Model comparison
MiMo-V2.5-Pro vs MiMo-V2-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 8 categories and MiMo-V2-Pro in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5-Pro leads 26.8 to 22.1.
- The biggest single-benchmark swing is NYT Connections (extended): 34.4% for MiMo-V2.5-Pro and 25.8% for MiMo-V2-Pro.
- Both cost about the same: $0.43 input and $0.87 output per million tokens.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5-Pro | MiMo-V2-Pro | |
|---|---|---|
| Provider | Xiaomi | Xiaomi |
| Noometry Index | 45.2 | 43.0 |
| Released | 2026-04-22 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.43 | $0.43 |
| Output $ / M tokens | $0.87 | $0.87 |
| Results tracked | 27 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.4 (#60), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1479 | 1433 |
| LMArena Coding | 1503 | 1476 |
| ALE-Bench | 899.8 | 785.17 |
| SciCode | 50.2% | — |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 26.8 (#130), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 34.4% | 25.8% |
| LMArena Hard Prompts | 1488 | 1457 |
| CritPt | 4% | — |
| Thematic Generalization | — | 45.9% |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
Math Too close to call
MiMo-V2.5-Pro: 40.0 (#96), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1481 | 1447 |
| ProofBench | 22% | — |
Knowledge Too close to call
MiMo-V2.5-Pro: 42.2 (#98), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1503 | 1478 |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.1 (#34), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1449 | 1416 |
| LMArena Chinese | 1507 | 1456 |
| LMArena French | 1488 | 1469 |
| LMArena German | 1458 | 1417 |
| LMArena Japanese | 1412 | 1366 |
| LMArena Korean | 1437 | 1400 |
| LMArena Russian | 1450 | 1427 |
| LMArena Spanish | 1471 | 1457 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.5 (#21), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1477 | 1445 |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#37), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1483 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.3 (#49), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | MiMo-V2.5-Pro | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1465 | 1436 |
| LMArena Creative Writing | 1440 | 1415 |
| LMArena Multi-Turn | 1477 | 1456 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than MiMo-V2-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.0 on the Noometry Index.
Which is cheaper, MiMo-V2.5-Pro or MiMo-V2-Pro?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is MiMo-V2.5-Pro or MiMo-V2-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 43.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do MiMo-V2.5-Pro and MiMo-V2-Pro share?
20 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and MiMo-V2-Pro has 23.