# Granite 3.1 2b Instruct vs Mistral Small 3.1

> Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 31.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-2b-instruct-vs-mistral-small-3-1
- 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 3 categories and Mistral Small 3.1 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.1 2b Instruct leads 30.6 to 13.7.

## Snapshot

| | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 32.6 | 31.4 |
| Rank | 243 | 263 |
| Context | — | 128K |
| Input $/M | — | $0.35 |
| Output $/M | — | $0.56 |
| Weights | Open | Open |

## Coding

- Granite 3.1 2b Instruct: 32.9 (#255)
- Mistral Small 3.1: 37.7 (#175)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1149 | 1309 |

## Reasoning

- Granite 3.1 2b Instruct: 21.0 (#206)
- Mistral Small 3.1: 18.9 (#249)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1278 |
| Chess Puzzles | — | 1% |
| Epoch Capabilities Index | — | 127.48 |

## Math

- Granite 3.1 2b Instruct: 30.6 (#206)
- Mistral Small 3.1: 13.7 (#295)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Math | 1159 | 1261 |
| OTIS Mock AIME 2024-2025 | — | 3.9% |
| Omni-MATH | — | 24.8% |

## Knowledge

- Granite 3.1 2b Instruct: 30.3 (#223)
- Mistral Small 3.1: 22.6 (#266)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Expert | 1131 | 1258 |
| GPQA Diamond | — | 41.9% |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |

## Multimodal

- Granite 3.1 2b Instruct: —
- Mistral Small 3.1: 32.6 (#93)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |

## Multilingual

- Granite 3.1 2b Instruct: 29.2 (#264)
- Mistral Small 3.1: 41.4 (#204)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1068 | 1255 |
| LMArena Chinese | 1138 | 1254 |
| LMArena Russian | 1063 | 1263 |
| LMArena French | — | 1270 |
| LMArena German | — | 1266 |
| LMArena Japanese | — | 1210 |
| LMArena Korean | — | 1206 |
| LMArena Spanish | — | 1283 |

## Instruction Following

- Granite 3.1 2b Instruct: 58.0 (#259)
- Mistral Small 3.1: 63.8 (#225)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1264 |
| IFEval | — | 75% |

## Long Context

- Granite 3.1 2b Instruct: 35.0 (#239)
- Mistral Small 3.1: 39.5 (#172)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1155 | 1300 |

## Writing & Preference

- Granite 3.1 2b Instruct: 34.3 (#269)
- Mistral Small 3.1: 37.2 (#254)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1127 | 1278 |
| LMArena Creative Writing | 1116 | 1253 |
| LMArena Multi-Turn | 1099 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |

## FAQ

### Is Granite 3.1 2b Instruct better than Mistral Small 3.1?

Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 31.4 on the Noometry Index.

### Is Granite 3.1 2b Instruct or Mistral Small 3.1 better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 37.7 versus 32.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 2b Instruct and Mistral Small 3.1 share?

12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Mistral Small 3.1 has 28.