistral Medium?

Magistral Medium is the stronger model overall, scoring 34.8 to 32.6 on the Noometry Index.

### Is Granite 3.1 2b Instruct or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 32.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 2b Instruct and Magistral Medium share?

12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Magistral Medium has 22.