# Devstral Small 2505 vs Llama 3.2 90B

> Devstral Small 2505 is the stronger model overall, scoring 34.3 to 27.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-llama-3-2-90b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Snapshot

| | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 34.3 | 27.5 |
| Rank | 233 | 331 |
| Context | 128K | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.30 | — |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.9 (#166)
- Llama 3.2 90B: —

| Benchmark | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |

## Agentic & Tool Use

- Devstral Small 2505: —
- Llama 3.2 90B: 30.0 (#80)

| Benchmark | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- Llama 3.2 90B: 21.7 (#217)

| Benchmark | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| EnigmaEval | — | 0.4% |
| Epoch Capabilities Index | — | 125.5 |

## Math

- Devstral Small 2505: —
- Llama 3.2 90B: 11.1 (#308)

| Benchmark | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| MATH Level 5 | — | 39.4% |

## Knowledge

- Devstral Small 2505: —
- Llama 3.2 90B: 21.7 (#274)

| Benchmark | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| MMLU | — | 80.3% |

## Multimodal

- Devstral Small 2505: —
- Llama 3.2 90B: 25.4 (#124)

| Benchmark | Devstral Small 2505 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## FAQ

### Is Devstral Small 2505 better than Llama 3.2 90B?

Devstral Small 2505 is the stronger model overall, scoring 34.3 to 27.5 on the Noometry Index.

### How many benchmarks do Devstral Small 2505 and Llama 3.2 90B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Llama 3.2 90B has 9.