Model comparison
MiMo-V2.6-Flash vs Step 3
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 40.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. MiMo-V2.6-Flash scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Flash leads 51.9 to 37.6.
Side by side
| MiMo-V2.6-Flash | Step 3 | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 48.5 | 40.5 |
| Released | 2026-09-21 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 53.4 (#30), Step 3: 40.1 (#147)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Coding | 1504 | 1367 |
| LMArena WebDev | 1637 | — |
| SciCode | 51.3% | — |
Reasoning MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 36.5 (#66), Step 3: 28.4 (#105)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1482 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 12% | — |
Math MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 51.9 (#52), Step 3: 37.6 (#148)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Math | 1468 | 1366 |
| ProofBench | 63% | — |
Knowledge MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 42.2 (#99), Step 3: 36.8 (#164)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Expert | 1501 | 1333 |
Multimodal MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 40.5 (#47), Step 3: 35.5 (#86)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Vision | 1259 | 1177 |
Multilingual MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 54.0 (#51), Step 3: 46.3 (#159)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Non-English | 1434 | 1327 |
| LMArena Chinese | 1511 | 1397 |
| LMArena Russian | 1409 | 1331 |
| LMArena Spanish | 1456 | 1371 |
| LMArena French | 1475 | — |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
Instruction Following MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 76.8 (#35), Step 3: 70.4 (#164)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1463 | 1332 |
Long Context MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 44.8 (#57), Step 3: 40.3 (#157)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Longer Query | 1463 | 1326 |
Writing & Preference MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 63.1 (#67), Step 3: 54.3 (#151)
| Benchmark | MiMo-V2.6-Flash | Step 3 |
|---|---|---|
| LMArena Text | 1455 | 1350 |
| LMArena Creative Writing | 1400 | 1321 |
| LMArena Multi-Turn | 1451 | 1341 |
Frequently asked questions
Is MiMo-V2.6-Flash better than Step 3?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 40.5 on the Noometry Index.
Is MiMo-V2.6-Flash or Step 3 better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 40.1 in the Noometry coding category.
How many benchmarks do MiMo-V2.6-Flash and Step 3 share?
14 benchmarks have published results for both models. MiMo-V2.6-Flash has 19 scored results on Noometry and Step 3 has 17.