# Magistral Small vs Qwen3 32B

> Qwen3 32B is the stronger model overall, scoring 38.8 to 29.9 on the Noometry Index. Magistral Small costs 1.6× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/magistral-small-vs-qwen3-32b
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Magistral Small scores higher in 1 category and Qwen3 32B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 37.9 to 24.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 6.3% for Magistral Small and 54.9% for Qwen3 32B.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Qwen3 32B accepts more context: 131K tokens versus 128K.

## Snapshot

| | Magistral Small | Qwen3 32B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 38.8 |
| Rank | 289 | 166 |
| Context | 128K | 131K |
| Input $/M | $0.50 | $0.70 |
| Output $/M | $1.50 | $2.80 |
| Weights | Open | Open |

## Coding

- Magistral Small: 37.8 (#172)
- Qwen3 32B: 37.3 (#184)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| SciCode | 35.2% | 35.4% |
| Aider Polyglot | — | 40% |
| LMArena Coding | — | 1358 |

## Agentic & Tool Use

- Magistral Small: —
- Qwen3 32B: 32.3 (#58)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Magistral Small: 6.9 (#345)
- Qwen3 32B: 19.6 (#233)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 6.3% | 54.9% |
| CritPt | 0.3% | 0.3% |
| Chess Puzzles | 3% | 5% |
| DTBench | 61.3% | 67.5% |
| Epoch Capabilities Index | 133.19 | 138.51 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 5% | — |
| LMArena Hard Prompts | — | 1335 |
| LMCA | — | 17.3% |

## Math

- Magistral Small: 24.9 (#253)
- Qwen3 32B: 37.9 (#89)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 66.9% |
| LMArena Math | — | 1399 |

## Knowledge

- Magistral Small: 30.9 (#215)
- Qwen3 32B: 40.0 (#112)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 56.1% | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |

## Multilingual

- Magistral Small: —
- Qwen3 32B: 45.8 (#162)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |

## Instruction Following

- Magistral Small: —
- Qwen3 32B: 69.1 (#174)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |

## Long Context

- Magistral Small: —
- Qwen3 32B: 43.7 (#83)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |

## Writing & Preference

- Magistral Small: —
- Qwen3 32B: 53.1 (#158)

| Benchmark | Magistral Small | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |

## FAQ

### Is Magistral Small better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 38.8 to 29.9 on the Noometry Index. Magistral Small costs 1.6× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

### Which is cheaper, Magistral Small or Qwen3 32B?

Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

### Is Magistral Small or Qwen3 32B better for coding?

They score almost the same on coding (37.8 vs 37.3); test both on your own repository before choosing.

### Which has the bigger context window?

Qwen3 32B does, with 131K tokens against 128K.

### How many benchmarks do Magistral Small and Qwen3 32B share?

8 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Qwen3 32B has 26.