# Mercury 2 vs MiMo-V2.6-Flash

> MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 39.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-mimo-v2-6-flash
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and MiMo-V2.6-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Flash leads 53.4 to 33.5.
- The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 51.3% for MiMo-V2.6-Flash.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 128K.
- MiMo-V2.6-Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| Provider | Inception | Xiaomi |
| Noometry Index | 39.1 | 48.5 |
| Rank | 175 | 55 |
| Context | 128K | 1.05M |
| Input $/M | $0.25 | $0.14 |
| Output $/M | $0.75 | $0.28 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.5 (#255)
- MiMo-V2.6-Flash: 53.4 (#30)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena WebDev | 1171 | 1637 |
| SciCode | 38.7% | 51.3% |
| LMArena Coding | 1391 | 1504 |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Reasoning

- Mercury 2: 23.8 (#170)
- MiMo-V2.6-Flash: 36.5 (#66)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| CritPt | 0.8% | 12% |
| LMArena Hard Prompts | 1362 | 1482 |

## Math

- Mercury 2: —
- MiMo-V2.6-Flash: 51.9 (#52)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| ProofBench | — | 63% |
| LMArena Math | — | 1468 |

## Knowledge

- Mercury 2: 36.2 (#172)
- MiMo-V2.6-Flash: 42.2 (#99)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1358 | 1501 |
| Vectara Hallucination Rate | 12.3% | — |

## Multimodal

- Mercury 2: —
- MiMo-V2.6-Flash: 40.5 (#47)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | — | 1259 |

## Multilingual

- Mercury 2: 46.6 (#157)
- MiMo-V2.6-Flash: 54.0 (#51)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1331 | 1434 |
| LMArena Chinese | 1417 | 1511 |
| LMArena Russian | 1304 | 1409 |
| LMArena French | — | 1475 |
| LMArena Spanish | — | 1456 |

## Instruction Following

- Mercury 2: 70.2 (#165)
- MiMo-V2.6-Flash: 76.8 (#35)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1329 | 1463 |

## Long Context

- Mercury 2: 40.5 (#154)
- MiMo-V2.6-Flash: 44.8 (#57)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1330 | 1463 |

## Writing & Preference

- Mercury 2: 53.8 (#155)
- MiMo-V2.6-Flash: 63.1 (#67)

| Benchmark | Mercury 2 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1355 | 1455 |
| LMArena Creative Writing | 1289 | 1400 |
| LMArena Multi-Turn | 1358 | 1451 |

## FAQ

### Is Mercury 2 better than MiMo-V2.6-Flash?

MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 39.1 on the Noometry Index.

### Which is cheaper, Mercury 2 or MiMo-V2.6-Flash?

MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Is Mercury 2 or MiMo-V2.6-Flash better for coding?

MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Flash does, with 1.05M tokens against 128K.

### How many benchmarks do Mercury 2 and MiMo-V2.6-Flash share?

14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and MiMo-V2.6-Flash has 19.