Model comparison
MiMo-V2.5 vs Sonar
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 52.6.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1 / $1 for Sonar.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 128K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5 | Sonar | |
|---|---|---|
| Provider | Xiaomi | Perplexity |
| Noometry Index | 43.4 | 38.5 |
| Released | 2026-04-22 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.14 | $1 |
| Output $ / M tokens | $0.28 | $1 |
| Results tracked | 23 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Sonar: 35.7 (#221)
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1469 | — |
| ALE-Bench | 513.95 | — |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Sonar: 21.1 (#227)
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| CritPt | 3.7% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1450 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Sonar: 33.7 (#200)
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| ProofBench | 16% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1436 | — |
Knowledge Not comparable
MiMo-V2.5: 40.8 (#115), Sonar: —
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Expert | 1460 | — |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Sonar: —
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual Not comparable
MiMo-V2.5: 51.9 (#99), Sonar: —
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Non-English | 1404 | — |
| LMArena Chinese | 1468 | — |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1306 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1395 | — |
| LMArena Spanish | 1416 | — |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Sonar: 71.4 (#150)
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1434 | — |
Long Context Not comparable
MiMo-V2.5: 44.2 (#73), Sonar: —
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Longer Query | 1445 | — |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Sonar: 52.6 (#167)
| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Text | 1428 | — |
| LMArena Creative Writing | 1393 | — |
| LMArena Multi-Turn | 1445 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is MiMo-V2.5 better than Sonar?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 38.5 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Sonar?
MiMo-V2.5 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-V2.5 or Sonar better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 128K.
How many benchmarks do MiMo-V2.5 and Sonar share?
0 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Sonar has 7.