# MiMo-V2.5 vs Step 3.5 Flash

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 41.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiMo-V2.5 scores higher in 7 categories and Step 3.5 Flash in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 27.8 to 21.2.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 256K.

## Snapshot

| | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 43.0 | 41.7 |
| Rank | 89 | 116 |
| Context | 1.05M | 256K |
| Input $/M | $0.14 | $0.10 |
| Output $/M | $0.28 | $0.30 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.6 (#75)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1469 | 1436 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| ALE-Bench | 513.95 | — |

## Reasoning

- MiMo-V2.5: 27.8 (#98)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 3.7% | — |

## Math

- MiMo-V2.5: 35.4 (#145)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1436 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| ProofBench | 16% | — |

## Knowledge

- MiMo-V2.5: 40.2 (#109)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1459 | 1422 |

## Multimodal

- MiMo-V2.5: 39.0 (#53)
- Step 3.5 Flash: —

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- MiMo-V2.5: 52.0 (#96)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1404 | 1386 |
| LMArena Chinese | 1467 | 1448 |
| LMArena French | 1447 | 1421 |
| LMArena German | 1421 | 1404 |
| LMArena Japanese | 1304 | 1353 |
| LMArena Korean | 1363 | 1350 |
| LMArena Russian | 1395 | 1385 |
| LMArena Spanish | 1412 | 1419 |

## Instruction Following

- MiMo-V2.5: 75.7 (#55)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1433 | 1385 |

## Long Context

- MiMo-V2.5: 44.1 (#69)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1444 | 1402 |

## Writing & Preference

- MiMo-V2.5: 61.8 (#82)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | MiMo-V2.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1427 | 1403 |
| LMArena Creative Writing | 1392 | 1357 |
| LMArena Multi-Turn | 1445 | 1405 |

## FAQ

### Is MiMo-V2.5 better than Step 3.5 Flash?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 41.7 on the Noometry Index.

### Which is cheaper, MiMo-V2.5 or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.

### Is MiMo-V2.5 or Step 3.5 Flash better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 41.7 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 256K.

### How many benchmarks do MiMo-V2.5 and Step 3.5 Flash share?

17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Step 3.5 Flash has 19.