# Devstral Small 2505 vs Qwen1.5-7B

> Devstral Small 2505 is the stronger model overall, scoring 33.9 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-qwen1-5-7b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Devstral Small 2505 leads 38.6 to 31.6.

## Snapshot

| | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.9 | 30.8 |
| Rank | 228 | 270 |
| Context | 128K | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.30 | — |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.6 (#160)
- Qwen1.5-7B: 31.6 (#271)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1107 |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- Qwen1.5-7B: 19.5 (#237)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1066 |

## Math

- Devstral Small 2505: —
- Qwen1.5-7B: 29.0 (#222)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| LMArena Math | — | 1080 |

## Knowledge

- Devstral Small 2505: —
- Qwen1.5-7B: 28.2 (#239)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | — | 1055 |
| MMLU | — | 62.6% |

## Multilingual

- Devstral Small 2505: —
- Qwen1.5-7B: 28.6 (#266)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | — | 1058 |
| LMArena Chinese | — | 1140 |
| LMArena Russian | — | 1006 |

## Instruction Following

- Devstral Small 2505: —
- Qwen1.5-7B: 54.4 (#276)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | — | 1058 |

## Long Context

- Devstral Small 2505: —
- Qwen1.5-7B: 33.1 (#261)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | — | 1090 |

## Writing & Preference

- Devstral Small 2505: —
- Qwen1.5-7B: 29.8 (#288)

| Benchmark | Devstral Small 2505 | Qwen1.5-7B |
|---|---|---|
| LMArena Text | — | 1084 |
| LMArena Creative Writing | — | 1035 |
| LMArena Multi-Turn | — | 1061 |

## FAQ

### Is Devstral Small 2505 better than Qwen1.5-7B?

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 30.8 on the Noometry Index.

### Is Devstral Small 2505 or Qwen1.5-7B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 31.6 in the Noometry coding category.

### How many benchmarks do Devstral Small 2505 and Qwen1.5-7B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen1.5-7B has 13.