# Mercury 2 vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 39.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mercury-2-vs-mimo-v2-6-pro
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and MiMo-V2.6-Pro in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 33.5.
- The biggest single-benchmark swing is CritPt: 0.8% for Mercury 2 and 26.6% for MiMo-V2.6-Pro.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| Provider | Inception | Xiaomi |
| Noometry Index | 39.1 | 50.3 |
| Rank | 175 | 49 |
| Context | 128K | 1.05M |
| Input $/M | $0.25 | $0.43 |
| Output $/M | $0.75 | $0.87 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.5 (#255)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1171 | 1629 |
| SciCode | 38.7% | 60.9% |
| LMArena Coding | 1391 | 1534 |
| ALE-Bench | 785.58 | 1,158 |
| WeirdML | 43.2% | — |

## Agentic & Tool Use

- Mercury 2: —
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |

## Reasoning

- Mercury 2: 23.8 (#170)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 0.8% | 26.6% |
| LMArena Hard Prompts | 1362 | 1512 |

## Math

- Mercury 2: —
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | — | 70% |
| LMArena Math | — | 1494 |

## Knowledge

- Mercury 2: 36.2 (#172)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1358 | 1543 |
| Vectara Hallucination Rate | 12.3% | — |

## Multimodal

- Mercury 2: —
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |

## Multilingual

- Mercury 2: 46.6 (#157)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1331 | 1474 |
| LMArena Chinese | 1417 | 1529 |
| LMArena Russian | 1304 | 1480 |

## Instruction Following

- Mercury 2: 70.2 (#165)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1329 | 1493 |

## Long Context

- Mercury 2: 40.5 (#154)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1330 | 1501 |

## Writing & Preference

- Mercury 2: 53.8 (#155)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1355 | 1492 |
| LMArena Creative Writing | 1289 | 1468 |
| LMArena Multi-Turn | 1358 | 1464 |

## FAQ

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

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 39.1 on the Noometry Index.

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

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

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

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

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

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

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