Model comparison
Magistral Medium vs Qwen2-72B
Magistral Medium is the stronger model overall, scoring 35.2 to 30.0 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 Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2-72B leads 23.2 to 8.6.
Side by side
| Magistral Medium | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 30.0 |
| Released | 2025-03-17 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| 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), Qwen2-72B: 29.1 (#310)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1319 | 1196 |
| SciCode | 39.2% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Magistral Medium: 8.6 (#348), Qwen2-72B: 23.2 (#181)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1191 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Epoch Capabilities Index | — | 125.28 |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Qwen2-72B: 30.2 (#236)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Math | 1250 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Qwen2-72B: 21.2 (#275)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1223 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Qwen2-72B: 35.9 (#244)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1232 | 1176 |
| LMArena Chinese | 1227 | 1240 |
| LMArena French | 1267 | 1170 |
| LMArena German | 1248 | 1151 |
| LMArena Japanese | 1175 | 1111 |
| LMArena Korean | 1125 | 1083 |
| LMArena Russian | 1224 | 1169 |
| LMArena Spanish | 1271 | 1169 |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Qwen2-72B: 61.7 (#241)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1181 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Qwen2-72B: 36.1 (#235)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1295 | 1192 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Qwen2-72B: 40.8 (#241)
| Benchmark | Magistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Text | 1255 | 1203 |
| LMArena Creative Writing | 1245 | 1181 |
| LMArena Multi-Turn | 1275 | 1196 |
Frequently asked questions
Is Magistral Medium better than Qwen2-72B?
Magistral Medium is the stronger model overall, scoring 35.2 to 30.0 on the Noometry Index.
Is Magistral Medium or Qwen2-72B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 29.1 in the Noometry coding category.
How many benchmarks do Magistral Medium and Qwen2-72B share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2-72B has 26.