Model comparison
MiMo-V2-Flash vs Sonar
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in writing & preference, where MiMo-V2-Flash leads 59.7 to 52.6.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $1 / $1 for Sonar.
- MiMo-V2-Flash accepts more context: 262K tokens versus 128K.
- MiMo-V2-Flash has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Flash | Sonar | |
|---|---|---|
| Provider | Xiaomi | Perplexity |
| Noometry Index | 41.3 | 38.5 |
| Released | 2025-12-16 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.14 | $1 |
| Output $ / M tokens | $0.28 | $1 |
| Results tracked | 21 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
MiMo-V2-Flash: 36.1 (#211), Sonar: 35.7 (#221)
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LMArena WebDev | 1330 | — |
| SciCode | 25.9% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1443 | — |
| ALE-Bench | 737.95 | — |
Reasoning MiMo-V2-Flash leads
MiMo-V2-Flash: 24.9 (#157), Sonar: 21.1 (#227)
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| CritPt | 0% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1420 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math MiMo-V2-Flash leads
MiMo-V2-Flash: 38.3 (#139), Sonar: 33.7 (#200)
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1396 | — |
Knowledge Not comparable
MiMo-V2-Flash: 39.7 (#131), Sonar: —
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LMArena Expert | 1425 | — |
Multilingual Not comparable
MiMo-V2-Flash: 51.0 (#113), Sonar: —
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LMArena Non-English | 1392 | — |
| LMArena Chinese | 1462 | — |
| LMArena French | 1429 | — |
| LMArena German | 1395 | — |
| LMArena Japanese | 1325 | — |
| LMArena Korean | 1358 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1420 | — |
Instruction Following MiMo-V2-Flash leads
MiMo-V2-Flash: 73.5 (#120), Sonar: 71.4 (#150)
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1392 | — |
Long Context Not comparable
MiMo-V2-Flash: 43.0 (#110), Sonar: —
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LMArena Longer Query | 1409 | — |
Writing & Preference MiMo-V2-Flash leads
MiMo-V2-Flash: 59.7 (#106), Sonar: 52.6 (#167)
| Benchmark | MiMo-V2-Flash | Sonar |
|---|---|---|
| LMArena Text | 1411 | — |
| LMArena Creative Writing | 1375 | — |
| LMArena Multi-Turn | 1404 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is MiMo-V2-Flash better than Sonar?
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 38.5 on the Noometry Index.
Which is cheaper, MiMo-V2-Flash or Sonar?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Sonar lists at $1 and $1.
Is MiMo-V2-Flash or Sonar better for coding?
They score almost the same on coding (36.1 vs 35.7); test both on your own repository before choosing.
Which has the bigger context window?
MiMo-V2-Flash does, with 262K tokens against 128K.
How many benchmarks do MiMo-V2-Flash and Sonar share?
0 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Sonar has 7.