# Devstral Small 2505 vs Qwen3.5-Flash

> Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 33.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-qwen3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Qwen3.5-Flash leads 32.9 to 19.1.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.10 / $0.40 for Qwen3.5-Flash.
- Qwen3.5-Flash accepts more context: 1M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.

## Snapshot

| | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.9 | 42.3 |
| Rank | 228 | 105 |
| Context | 128K | 1M |
| Input $/M | $0.10 | $0.10 |
| Output $/M | $0.30 | $0.40 |
| Weights | Open | Proprietary |

## Coding

- Devstral Small 2505: 38.6 (#160)
- Qwen3.5-Flash: 33.9 (#234)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1243 |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1412 |
| ALE-Bench | — | 221.8 |

## Agentic & Tool Use

- Devstral Small 2505: —
- Qwen3.5-Flash: —

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- Qwen3.5-Flash: 32.9 (#63)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 21% |
| LMArena Hard Prompts | — | 1404 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
| Epoch Capabilities Index | — | 143.98 |

## Math

- Devstral Small 2505: —
- Qwen3.5-Flash: 36.3 (#117)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 18.2% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| LMArena Math | — | 1407 |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Devstral Small 2505: —
- Qwen3.5-Flash: 43.2 (#84)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | — | 82.3% |
| SimpleQA Verified | — | 20.3% |
| Vectara Hallucination Rate | — | 10.5% |
| LMArena Expert | — | 1408 |

## Multilingual

- Devstral Small 2505: —
- Qwen3.5-Flash: 50.7 (#116)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1412 |
| LMArena German | — | 1389 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1344 |
| LMArena Russian | — | 1379 |
| LMArena Spanish | — | 1399 |

## Instruction Following

- Devstral Small 2505: —
- Qwen3.5-Flash: 72.8 (#133)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | — | 1374 |

## Long Context

- Devstral Small 2505: —
- Qwen3.5-Flash: 42.4 (#119)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | — | 1392 |

## Writing & Preference

- Devstral Small 2505: —
- Qwen3.5-Flash: 58.2 (#117)

| Benchmark | Devstral Small 2505 | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | — | 1397 |
| LMArena Creative Writing | — | 1343 |
| LMArena Multi-Turn | — | 1393 |

## FAQ

### Is Devstral Small 2505 better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 33.9 on the Noometry Index.

### Which is cheaper, Devstral Small 2505 or Qwen3.5-Flash?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.5-Flash lists at $0.10 and $0.40.

### Is Devstral Small 2505 or Qwen3.5-Flash better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 33.9 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5-Flash does, with 1M tokens against 128K.

### How many benchmarks do Devstral Small 2505 and Qwen3.5-Flash share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3.5-Flash has 32.