Model comparison
Magistral Medium vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 34.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Max Preview leads 40.8 to 8.7.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 51.1 |
| Released | 2025-03-17 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $1.30 |
| Output $ / M tokens | $5 | $7.80 |
| Results tracked | 22 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Magistral Medium: 38.6 (#161), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1319 | 1472 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| SciCode | 39.2% | — |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3.6 Max Preview: —
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Magistral Medium: 8.7 (#342), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1457 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 74.1% |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.27 |
Math Qwen3.6 Max Preview leads
Magistral Medium: 32.4 (#187), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1249 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Magistral Medium: 32.9 (#199), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1222 | 1476 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
Multilingual Qwen3.6 Max Preview leads
Magistral Medium: 39.8 (#219), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1232 | 1436 |
| LMArena Chinese | 1225 | 1487 |
| LMArena French | 1268 | 1449 |
| LMArena Russian | 1224 | 1444 |
| LMArena Spanish | 1269 | 1452 |
| LMArena German | 1248 | — |
| LMArena Japanese | 1176 | — |
| LMArena Korean | 1125 | — |
Instruction Following Qwen3.6 Max Preview leads
Magistral Medium: 66.2 (#207), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1254 | 1437 |
Long Context Qwen3.6 Max Preview leads
Magistral Medium: 39.3 (#178), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1295 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Magistral Medium: 46.5 (#214), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | Magistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1255 | 1447 |
| LMArena Creative Writing | 1245 | 1435 |
| LMArena Multi-Turn | 1275 | 1456 |
Frequently asked questions
Is Magistral Medium better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 34.8 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3.6 Max Preview?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Magistral Medium or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 38.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 128K.
How many benchmarks do Magistral Medium and Qwen3.6 Max Preview share?
14 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3.6 Max Preview has 29.