# Granite 4.2 3b vs Mistral Small 3

> Granite 4.2 3b is the stronger model overall, scoring 39.4 to 31.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 7 categories and Mistral Small 3 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.2 3b leads 47.2 to 32.2.

## Snapshot

| | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 39.4 | 31.2 |
| Rank | 169 | 278 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 40.0 (#151)
- Mistral Small 3: 36.5 (#207)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1361 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Reasoning

- Granite 4.2 3b: 26.0 (#138)
- Mistral Small 3: 18.9 (#273)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1306 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |

## Math

- Granite 4.2 3b: —
- Mistral Small 3: 16.3 (#295)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| LMArena Math | — | 1240 |

## Knowledge

- Granite 4.2 3b: 36.3 (#171)
- Mistral Small 3: 25.1 (#263)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1315 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |

## Multilingual

- Granite 4.2 3b: 42.1 (#198)
- Mistral Small 3: 37.3 (#236)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1268 | 1198 |
| LMArena Chinese | 1269 | 1204 |
| LMArena Russian | 1249 | 1216 |
| LMArena French | — | 1203 |
| LMArena German | — | 1211 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |

## Instruction Following

- Granite 4.2 3b: 67.1 (#200)
- Mistral Small 3: 63.7 (#229)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1273 | 1214 |

## Long Context

- Granite 4.2 3b: 39.2 (#185)
- Mistral Small 3: 37.8 (#211)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1291 | 1246 |

## Writing & Preference

- Granite 4.2 3b: 47.2 (#212)
- Mistral Small 3: 32.2 (#280)

| Benchmark | Granite 4.2 3b | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1293 | 1234 |
| LMArena Creative Writing | 1205 | 1195 |
| LMArena Multi-Turn | 1290 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Granite 4.2 3b better than Mistral Small 3?

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 31.2 on the Noometry Index.

### Is Granite 4.2 3b or Mistral Small 3 better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 36.5 in the Noometry coding category.

### How many benchmarks do Granite 4.2 3b and Mistral Small 3 share?

11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Mistral Small 3 has 24.