Model comparison
Magistral Medium vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 35.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 34.5 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 73.7% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $2 / $5 for Magistral Medium.
Side by side
| Magistral Medium | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 46.0 |
| Released | 2025-03-17 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $0.60 |
| Output $ / M tokens | $5 | $3.60 |
| Results tracked | 22 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Magistral Medium: 39.1 (#161), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1319 | 1465 |
| LMArena WebDev | — | 1400 |
| SciCode | 39.2% | — |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Magistral Medium: 8.6 (#348), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 73.7% |
| LMArena Hard Prompts | 1267 | 1448 |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 58.9% |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |
Math Qwen3.5 397B-A17B leads
Magistral Medium: 35.1 (#189), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1250 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Qwen3.5 397B-A17B leads
Magistral Medium: 33.5 (#202), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1223 | 1462 |
| GPQA Diamond | — | 86.4% |
Multimodal Not comparable
Magistral Medium: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Magistral Medium: 39.6 (#224), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1232 | 1430 |
| LMArena Chinese | 1227 | 1500 |
| LMArena French | 1267 | 1461 |
| LMArena German | 1248 | 1447 |
| LMArena Japanese | 1175 | 1426 |
| LMArena Korean | 1125 | 1384 |
| LMArena Russian | 1224 | 1429 |
| LMArena Spanish | 1271 | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Magistral Medium: 66.0 (#211), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1424 |
Long Context Qwen3.5 397B-A17B leads
Magistral Medium: 39.3 (#183), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1295 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Magistral Medium: 46.3 (#219), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Magistral Medium | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1255 | 1438 |
| LMArena Creative Writing | 1245 | 1401 |
| LMArena Multi-Turn | 1275 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is Magistral Medium better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Magistral Medium and Qwen3.5 397B-A17B share?
18 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3.5 397B-A17B has 36.