Model comparison
MiMo-V2-Omni vs Phi-4 Mini
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 30.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where MiMo-V2-Omni leads 42.7 to 27.6.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2-Omni.
- MiMo-V2-Omni accepts more context: 262K tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Omni | Phi-4 Mini | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 42.9 | 30.4 |
| Released | 2026-03-18 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 262K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.14 | $0.075 |
| Output $ / M tokens | $0.28 | $0.30 |
| Results tracked | 18 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Omni leads
MiMo-V2-Omni: 42.7 (#87), Phi-4 Mini: 27.6 (#312)
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LMArena Coding | 1467 | — |
Reasoning MiMo-V2-Omni leads
MiMo-V2-Omni: 28.6 (#86), Phi-4 Mini: 21.7 (#190)
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1445 | — |
Math Not comparable
MiMo-V2-Omni: 36.4 (#112), Phi-4 Mini: —
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1432 | — |
Knowledge MiMo-V2-Omni leads
MiMo-V2-Omni: 39.9 (#114), Phi-4 Mini: 24.8 (#261)
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1449 | — |
Multimodal Not comparable
MiMo-V2-Omni: 37.9 (#62), Phi-4 Mini: —
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1228 | — |
Multilingual Not comparable
MiMo-V2-Omni: 52.0 (#97), Phi-4 Mini: —
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1404 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1448 | — |
| LMArena German | 1398 | — |
| LMArena Japanese | 1318 | — |
| LMArena Korean | 1355 | — |
| LMArena Russian | 1412 | — |
| LMArena Spanish | 1432 | — |
Instruction Following Not comparable
MiMo-V2-Omni: 75.4 (#62), Phi-4 Mini: —
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1428 | — |
Long Context Not comparable
MiMo-V2-Omni: 44.1 (#72), Phi-4 Mini: —
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1442 | — |
Writing & Preference Not comparable
MiMo-V2-Omni: 61.6 (#83), Phi-4 Mini: —
| Benchmark | MiMo-V2-Omni | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1424 | — |
| LMArena Creative Writing | 1393 | — |
| LMArena Multi-Turn | 1446 | — |
Frequently asked questions
Is MiMo-V2-Omni better than Phi-4 Mini?
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 30.4 on the Noometry Index.
Which is cheaper, MiMo-V2-Omni or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; MiMo-V2-Omni lists at $0.14 and $0.28.
Is MiMo-V2-Omni or Phi-4 Mini better for coding?
MiMo-V2-Omni scores higher on coding benchmarks: 42.7 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Omni does, with 262K tokens against 128K.
How many benchmarks do MiMo-V2-Omni and Phi-4 Mini share?
0 benchmarks have published results for both models. MiMo-V2-Omni has 18 scored results on Noometry and Phi-4 Mini has 3.