Model comparison
Magistral Medium vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 35.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 46.3.
- The biggest single-benchmark swing is SciCode: 39.2% for Magistral Medium and 50.2% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $5 for Magistral Medium.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 262K.
Side by side
| Magistral Medium | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Mistral AI | Xiaomi |
| Noometry Index | 35.2 | 45.2 |
| Released | 2025-03-17 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 262K | 1.05M |
| Max output | 16K | 131K |
| Input $ / M tokens | $2 | $0.43 |
| Output $ / M tokens | $5 | $0.87 |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Magistral Medium: 39.1 (#161), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 39.2% | 50.2% |
| LMArena Coding | 1319 | 1503 |
| LMArena WebDev | — | 1479 |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Magistral Medium: 8.6 (#348), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0.3% | 4% |
| LMArena Hard Prompts | 1267 | 1488 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 6.1% | — |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
Math MiMo-V2.5-Pro leads
Magistral Medium: 35.1 (#189), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1250 | 1481 |
| ProofBench | — | 22% |
Knowledge MiMo-V2.5-Pro leads
Magistral Medium: 33.5 (#202), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1223 | 1503 |
Multilingual MiMo-V2.5-Pro leads
Magistral Medium: 39.6 (#224), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1232 | 1449 |
| LMArena Chinese | 1227 | 1507 |
| LMArena French | 1267 | 1488 |
| LMArena German | 1248 | 1458 |
| LMArena Japanese | 1175 | 1412 |
| LMArena Korean | 1125 | 1437 |
| LMArena Russian | 1224 | 1450 |
| LMArena Spanish | 1271 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Magistral Medium: 66.0 (#211), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1254 | 1477 |
Long Context MiMo-V2.5-Pro leads
Magistral Medium: 39.3 (#183), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1295 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Magistral Medium: 46.3 (#219), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Magistral Medium | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1255 | 1465 |
| LMArena Creative Writing | 1245 | 1440 |
| LMArena Multi-Turn | 1275 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Magistral Medium better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 262K.
How many benchmarks do Magistral Medium and MiMo-V2.5-Pro share?
19 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and MiMo-V2.5-Pro has 27.