Model comparison
MiMo-V2-Omni vs Step 3
MiMo-V2-Omni is the stronger model overall, scoring 43.6 to 40.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. MiMo-V2-Omni scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Omni leads 61.4 to 54.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Omni | Step 3 | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 43.6 | 40.5 |
| Released | 2026-03-18 | — |
| Weights | Proprietary | Open |
| Context window | 262K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Omni leads
MiMo-V2-Omni: 43.3 (#89), Step 3: 40.1 (#147)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Coding | 1466 | 1367 |
Reasoning MiMo-V2-Omni leads
MiMo-V2-Omni: 29.7 (#88), Step 3: 28.4 (#105)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1445 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math MiMo-V2-Omni leads
MiMo-V2-Omni: 39.1 (#115), Step 3: 37.6 (#148)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Math | 1430 | 1366 |
Knowledge MiMo-V2-Omni leads
MiMo-V2-Omni: 40.5 (#118), Step 3: 36.8 (#164)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Expert | 1449 | 1333 |
Multimodal MiMo-V2-Omni leads
MiMo-V2-Omni: 38.6 (#63), Step 3: 35.5 (#86)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Vision | 1228 | 1177 |
Multilingual MiMo-V2-Omni leads
MiMo-V2-Omni: 51.8 (#102), Step 3: 46.3 (#159)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Non-English | 1404 | 1327 |
| LMArena Chinese | 1465 | 1397 |
| LMArena German | 1399 | 1371 |
| LMArena Korean | 1355 | 1269 |
| LMArena Russian | 1412 | 1331 |
| LMArena Spanish | 1434 | 1371 |
| LMArena French | 1447 | — |
| LMArena Japanese | 1317 | — |
Instruction Following MiMo-V2-Omni leads
MiMo-V2-Omni: 75.2 (#66), Step 3: 70.4 (#164)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1332 |
Long Context MiMo-V2-Omni leads
MiMo-V2-Omni: 44.1 (#76), Step 3: 40.3 (#157)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Longer Query | 1442 | 1326 |
Writing & Preference MiMo-V2-Omni leads
MiMo-V2-Omni: 61.4 (#87), Step 3: 54.3 (#151)
| Benchmark | MiMo-V2-Omni | Step 3 |
|---|---|---|
| LMArena Text | 1423 | 1350 |
| LMArena Creative Writing | 1392 | 1321 |
| LMArena Multi-Turn | 1445 | 1341 |
Frequently asked questions
Is MiMo-V2-Omni better than Step 3?
MiMo-V2-Omni is the stronger model overall, scoring 43.6 to 40.5 on the Noometry Index.
Is MiMo-V2-Omni or Step 3 better for coding?
MiMo-V2-Omni scores higher on coding benchmarks: 43.3 versus 40.1 in the Noometry coding category.
How many benchmarks do MiMo-V2-Omni and Step 3 share?
16 benchmarks have published results for both models. MiMo-V2-Omni has 18 scored results on Noometry and Step 3 has 17.