# Devstral Small 2505 vs Granite 3.0 2b Instruct

> Devstral Small 2505 is the stronger model overall, scoring 33.9 to 30.2 on the Noometry Index.

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

## Summary

- The widest gap is in coding, where Devstral Small 2505 leads 38.6 to 27.8.

## Snapshot

| | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 33.9 | 30.2 |
| Rank | 228 | 284 |
| Context | 128K | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.30 | — |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.6 (#160)
- Granite 3.0 2b Instruct: 27.8 (#311)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| BigCodeBench Instruct | — | 20.5% |
| LMArena Coding | — | 1090 |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- Granite 3.0 2b Instruct: 19.6 (#234)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1073 |

## Math

- Devstral Small 2505: —
- Granite 3.0 2b Instruct: 29.7 (#215)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | — | 1117 |

## Knowledge

- Devstral Small 2505: —
- Granite 3.0 2b Instruct: 28.4 (#238)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1064 |

## Multilingual

- Devstral Small 2505: —
- Granite 3.0 2b Instruct: 27.1 (#273)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1033 |
| LMArena Chinese | — | 1070 |
| LMArena Russian | — | 1045 |

## Instruction Following

- Devstral Small 2505: —
- Granite 3.0 2b Instruct: 54.2 (#279)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1056 |

## Long Context

- Devstral Small 2505: —
- Granite 3.0 2b Instruct: 32.5 (#263)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1071 |

## Writing & Preference

- Devstral Small 2505: —
- Granite 3.0 2b Instruct: 29.8 (#287)

| Benchmark | Devstral Small 2505 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | — | 1080 |
| LMArena Creative Writing | — | 1046 |
| LMArena Multi-Turn | — | 1053 |

## FAQ

### Is Devstral Small 2505 better than Granite 3.0 2b Instruct?

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 30.2 on the Noometry Index.

### Is Devstral Small 2505 or Granite 3.0 2b Instruct better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 27.8 in the Noometry coding category.

### How many benchmarks do Devstral Small 2505 and Granite 3.0 2b Instruct share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Granite 3.0 2b Instruct has 13.