Model comparison
MiMo-V2-Flash vs Phi-4
MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 30.9 on the Noometry Index. Phi-4 costs 2.0× less per token, which makes it the better buy when MiMo-V2-Flash's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiMo-V2-Flash scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Flash leads 59.9 to 40.7.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2-Flash.
- MiMo-V2-Flash accepts more context: 262K tokens versus 128K.
Side by side
| MiMo-V2-Flash | Phi-4 | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 40.8 | 30.9 |
| Released | 2025-12-16 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.14 | $0.07 |
| Output $ / M tokens | $0.28 | $0.14 |
| Results tracked | 21 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Flash leads
MiMo-V2-Flash: 35.8 (#205), Phi-4: 33.8 (#237)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Coding | 1443 | 1231 |
| LMArena WebDev | 1330 | — |
| SciCode | 25.9% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 737.95 | — |
Agentic & Tool Use Not comparable
MiMo-V2-Flash: —, Phi-4: 22.6 (#120)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning MiMo-V2-Flash leads
MiMo-V2-Flash: 24.1 (#155), Phi-4: 17.0 (#287)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1220 |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.43 |
| LiveBench | — | 41.6% |
Math MiMo-V2-Flash leads
MiMo-V2-Flash: 35.6 (#141), Phi-4: 19.6 (#279)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Math | 1396 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge MiMo-V2-Flash leads
MiMo-V2-Flash: 39.1 (#126), Phi-4: 32.5 (#204)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Expert | 1425 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multilingual MiMo-V2-Flash leads
MiMo-V2-Flash: 51.1 (#109), Phi-4: 37.4 (#232)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Non-English | 1391 | 1197 |
| LMArena Chinese | 1463 | 1211 |
| LMArena French | 1429 | 1223 |
| LMArena German | 1395 | 1222 |
| LMArena Japanese | 1324 | 1158 |
| LMArena Korean | 1358 | 1151 |
| LMArena Russian | 1387 | 1209 |
| LMArena Spanish | 1420 | 1234 |
Instruction Following MiMo-V2-Flash leads
MiMo-V2-Flash: 73.7 (#115), Phi-4: 60.6 (#246)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1392 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context MiMo-V2-Flash leads
MiMo-V2-Flash: 43.0 (#106), Phi-4: 36.9 (#221)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1409 | 1217 |
Writing & Preference MiMo-V2-Flash leads
MiMo-V2-Flash: 59.9 (#101), Phi-4: 40.7 (#239)
| Benchmark | MiMo-V2-Flash | Phi-4 |
|---|---|---|
| LMArena Text | 1411 | 1217 |
| LMArena Creative Writing | 1375 | 1182 |
| LMArena Multi-Turn | 1404 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is MiMo-V2-Flash better than Phi-4?
MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 30.9 on the Noometry Index. Phi-4 costs 2.0× less per token, which makes it the better buy when MiMo-V2-Flash's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2-Flash or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; MiMo-V2-Flash lists at $0.14 and $0.28.
Is MiMo-V2-Flash or Phi-4 better for coding?
MiMo-V2-Flash scores higher on coding benchmarks: 35.8 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Flash does, with 262K tokens against 128K.
How many benchmarks do MiMo-V2-Flash and Phi-4 share?
17 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Phi-4 has 37.