# Mistral Medium 3.5 vs Qwen Max

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-3-5-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 36.4 to 21.0.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 33K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 34.4 |
| Rank | 151 | 226 |
| Context | 262K | 33K |
| Input $/M | $1.50 | $1.60 |
| Output $/M | $7.50 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- Mistral Medium 3.5: 35.7 (#208)
- Qwen Max: 30.3 (#288)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Coding | 1461 | 1288 |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1263 | — |

## Reasoning

- Mistral Medium 3.5: 16.6 (#290)
- Qwen Max: 24.1 (#154)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1270 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| Epoch Capabilities Index | 141.42 | — |

## Math

- Mistral Medium 3.5: 36.4 (#113)
- Qwen Max: 21.0 (#272)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Math | 1432 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- Mistral Medium 3.5: 39.3 (#123)
- Qwen Max: 30.3 (#222)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Expert | 1431 | 1248 |
| GPQA Diamond | — | 56.1% |

## Multimodal

- Mistral Medium 3.5: 37.6 (#64)
- Qwen Max: —

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Medium 3.5: 52.1 (#93)
- Qwen Max: 42.0 (#197)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1405 | 1263 |
| LMArena Chinese | 1443 | 1254 |
| LMArena French | 1448 | 1329 |
| LMArena German | 1453 | 1254 |
| LMArena Korean | 1387 | 1141 |
| LMArena Russian | 1396 | 1274 |
| LMArena Spanish | 1406 | 1290 |
| LMArena Japanese | — | 1205 |

## Instruction Following

- Mistral Medium 3.5: 74.7 (#87)
- Qwen Max: 66.7 (#203)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1414 | 1262 |

## Long Context

- Mistral Medium 3.5: 43.2 (#101)
- Qwen Max: 39.4 (#175)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1414 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Mistral Medium 3.5: 58.6 (#113)
- Qwen Max: 48.0 (#200)

| Benchmark | Mistral Medium 3.5 | Qwen Max |
|---|---|---|
| LMArena Text | 1421 | 1282 |
| LMArena Creative Writing | 1372 | 1248 |
| LMArena Multi-Turn | 1423 | 1277 |
| EQ-Bench 4 | 993 | — |

## FAQ

### Is Mistral Medium 3.5 better than Qwen Max?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 34.4 on the Noometry Index.

### Which is cheaper, Mistral Medium 3.5 or Qwen Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or Qwen Max better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 33K.

### How many benchmarks do Mistral Medium 3.5 and Qwen Max share?

16 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen Max has 23.