Model comparison
MiMo-V2.6-Flash vs Step 3.7 Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 37.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
StepFunSummary
- They share 2 benchmarks with published results for both. MiMo-V2.6-Flash scores higher in 3 categories and Step 3.7 Flash in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Flash leads 36.5 to 21.6.
- The biggest single-benchmark swing is SciCode: 51.3% for MiMo-V2.6-Flash and 40% for Step 3.7 Flash.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 256K.
Side by side
| MiMo-V2.6-Flash | Step 3.7 Flash | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 48.5 | 37.3 |
| Released | 2026-09-21 | 2026-05-29 |
| Weights | Open | Open |
| Context window | 1.05M | 256K |
| Max output | 131K | 256K |
| Input $ / M tokens | $0.14 | $0.18 |
| Output $ / M tokens | $0.28 | $1.11 |
| Results tracked | 19 | 5 |
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 3.7 Flash: 40.0 (#150)
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| SciCode | 51.3% | 40% |
| LMArena WebDev | 1637 | — |
| LMArena Coding | 1504 | — |
| ALE-Bench | — | 694.12 |
Reasoning MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 36.5 (#66), Step 3.7 Flash: 21.6 (#219)
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| CritPt | 12% | 2.3% |
| NYT Connections (extended) | — | 39.7% |
| LMArena Hard Prompts | 1482 | — |
Math MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 51.9 (#52), Step 3.7 Flash: 42.9 (#82)
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| ProofBench | 63% | — |
| LMArena Math | 1468 | — |
Knowledge Not comparable
MiMo-V2.6-Flash: 42.2 (#99), Step 3.7 Flash: —
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| LMArena Expert | 1501 | — |
Multimodal Not comparable
MiMo-V2.6-Flash: 40.5 (#47), Step 3.7 Flash: —
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Not comparable
MiMo-V2.6-Flash: 54.0 (#51), Step 3.7 Flash: —
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1511 | — |
| LMArena French | 1475 | — |
| LMArena Russian | 1409 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Not comparable
MiMo-V2.6-Flash: 76.8 (#35), Step 3.7 Flash: —
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1463 | — |
Long Context Not comparable
MiMo-V2.6-Flash: 44.8 (#57), Step 3.7 Flash: —
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1463 | — |
Writing & Preference Not comparable
MiMo-V2.6-Flash: 63.1 (#67), Step 3.7 Flash: —
| Benchmark | MiMo-V2.6-Flash | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1455 | — |
| LMArena Creative Writing | 1400 | — |
| LMArena Multi-Turn | 1451 | — |
Frequently asked questions
Is MiMo-V2.6-Flash better than Step 3.7 Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 37.3 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Flash or Step 3.7 Flash?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.
Is MiMo-V2.6-Flash or Step 3.7 Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 256K.
How many benchmarks do MiMo-V2.6-Flash and Step 3.7 Flash share?
2 benchmarks have published results for both models. MiMo-V2.6-Flash has 19 scored results on Noometry and Step 3.7 Flash has 5.