Model comparison
Magistral Medium vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 35.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Magistral Medium scores higher in 1 category and Qwen3 32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3 32B leads 20.2 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 54.9% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| Magistral Medium | Qwen3 32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 39.2 |
| Released | 2025-03-17 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 16K | 16K |
| Input $ / M tokens | $2 | $0.70 |
| Output $ / M tokens | $5 | $2.80 |
| Results tracked | 22 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Qwen3 32B: 37.7 (#190)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| SciCode | 39.2% | 35.4% |
| LMArena Coding | 1319 | 1358 |
| Aider Polyglot | — | 40% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Magistral Medium: 8.6 (#348), Qwen3 32B: 20.2 (#241)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 54.9% |
| CritPt | 0.3% | 0.3% |
| LMArena Hard Prompts | 1267 | 1334 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 6.1% | — |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Magistral Medium: 35.1 (#189), Qwen3 32B: 39.7 (#99)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| LMArena Math | 1250 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
Knowledge Qwen3 32B leads
Magistral Medium: 33.5 (#202), Qwen3 32B: 40.0 (#125)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| LMArena Expert | 1223 | 1362 |
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
Multilingual Qwen3 32B leads
Magistral Medium: 39.6 (#224), Qwen3 32B: 45.6 (#167)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1232 | 1317 |
| LMArena Chinese | 1227 | 1357 |
| LMArena German | 1248 | 1341 |
| LMArena Russian | 1224 | 1311 |
| LMArena French | 1267 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Qwen3 32B leads
Magistral Medium: 66.0 (#211), Qwen3 32B: 68.9 (#179)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1305 |
Long Context Qwen3 32B leads
Magistral Medium: 39.3 (#183), Qwen3 32B: 43.8 (#87)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1295 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Magistral Medium: 46.3 (#219), Qwen3 32B: 52.9 (#163)
| Benchmark | Magistral Medium | Qwen3 32B |
|---|---|---|
| LMArena Text | 1255 | 1340 |
| LMArena Creative Writing | 1245 | 1297 |
| LMArena Multi-Turn | 1275 | 1331 |
Frequently asked questions
Is Magistral Medium better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen3 32B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 131K.
How many benchmarks do Magistral Medium and Qwen3 32B share?
16 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3 32B has 26.