Model comparison
MiMo-V2-Flash vs Step 3
MiMo-V2-Flash and Step 3 score almost the same on the Noometry Index (41.3 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. MiMo-V2-Flash scores higher in 6 categories and Step 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Flash leads 59.7 to 54.3.
Side by side
| MiMo-V2-Flash | Step 3 | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 41.3 | 40.5 |
| Released | 2025-12-16 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
MiMo-V2-Flash: 36.1 (#211), Step 3: 40.1 (#147)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Coding | 1443 | 1367 |
| LMArena WebDev | 1330 | — |
| SciCode | 25.9% | — |
| ALE-Bench | 737.95 | — |
Reasoning Step 3 leads
MiMo-V2-Flash: 24.9 (#157), Step 3: 28.4 (#105)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 0% | — |
Math Too close to call
MiMo-V2-Flash: 38.3 (#139), Step 3: 37.6 (#148)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Math | 1396 | 1366 |
Knowledge MiMo-V2-Flash leads
MiMo-V2-Flash: 39.7 (#131), Step 3: 36.8 (#164)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Expert | 1425 | 1333 |
Multimodal Not comparable
MiMo-V2-Flash: —, Step 3: 35.5 (#86)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual MiMo-V2-Flash leads
MiMo-V2-Flash: 51.0 (#113), Step 3: 46.3 (#159)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Non-English | 1392 | 1327 |
| LMArena Chinese | 1462 | 1397 |
| LMArena German | 1395 | 1371 |
| LMArena Korean | 1358 | 1269 |
| LMArena Russian | 1387 | 1331 |
| LMArena Spanish | 1420 | 1371 |
| LMArena French | 1429 | — |
| LMArena Japanese | 1325 | — |
Instruction Following MiMo-V2-Flash leads
MiMo-V2-Flash: 73.5 (#120), Step 3: 70.4 (#164)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1392 | 1332 |
Long Context MiMo-V2-Flash leads
MiMo-V2-Flash: 43.0 (#110), Step 3: 40.3 (#157)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Longer Query | 1409 | 1326 |
Writing & Preference MiMo-V2-Flash leads
MiMo-V2-Flash: 59.7 (#106), Step 3: 54.3 (#151)
| Benchmark | MiMo-V2-Flash | Step 3 |
|---|---|---|
| LMArena Text | 1411 | 1350 |
| LMArena Creative Writing | 1375 | 1321 |
| LMArena Multi-Turn | 1404 | 1341 |
Frequently asked questions
Is MiMo-V2-Flash better than Step 3?
MiMo-V2-Flash and Step 3 score almost the same on the Noometry Index (41.3 vs 40.5), so choose on price, context window or the category you care about most.
Is MiMo-V2-Flash or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 36.1 in the Noometry coding category.
How many benchmarks do MiMo-V2-Flash and Step 3 share?
15 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Step 3 has 17.