# Devstral Small 2505 vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.8 to 34.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-qwq-32b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where QwQ-32B leads 23.7 to 19.7.

## Snapshot

| | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 39.8 |
| Rank | 233 | 159 |
| Context | 128K | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.30 | — |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.9 (#166)
- QwQ-32B: 35.4 (#226)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| Aider Polyglot | — | 20.9% |
| SciCode | 28.8% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| LMArena Coding | — | 1333 |
| BigCodeBench Complete | — | 54.4% |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- QwQ-32B: 23.7 (#174)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LMArena Hard Prompts | — | 1325 |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- Devstral Small 2505: —
- QwQ-32B: 38.0 (#143)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| LMArena Math | — | 1359 |

## Knowledge

- Devstral Small 2505: —
- QwQ-32B: 37.2 (#158)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| LMArena Expert | — | 1324 |

## Multilingual

- Devstral Small 2505: —
- QwQ-32B: 44.8 (#176)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| LMArena Non-English | — | 1305 |
| LMArena Chinese | — | 1378 |
| LMArena French | — | 1336 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
| LMArena Russian | — | 1297 |
| LMArena Spanish | — | 1354 |

## Instruction Following

- Devstral Small 2505: —
- QwQ-32B: 72.6 (#137)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | — | 81.8% |
| LMArena Instruction Following | — | 1297 |

## Long Context

- Devstral Small 2505: —
- QwQ-32B: 49.0 (#11)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1308 |

## Writing & Preference

- Devstral Small 2505: —
- QwQ-32B: 50.6 (#180)

| Benchmark | Devstral Small 2505 | QwQ-32B |
|---|---|---|
| LMArena Text | — | 1329 |
| LMArena Creative Writing | — | 1288 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 51.4% |

## FAQ

### Is Devstral Small 2505 better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 34.3 on the Noometry Index.

### Is Devstral Small 2505 or QwQ-32B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 35.4 in the Noometry coding category.

### How many benchmarks do Devstral Small 2505 and QwQ-32B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and QwQ-32B has 36.