# Mistral Small vs Qwen3.5-Flash

> Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 33.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-vs-qwen3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Mistral Small scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5-Flash leads 36.3 to 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Qwen3.5-Flash accepts more context: 1M tokens versus 256K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.1 | 42.3 |
| Rank | 238 | 105 |
| Context | 256K | 1M |
| Input $/M | $0.15 | $0.10 |
| Output $/M | $0.60 | $0.40 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small: 33.5 (#242)
- Qwen3.5-Flash: 33.9 (#234)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1363 | 1412 |
| ALE-Bench | 497.62 | 221.8 |
| LMArena WebDev | — | 1243 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |

## Agentic & Tool Use

- Mistral Small: 27.9 (#87)
- Qwen3.5-Flash: —

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
| Vending-Bench 2 | — | 462.69 |

## Reasoning

- Mistral Small: 19.3 (#238)
- Qwen3.5-Flash: 32.9 (#63)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1336 | 1404 |
| DTBench | 70.9% | 82.9% |
| LMCA | 20.6% | 29.1% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 143.98 |
| LiveBench | 44% | — |

## Math

- Mistral Small: 15.4 (#287)
- Qwen3.5-Flash: 36.3 (#117)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 84.4% |
| LMArena Math | 1341 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Mistral Small: 30.9 (#214)
- Qwen3.5-Flash: 43.2 (#84)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 47.5% | 82.3% |
| Vectara Hallucination Rate | 5.1% | 10.5% |
| LMArena Expert | 1293 | 1408 |
| SimpleQA Verified | — | 20.3% |
| MMLU | 68.7% | — |

## Multimodal

- Mistral Small: 32.9 (#91)
- Qwen3.5-Flash: —

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.7 (#164)
- Qwen3.5-Flash: 50.7 (#116)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1315 | 1385 |
| LMArena Chinese | 1342 | 1446 |
| LMArena French | 1337 | 1412 |
| LMArena German | 1341 | 1389 |
| LMArena Japanese | 1275 | 1369 |
| LMArena Korean | 1260 | 1344 |
| LMArena Russian | 1324 | 1379 |
| LMArena Spanish | 1346 | 1399 |

## Instruction Following

- Mistral Small: 66.6 (#204)
- Qwen3.5-Flash: 72.8 (#133)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1310 | 1374 |
| LiveBench Instruction Following | 63.7% | — |

## Long Context

- Mistral Small: 40.4 (#151)
- Qwen3.5-Flash: 42.4 (#119)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1327 | 1392 |

## Writing & Preference

- Mistral Small: 52.6 (#165)
- Qwen3.5-Flash: 58.2 (#117)

| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1338 | 1397 |
| LMArena Creative Writing | 1304 | 1343 |
| LMArena Multi-Turn | 1344 | 1393 |
| LiveBench Language | 30.5% | — |

## FAQ

### Is Mistral Small better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 33.1 on the Noometry Index.

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

Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Small lists at $0.15 and $0.60.

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

They score almost the same on coding (33.5 vs 33.9); test both on your own repository before choosing.

### Which has the bigger context window?

Qwen3.5-Flash does, with 1M tokens against 256K.

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

23 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3.5-Flash has 32.