# Devstral Small 2505 vs Granite 4.2 3b

> Granite 4.2 3b is the stronger model overall, scoring 39.4 to 34.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-granite-4-2-3b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Granite 4.2 3b leads 26.0 to 19.7.

## Snapshot

| | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 34.3 | 39.4 |
| Rank | 233 | 169 |
| Context | 128K | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.30 | — |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.9 (#166)
- Granite 4.2 3b: 40.0 (#151)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1361 |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- Granite 4.2 3b: 26.0 (#138)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1306 |

## Knowledge

- Devstral Small 2505: —
- Granite 4.2 3b: 36.3 (#171)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| LMArena Expert | — | 1315 |

## Multilingual

- Devstral Small 2505: —
- Granite 4.2 3b: 42.1 (#198)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| LMArena Non-English | — | 1268 |
| LMArena Chinese | — | 1269 |
| LMArena Russian | — | 1249 |

## Instruction Following

- Devstral Small 2505: —
- Granite 4.2 3b: 67.1 (#200)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| LMArena Instruction Following | — | 1273 |

## Long Context

- Devstral Small 2505: —
- Granite 4.2 3b: 39.2 (#185)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| LMArena Longer Query | — | 1291 |

## Writing & Preference

- Devstral Small 2505: —
- Granite 4.2 3b: 47.2 (#212)

| Benchmark | Devstral Small 2505 | Granite 4.2 3b |
|---|---|---|
| LMArena Text | — | 1293 |
| LMArena Creative Writing | — | 1205 |
| LMArena Multi-Turn | — | 1290 |

## FAQ

### Is Devstral Small 2505 better than Granite 4.2 3b?

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 34.3 on the Noometry Index.

### Is Devstral Small 2505 or Granite 4.2 3b better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 38.9 in the Noometry coding category.

### How many benchmarks do Devstral Small 2505 and Granite 4.2 3b share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Granite 4.2 3b has 11.