Model comparison
Magistral Medium vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 35.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 6.1% for Magistral Medium and 87.5% for Qwen3.8 27B.
- Qwen3.8 27B is cheaper at $0.99 / $1.49 per million input/output tokens, against $2 / $5 for Magistral Medium.
Side by side
| Magistral Medium | Qwen3.8 27B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 46.0 |
| Released | 2025-03-17 | 2026-08-14 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 16K | 33K |
| Input $ / M tokens | $2 | $0.99 |
| Output $ / M tokens | $5 | $1.49 |
| Results tracked | 22 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Magistral Medium: 39.1 (#161), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| SciCode | 39.2% | 46.6% |
| LMArena Coding | 1319 | 1482 |
| LMArena WebDev | — | 1593 |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Magistral Medium: 8.6 (#348), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| ARC-AGI-2 | 0% | 42.4% |
| ARC-AGI-1 | 6.1% | 87.5% |
| CritPt | 0.3% | 5.4% |
| LMArena Hard Prompts | 1267 | 1460 |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 54.5% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
Magistral Medium: 35.1 (#189), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1250 | 1456 |
| ProofBench | — | 16% |
Knowledge Qwen3.8 27B leads
Magistral Medium: 33.5 (#202), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1223 | 1482 |
Multimodal Not comparable
Magistral Medium: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Magistral Medium: 39.6 (#224), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1232 | 1430 |
| LMArena Chinese | 1227 | 1504 |
| LMArena French | 1267 | 1465 |
| LMArena German | 1248 | 1438 |
| LMArena Japanese | 1175 | 1384 |
| LMArena Korean | 1125 | 1393 |
| LMArena Russian | 1224 | 1415 |
| LMArena Spanish | 1271 | 1448 |
Instruction Following Qwen3.8 27B leads
Magistral Medium: 66.0 (#211), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1439 |
Long Context Qwen3.8 27B leads
Magistral Medium: 39.3 (#183), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1295 | 1450 |
Writing & Preference Qwen3.8 27B leads
Magistral Medium: 46.3 (#219), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Magistral Medium | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1255 | 1441 |
| LMArena Creative Writing | 1245 | 1384 |
| LMArena Multi-Turn | 1275 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Magistral Medium better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3.8 27B?
Qwen3.8 27B is cheaper. It lists at $0.99 per million input tokens and $1.49 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 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 Qwen3.8 27B share?
21 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3.8 27B has 31.