Model comparison
Magistral Medium vs Qwen1.5-32B
Magistral Medium is the stronger model overall, scoring 35.2 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Magistral 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 knowledge, where Magistral Medium leads 33.5 to 13.5.
Side by side
| Magistral Medium | Qwen1.5-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 30.5 |
| Released | 2025-03-17 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1319 | 1155 |
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen1.5-32B leads
Magistral Medium: 8.6 (#348), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1130 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1250 | 1155 |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1223 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1232 | 1106 |
| LMArena Chinese | 1227 | 1177 |
| LMArena French | 1267 | 1101 |
| LMArena German | 1248 | 1058 |
| LMArena Japanese | 1175 | 1027 |
| LMArena Korean | 1125 | 1008 |
| LMArena Russian | 1224 | 1073 |
| LMArena Spanish | 1271 | 1089 |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1116 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1295 | 1146 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Magistral Medium | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1255 | 1137 |
| LMArena Creative Writing | 1245 | 1083 |
| LMArena Multi-Turn | 1275 | 1140 |
Frequently asked questions
Is Magistral Medium better than Qwen1.5-32B?
Magistral Medium is the stronger model overall, scoring 35.2 to 30.5 on the Noometry Index.
Is Magistral Medium or Qwen1.5-32B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 31.7 in the Noometry coding category.
How many benchmarks do Magistral Medium and Qwen1.5-32B share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen1.5-32B has 21.