# Mistral Medium vs Qwen1.5-32B

> Mistral Medium is the stronger model overall, scoring 36.0 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-vs-qwen1-5-32b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Mistral Medium scores higher in 7 categories and Qwen1.5-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 34.4.
- The biggest single-benchmark swing is GPQA Diamond: 59.5% for Mistral Medium and 30.7% for Qwen1.5-32B.

## Snapshot

| | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 30.0 |
| Rank | 211 | 288 |
| Context | 262K | — |
| Input $/M | $1.50 | — |
| Output $/M | $7.50 | — |
| Weights | Open | Open |

## Coding

- Mistral Medium: 33.8 (#241)
- Qwen1.5-32B: 31.1 (#278)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1434 | 1155 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 763.98 | — |

## Agentic & Tool Use

- Mistral Medium: 28.1 (#84)
- Qwen1.5-32B: —

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |

## Reasoning

- Mistral Medium: 23.3 (#165)
- Qwen1.5-32B: 20.9 (#210)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1131 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |

## Math

- Mistral Medium: 27.2 (#238)
- Qwen1.5-32B: 30.5 (#207)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1409 | 1155 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Medium: 24.9 (#260)
- Qwen1.5-32B: 13.5 (#291)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 59.5% | 30.7% |
| LMArena Expert | 1408 | 1126 |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
| MMLU | — | 74.4% |

## Multimodal

- Mistral Medium: 34.6 (#82)
- Qwen1.5-32B: —

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1172 | — |

## Multilingual

- Mistral Medium: 52.3 (#86)
- Qwen1.5-32B: 31.6 (#254)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1408 | 1106 |
| LMArena Chinese | 1448 | 1176 |
| LMArena French | 1460 | 1100 |
| LMArena German | 1433 | 1058 |
| LMArena Japanese | 1378 | 1027 |
| LMArena Korean | 1382 | 1007 |
| LMArena Russian | 1411 | 1073 |
| LMArena Spanish | 1433 | 1089 |

## Instruction Following

- Mistral Medium: 73.9 (#111)
- Qwen1.5-32B: 58.0 (#260)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1398 | 1116 |

## Long Context

- Mistral Medium: 42.9 (#108)
- Qwen1.5-32B: 34.7 (#241)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1406 | 1146 |

## Writing & Preference

- Mistral Medium: 60.2 (#97)
- Qwen1.5-32B: 34.4 (#266)

| Benchmark | Mistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1424 | 1137 |
| LMArena Creative Writing | 1391 | 1083 |
| LMArena Multi-Turn | 1418 | 1140 |
| Short-Story Creative Writing | 77.3% | — |

## FAQ

### Is Mistral Medium better than Qwen1.5-32B?

Mistral Medium is the stronger model overall, scoring 36.0 to 30.0 on the Noometry Index.

### Is Mistral Medium or Qwen1.5-32B better for coding?

Mistral Medium scores higher on coding benchmarks: 33.8 versus 31.1 in the Noometry coding category.

### How many benchmarks do Mistral Medium and Qwen1.5-32B share?

18 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen1.5-32B has 21.