Model comparison
Magistral Medium vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 35.2 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 2 categories and Qwen2.5 Plus 1127 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2.5 Plus 1127 leads 25.9 to 8.6.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 38.8 |
| Released | 2025-03-17 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Magistral Medium: 39.1 (#161), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1319 | 1314 |
| SciCode | 39.2% | — |
Reasoning Qwen2.5 Plus 1127 leads
Magistral Medium: 8.6 (#348), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1299 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Qwen2.5 Plus 1127 leads
Magistral Medium: 35.1 (#189), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1250 | 1298 |
Knowledge Qwen2.5 Plus 1127 leads
Magistral Medium: 33.5 (#202), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1223 | 1289 |
Multilingual Qwen2.5 Plus 1127 leads
Magistral Medium: 39.6 (#224), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1232 | 1265 |
| LMArena Chinese | 1227 | 1314 |
| LMArena German | 1248 | 1231 |
| LMArena Japanese | 1175 | 1207 |
| LMArena Russian | 1224 | 1271 |
| LMArena French | 1267 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Qwen2.5 Plus 1127 leads
Magistral Medium: 66.0 (#211), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1275 |
Long Context Too close to call
Magistral Medium: 39.3 (#183), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1295 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Magistral Medium: 46.3 (#219), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | Magistral Medium | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1255 | 1299 |
| LMArena Creative Writing | 1245 | 1262 |
| LMArena Multi-Turn | 1275 | 1299 |
Frequently asked questions
Is Magistral Medium better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 35.2 on the Noometry Index.
Is Magistral Medium or Qwen2.5 Plus 1127 better for coding?
They score almost the same on coding (39.1 vs 38.5); test both on your own repository before choosing.
How many benchmarks do Magistral Medium and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2.5 Plus 1127 has 14.