# Mistral Medium 3.5 vs Qwen3 32B

> Mistral Medium 3.5 and Qwen3 32B score almost the same on the Noometry Index (39.6 vs 38.8), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mistral-medium-3-5-vs-qwen3-32b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 3 categories and Qwen3 32B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Medium 3.5 leads 52.1 to 45.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 41.4% for Mistral Medium 3.5 and 54.9% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 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 131K.

## Snapshot

| | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 38.8 |
| Rank | 151 | 166 |
| Context | 262K | 131K |
| Input $/M | $1.50 | $0.70 |
| Output $/M | $7.50 | $2.80 |
| Weights | Open | Open |

## Coding

- Mistral Medium 3.5: 35.7 (#208)
- Qwen3 32B: 37.3 (#184)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1461 | 1358 |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1263 | — |
| SciCode | — | 35.4% |

## Agentic & Tool Use

- Mistral Medium 3.5: —
- Qwen3 32B: 32.3 (#58)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Mistral Medium 3.5: 16.6 (#290)
- Qwen3 32B: 19.6 (#233)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 41.4% | 54.9% |
| LMArena Hard Prompts | 1436 | 1335 |
| Epoch Capabilities Index | 141.42 | 138.51 |
| NYT Connections (extended) | 12.9% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |

## Math

- Mistral Medium 3.5: 36.4 (#113)
- Qwen3 32B: 37.9 (#89)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Math | 1432 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |

## Knowledge

- Mistral Medium 3.5: 39.3 (#123)
- Qwen3 32B: 40.0 (#112)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Expert | 1431 | 1362 |
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |

## Multimodal

- Mistral Medium 3.5: 37.6 (#64)
- Qwen3 32B: —

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Medium 3.5: 52.1 (#93)
- Qwen3 32B: 45.8 (#162)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1405 | 1317 |
| LMArena Chinese | 1443 | 1357 |
| LMArena German | 1453 | 1341 |
| LMArena Russian | 1396 | 1311 |
| LMArena French | 1448 | — |
| LMArena Korean | 1387 | — |
| LMArena Spanish | 1406 | — |

## Instruction Following

- Mistral Medium 3.5: 74.7 (#87)
- Qwen3 32B: 69.1 (#174)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1305 |

## Long Context

- Mistral Medium 3.5: 43.2 (#101)
- Qwen3 32B: 43.7 (#83)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1414 | 1327 |
| Fiction.LiveBench | — | 74.2% |

## Writing & Preference

- Mistral Medium 3.5: 58.6 (#113)
- Qwen3 32B: 53.1 (#158)

| Benchmark | Mistral Medium 3.5 | Qwen3 32B |
|---|---|---|
| LMArena Text | 1421 | 1340 |
| LMArena Creative Writing | 1372 | 1297 |
| LMArena Multi-Turn | 1423 | 1331 |
| EQ-Bench 4 | 993 | — |

## FAQ

### Is Mistral Medium 3.5 better than Qwen3 32B?

Mistral Medium 3.5 and Qwen3 32B score almost the same on the Noometry Index (39.6 vs 38.8), so choose on price, context window or the category you care about most.

### Which is cheaper, Mistral Medium 3.5 or Qwen3 32B?

Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.3 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 131K.

### How many benchmarks do Mistral Medium 3.5 and Qwen3 32B share?

15 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen3 32B has 26.