# Granite 3.1 2b Instruct vs Mistral Small 3

> Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-2b-instruct-vs-mistral-small-3
- 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 4 categories and Mistral Small 3 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.1 2b Instruct leads 30.6 to 15.3.

## Snapshot

| | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 32.6 | 30.9 |
| Rank | 243 | 268 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Granite 3.1 2b Instruct: 32.9 (#255)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1149 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Reasoning

- Granite 3.1 2b Instruct: 21.0 (#206)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.06 |

## Math

- Granite 3.1 2b Instruct: 30.6 (#206)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1159 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |

## Knowledge

- Granite 3.1 2b Instruct: 30.3 (#223)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1131 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |

## Multilingual

- Granite 3.1 2b Instruct: 29.2 (#264)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1068 | 1198 |
| LMArena Chinese | 1138 | 1204 |
| LMArena Russian | 1063 | 1216 |
| LMArena French | — | 1202 |
| LMArena German | — | 1211 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |

## Instruction Following

- Granite 3.1 2b Instruct: 58.0 (#259)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1214 |

## Long Context

- Granite 3.1 2b Instruct: 35.0 (#239)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1155 | 1246 |

## Writing & Preference

- Granite 3.1 2b Instruct: 34.3 (#269)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Granite 3.1 2b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1127 | 1234 |
| LMArena Creative Writing | 1116 | 1195 |
| LMArena Multi-Turn | 1099 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Granite 3.1 2b Instruct better than Mistral Small 3?

Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 30.9 on the Noometry Index.

### Is Granite 3.1 2b Instruct or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 32.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 2b Instruct and Mistral Small 3 share?

12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Mistral Small 3 has 24.