Model comparison
MiMo-V2-Pro vs Step 3
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. MiMo-V2-Pro scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 54.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Step 3 | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 43.0 | 40.5 |
| Released | 2026-03-18 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 23 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
MiMo-V2-Pro: 43.8 (#83), Step 3: 40.1 (#147)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Coding | 1476 | 1367 |
| LMArena WebDev | 1433 | — |
| ALE-Bench | 785.17 | — |
Reasoning Step 3 leads
MiMo-V2-Pro: 22.1 (#206), Step 3: 28.4 (#105)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 25.8% | — |
| Thematic Generalization | 45.9% | — |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 39.5 (#102), Step 3: 37.6 (#148)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Math | 1447 | 1366 |
Knowledge MiMo-V2-Pro leads
MiMo-V2-Pro: 41.4 (#111), Step 3: 36.8 (#164)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Expert | 1478 | 1333 |
Multimodal Not comparable
MiMo-V2-Pro: —, Step 3: 35.5 (#86)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual MiMo-V2-Pro leads
MiMo-V2-Pro: 52.7 (#81), Step 3: 46.3 (#159)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Non-English | 1416 | 1327 |
| LMArena Chinese | 1456 | 1397 |
| LMArena German | 1417 | 1371 |
| LMArena Korean | 1400 | 1269 |
| LMArena Russian | 1427 | 1331 |
| LMArena Spanish | 1457 | 1371 |
| LMArena French | 1469 | — |
| LMArena Japanese | 1366 | — |
Instruction Following MiMo-V2-Pro leads
MiMo-V2-Pro: 76.0 (#49), Step 3: 70.4 (#164)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1445 | 1332 |
Long Context MiMo-V2-Pro leads
MiMo-V2-Pro: 41.5 (#138), Step 3: 40.3 (#157)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Longer Query | 1455 | 1326 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
Writing & Preference MiMo-V2-Pro leads
MiMo-V2-Pro: 62.8 (#70), Step 3: 54.3 (#151)
| Benchmark | MiMo-V2-Pro | Step 3 |
|---|---|---|
| LMArena Text | 1436 | 1350 |
| LMArena Creative Writing | 1415 | 1321 |
| LMArena Multi-Turn | 1456 | 1341 |
Frequently asked questions
Is MiMo-V2-Pro better than Step 3?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 40.5 on the Noometry Index.
Is MiMo-V2-Pro or Step 3 better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 40.1 in the Noometry coding category.
How many benchmarks do MiMo-V2-Pro and Step 3 share?
15 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Step 3 has 17.