Model comparison
Magistral Medium vs Qwen Max
Magistral Medium and Qwen Max score almost the same on the Noometry Index (35.2 vs 34.7), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 3 categories and Qwen Max in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Max leads 25.1 to 8.6.
- Both cost about the same: $2 input and $5 output per million tokens.
- Magistral Medium accepts more context: 262K tokens versus 33K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Qwen Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 34.7 |
| Released | 2025-03-17 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 262K | 33K |
| Max output | 16K | 8K |
| Input $ / M tokens | $2 | $1.60 |
| Output $ / M tokens | $5 | $6.40 |
| Results tracked | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Qwen Max: 30.7 (#292)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Coding | 1319 | 1288 |
| Aider Polyglot | — | 21.8% |
| SciCode | 39.2% | — |
Reasoning Qwen Max leads
Magistral Medium: 8.6 (#348), Qwen Max: 25.1 (#151)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1269 |
| 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), Qwen Max: 22.3 (#276)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Math | 1250 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Qwen Max: 30.3 (#228)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Expert | 1223 | 1248 |
| GPQA Diamond | — | 56.1% |
Multilingual Qwen Max leads
Magistral Medium: 39.6 (#224), Qwen Max: 41.8 (#202)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Non-English | 1232 | 1263 |
| LMArena Chinese | 1227 | 1254 |
| LMArena French | 1267 | 1330 |
| LMArena German | 1248 | 1254 |
| LMArena Japanese | 1175 | 1205 |
| LMArena Korean | 1125 | 1142 |
| LMArena Russian | 1224 | 1274 |
| LMArena Spanish | 1271 | 1290 |
Instruction Following Too close to call
Magistral Medium: 66.0 (#211), Qwen Max: 66.5 (#208)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1254 | 1262 |
Long Context Too close to call
Magistral Medium: 39.3 (#183), Qwen Max: 39.4 (#180)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1295 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Magistral Medium: 46.3 (#219), Qwen Max: 47.8 (#205)
| Benchmark | Magistral Medium | Qwen Max |
|---|---|---|
| LMArena Text | 1255 | 1282 |
| LMArena Creative Writing | 1245 | 1248 |
| LMArena Multi-Turn | 1275 | 1277 |
Frequently asked questions
Is Magistral Medium better than Qwen Max?
Magistral Medium and Qwen Max score almost the same on the Noometry Index (35.2 vs 34.7), so choose on price, context window or the category you care about most.
Which is cheaper, Magistral Medium or Qwen Max?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Magistral Medium or Qwen Max better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 33K.
How many benchmarks do Magistral Medium and Qwen Max share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen Max has 23.