# MiMo-V2.6-Flash vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 48.5 on the Noometry Index. MiMo-V2.6-Flash costs 3.1× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mimo-v2-6-flash-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiMo-V2.6-Flash scores higher in 0 categories and MiMo-V2.6-Pro in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 36.5.
- The biggest single-benchmark swing is CritPt: 12% for MiMo-V2.6-Flash and 26.6% for MiMo-V2.6-Pro.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.

## Snapshot

| | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| Provider | Xiaomi | Xiaomi |
| Noometry Index | 48.5 | 50.3 |
| Rank | 55 | 49 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.14 | $0.43 |
| Output $/M | $0.28 | $0.87 |
| Weights | Open | Open |

## Coding

- MiMo-V2.6-Flash: 53.4 (#30)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1637 | 1629 |
| SciCode | 51.3% | 60.9% |
| LMArena Coding | 1504 | 1534 |
| ALE-Bench | — | 1,158 |

## Agentic & Tool Use

- MiMo-V2.6-Flash: —
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |

## Reasoning

- MiMo-V2.6-Flash: 36.5 (#66)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 12% | 26.6% |
| LMArena Hard Prompts | 1482 | 1512 |

## Math

- MiMo-V2.6-Flash: 51.9 (#52)
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 63% | 70% |
| LMArena Math | 1468 | 1494 |

## Knowledge

- MiMo-V2.6-Flash: 42.2 (#99)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1501 | 1543 |

## Multimodal

- MiMo-V2.6-Flash: 40.5 (#47)
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1259 | 1264 |

## Multilingual

- MiMo-V2.6-Flash: 54.0 (#51)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1434 | 1474 |
| LMArena Chinese | 1511 | 1529 |
| LMArena Russian | 1409 | 1480 |
| LMArena French | 1475 | — |
| LMArena Spanish | 1456 | — |

## Instruction Following

- MiMo-V2.6-Flash: 76.8 (#35)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1463 | 1493 |

## Long Context

- MiMo-V2.6-Flash: 44.8 (#57)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1463 | 1501 |

## Writing & Preference

- MiMo-V2.6-Flash: 63.1 (#67)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | MiMo-V2.6-Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1455 | 1492 |
| LMArena Creative Writing | 1400 | 1468 |
| LMArena Multi-Turn | 1451 | 1464 |

## FAQ

### Is MiMo-V2.6-Flash better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 48.5 on the Noometry Index. MiMo-V2.6-Flash costs 3.1× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

### Which is cheaper, MiMo-V2.6-Flash or MiMo-V2.6-Pro?

MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

### Is MiMo-V2.6-Flash or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 53.4 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1.05M tokens.

### How many benchmarks do MiMo-V2.6-Flash and MiMo-V2.6-Pro share?

17 benchmarks have published results for both models. MiMo-V2.6-Flash has 19 scored results on Noometry and MiMo-V2.6-Pro has 19.