Model comparison
Magistral Small vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.2 on the Noometry Index.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Magistral Small scores higher in 0 categories and MiMo-V2.5-Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5-Pro leads 26.8 to 6.8.
- The biggest single-benchmark swing is DTBench: 61.3% for Magistral Small and 84.5% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 128K.
Side by side
| Magistral Small | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Mistral AI | Xiaomi |
| Noometry Index | 30.2 | 45.2 |
| Released | 2025-06-10 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 128K | 1.05M |
| Max output | 40K | 131K |
| Input $ / M tokens | $0.50 | $0.43 |
| Output $ / M tokens | $1.50 | $0.87 |
| Results tracked | 10 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Magistral Small: 38.4 (#176), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 35.2% | 50.2% |
| LMArena WebDev | — | 1479 |
| LMArena Coding | — | 1503 |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Magistral Small: 6.8 (#350), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0.3% | 4% |
| DTBench | 61.3% | 84.5% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 5% | — |
| Chess Puzzles | 3% | — |
| LMArena Hard Prompts | — | 1488 |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | 133.19 | — |
Math MiMo-V2.5-Pro leads
Magistral Small: 26.2 (#261), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| ProofBench | — | 22% |
| LMArena Math | — | 1481 |
Knowledge MiMo-V2.5-Pro leads
Magistral Small: 30.9 (#223), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| LMArena Expert | — | 1503 |
Multilingual Not comparable
Magistral Small: —, MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | — | 1449 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1488 |
| LMArena German | — | 1458 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1437 |
| LMArena Russian | — | 1450 |
| LMArena Spanish | — | 1471 |
Instruction Following Not comparable
Magistral Small: —, MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1477 |
Long Context Not comparable
Magistral Small: —, MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | — | 1483 |
Writing & Preference Not comparable
Magistral Small: —, MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Magistral Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | — | 1465 |
| LMArena Creative Writing | — | 1440 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Magistral Small better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.2 on the Noometry Index.
Which is cheaper, Magistral Small 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 Small lists at $0.50 and $1.50.
Is Magistral Small or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 38.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 128K.
How many benchmarks do Magistral Small and MiMo-V2.5-Pro share?
3 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and MiMo-V2.5-Pro has 27.