Model comparison
MiMo-V2-Flash vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 41.3 on the Noometry Index. MiMo-V2-Flash costs 3.1× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. MiMo-V2-Flash scores higher in 2 categories and MiMo-V2-Pro in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2-Pro leads 43.8 to 36.1.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 262K.
- MiMo-V2-Flash has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Flash | MiMo-V2-Pro | |
|---|---|---|
| Provider | Xiaomi | Xiaomi |
| Noometry Index | 41.3 | 43.0 |
| Released | 2025-12-16 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.14 | $0.43 |
| Output $ / M tokens | $0.28 | $0.87 |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
MiMo-V2-Flash: 36.1 (#211), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1330 | 1433 |
| LMArena Coding | 1443 | 1476 |
| ALE-Bench | 737.95 | 785.17 |
| SciCode | 25.9% | — |
Reasoning MiMo-V2-Flash leads
MiMo-V2-Flash: 24.9 (#157), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| CritPt | 0% | — |
| Thematic Generalization | — | 45.9% |
Math MiMo-V2-Pro leads
MiMo-V2-Flash: 38.3 (#139), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1396 | 1447 |
Knowledge MiMo-V2-Pro leads
MiMo-V2-Flash: 39.7 (#131), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1425 | 1478 |
Multilingual MiMo-V2-Pro leads
MiMo-V2-Flash: 51.0 (#113), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1392 | 1416 |
| LMArena Chinese | 1462 | 1456 |
| LMArena French | 1429 | 1469 |
| LMArena German | 1395 | 1417 |
| LMArena Japanese | 1325 | 1366 |
| LMArena Korean | 1358 | 1400 |
| LMArena Russian | 1387 | 1427 |
| LMArena Spanish | 1420 | 1457 |
Instruction Following MiMo-V2-Pro leads
MiMo-V2-Flash: 73.5 (#120), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1392 | 1445 |
Long Context MiMo-V2-Flash leads
MiMo-V2-Flash: 43.0 (#110), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1409 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
MiMo-V2-Flash: 59.7 (#106), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | MiMo-V2-Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1411 | 1436 |
| LMArena Creative Writing | 1375 | 1415 |
| LMArena Multi-Turn | 1404 | 1456 |
Frequently asked questions
Is MiMo-V2-Flash better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 41.3 on the Noometry Index. MiMo-V2-Flash costs 3.1× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2-Flash or MiMo-V2-Pro?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is MiMo-V2-Flash or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2-Flash and MiMo-V2-Pro share?
19 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and MiMo-V2-Pro has 23.