# MiMo-V2.5 vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 43.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. MiMo-V2.5 scores higher in 0 categories and Muse Spark in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 40.2.
- The biggest single-benchmark swing is SciCode: 43.1% for MiMo-V2.5 and 51.5% for Muse Spark.
- MiMo-V2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2.5 | Muse Spark |
|---|---|---|
| Provider | Xiaomi | Meta |
| Noometry Index | 43.0 | 50.3 |
| Rank | 89 | 41 |
| Context | 1.05M | — |
| Input $/M | $0.14 | — |
| Output $/M | $0.28 | — |
| Weights | Open | Proprietary |

## Coding

- MiMo-V2.5: 43.6 (#75)
- Muse Spark: 45.6 (#65)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| SciCode | 43.1% | 51.5% |
| LMArena Coding | 1469 | 1482 |
| LMArena WebDev | 1438 | — |
| ALE-Bench | 513.95 | — |

## Reasoning

- MiMo-V2.5: 27.8 (#98)
- Muse Spark: 34.9 (#61)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| CritPt | 3.7% | 11.3% |
| LMArena Hard Prompts | 1450 | 1475 |
| Epoch Capabilities Index | — | 152.09 |

## Math

- MiMo-V2.5: 35.4 (#145)
- Muse Spark: 46.8 (#57)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| ProofBench | 16% | 17% |
| LMArena Math | 1436 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- MiMo-V2.5: 40.2 (#109)
- Muse Spark: 65.7 (#12)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| LMArena Expert | 1459 | 1458 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |

## Multimodal

- MiMo-V2.5: 39.0 (#53)
- Muse Spark: 42.7 (#23)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| LMArena Vision | 1245 | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- MiMo-V2.5: 52.0 (#96)
- Muse Spark: 56.3 (#23)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1404 | 1464 |
| LMArena Chinese | 1467 | 1507 |
| LMArena French | 1447 | 1497 |
| LMArena German | 1421 | 1497 |
| LMArena Korean | 1363 | 1457 |
| LMArena Russian | 1395 | 1467 |
| LMArena Spanish | 1412 | 1471 |
| LMArena Japanese | 1304 | — |

## Instruction Following

- MiMo-V2.5: 75.7 (#55)
- Muse Spark: 76.1 (#47)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1433 | 1443 |

## Long Context

- MiMo-V2.5: 44.1 (#69)
- Muse Spark: 44.4 (#65)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1444 | 1451 |

## Writing & Preference

- MiMo-V2.5: 61.8 (#82)
- Muse Spark: 66.2 (#37)

| Benchmark | MiMo-V2.5 | Muse Spark |
|---|---|---|
| LMArena Text | 1427 | 1474 |
| LMArena Creative Writing | 1392 | 1460 |
| LMArena Multi-Turn | 1445 | 1477 |

## FAQ

### Is MiMo-V2.5 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 43.0 on the Noometry Index.

### Is MiMo-V2.5 or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 43.6 in the Noometry coding category.

### How many benchmarks do MiMo-V2.5 and Muse Spark share?

20 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Muse Spark has 27.