Model comparison
Magistral Medium vs Qwen1.5-72B
Magistral Medium is the stronger model overall, scoring 34.8 to 30.3 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 Qwen1.5-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 32.9 to 11.5.
Side by side
| Magistral Medium | Qwen1.5-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 30.3 |
| Released | 2025-03-17 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 38.6 (#161), Qwen1.5-72B: 31.4 (#272)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1319 | 1166 |
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Qwen1.5-72B leads
Magistral Medium: 8.7 (#342), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1148 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Magistral Medium leads
Magistral Medium: 32.4 (#187), Qwen1.5-72B: 30.7 (#205)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1249 | 1164 |
Knowledge Magistral Medium leads
Magistral Medium: 32.9 (#199), Qwen1.5-72B: 11.5 (#295)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1222 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Magistral Medium leads
Magistral Medium: 39.8 (#219), Qwen1.5-72B: 33.4 (#248)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1232 | 1135 |
| LMArena Chinese | 1225 | 1186 |
| LMArena French | 1268 | 1158 |
| LMArena German | 1248 | 1084 |
| LMArena Japanese | 1176 | 1061 |
| LMArena Korean | 1125 | 1049 |
| LMArena Russian | 1224 | 1104 |
| LMArena Spanish | 1269 | 1110 |
Instruction Following Magistral Medium leads
Magistral Medium: 66.2 (#207), Qwen1.5-72B: 59.6 (#251)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1142 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#178), Qwen1.5-72B: 35.0 (#238)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1295 | 1157 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.5 (#214), Qwen1.5-72B: 37.4 (#253)
| Benchmark | Magistral Medium | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1255 | 1166 |
| LMArena Creative Writing | 1245 | 1137 |
| LMArena Multi-Turn | 1275 | 1160 |
Frequently asked questions
Is Magistral Medium better than Qwen1.5-72B?
Magistral Medium is the stronger model overall, scoring 34.8 to 30.3 on the Noometry Index.
Is Magistral Medium or Qwen1.5-72B better for coding?
Magistral Medium scores higher on coding benchmarks: 38.6 versus 31.4 in the Noometry coding category.
How many benchmarks do Magistral Medium and Qwen1.5-72B share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen1.5-72B has 22.