# Mistral Medium vs Qwen3.6 Flash

> Qwen3.6 Flash is the stronger model overall, scoring 38.8 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-vs-qwen3-6-flash
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Mistral Medium scores higher in 0 categories and Qwen3.6 Flash in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Flash leads 42.1 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 84.4% for Qwen3.6 Flash.
- Qwen3.6 Flash is cheaper at $0.19 / $1.13 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Qwen3.6 Flash accepts more context: 1M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 38.8 |
| Rank | 218 | 182 |
| Context | 262K | 1M |
| Input $/M | $1.50 | $0.19 |
| Output $/M | $7.50 | $1.13 |
| Weights | Open | Proprietary |

## Coding

- Mistral Medium: 34.2 (#243)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| ALE-Bench | 763.98 | 326.4 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| LMArena Coding | 1434 | — |

## Agentic & Tool Use

- Mistral Medium: 28.3 (#90)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |

## Reasoning

- Mistral Medium: 24.0 (#167)
- Qwen3.6 Flash: 29.0 (#96)

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| DTBench | 75.5% | 77.1% |
| LMCA | 26.1% | 31% |
| SimpleBench | — | 35.2% |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 20% |
| LMArena Hard Prompts | 1426 | — |
| Mystery Game Puzzles | — | 18% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 143.26 |

## Math

- Mistral Medium: 28.1 (#245)
- Qwen3.6 Flash: 39.0 (#117)

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 84.4% |
| FrontierMath (Feb 2025 set) | 0.3% | 10.3% |
| FrontierMath (Tiers 1-3) | — | 22.5% |
| ProofBench | 9% | — |
| LMArena Math | 1408 | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Mistral Medium: 25.0 (#265)
- Qwen3.6 Flash: 42.1 (#100)

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| GPQA Diamond | 59.5% | 83.3% |
| Humanity's Last Exam | 4.5% | — |
| SimpleQA Verified | — | 15.9% |
| Vectara Hallucination Rate | 22.7% | — |
| LMArena Expert | 1408 | — |

## Multimodal

- Mistral Medium: 35.3 (#88)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| LMArena Vision | 1172 | — |

## Multilingual

- Mistral Medium: 52.1 (#91)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| LMArena Non-English | 1408 | — |
| LMArena Chinese | 1447 | — |
| LMArena French | 1459 | — |
| LMArena German | 1432 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1433 | — |

## Instruction Following

- Mistral Medium: 73.7 (#116)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1398 | — |

## Long Context

- Mistral Medium: 42.9 (#114)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1406 | — |

## Writing & Preference

- Mistral Medium: 60.0 (#103)
- Qwen3.6 Flash: —

| Benchmark | Mistral Medium | Qwen3.6 Flash |
|---|---|---|
| LMArena Text | 1424 | — |
| LMArena Creative Writing | 1391 | — |
| Short-Story Creative Writing | 77.3% | — |
| LMArena Multi-Turn | 1418 | — |

## FAQ

### Is Mistral Medium better than Qwen3.6 Flash?

Qwen3.6 Flash is the stronger model overall, scoring 38.8 to 36.3 on the Noometry Index.

### Which is cheaper, Mistral Medium or Qwen3.6 Flash?

Qwen3.6 Flash is cheaper. It lists at $0.19 per million input tokens and $1.13 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Which has the bigger context window?

Qwen3.6 Flash does, with 1M tokens against 262K.

### How many benchmarks do Mistral Medium and Qwen3.6 Flash share?

6 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3.6 Flash has 13.