# Muse Spark vs Yi-Lightning

> Muse Spark is the stronger model overall, scoring 50.3 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/muse-spark-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 34.8.

## Snapshot

| | Muse Spark | Yi-Lightning |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 50.3 | 36.5 |
| Rank | 41 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Muse Spark: 45.6 (#65)
- Yi-Lightning: 27.0 (#315)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1482 | 1313 |
| Aider Polyglot | — | 12.9% |
| SciCode | 51.5% | — |

## Reasoning

- Muse Spark: 34.9 (#61)
- Yi-Lightning: 24.9 (#137)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1475 | 1302 |
| CritPt | 11.3% | — |
| Epoch Capabilities Index | 152.09 | — |

## Math

- Muse Spark: 46.8 (#57)
- Yi-Lightning: 33.5 (#173)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Math | 1455 | 1300 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Muse Spark: 65.7 (#12)
- Yi-Lightning: 34.8 (#182)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1458 | 1286 |
| GPQA Diamond | 89.8% | — |
| Humanity's Last Exam | 40.6% | — |

## Multimodal

- Muse Spark: 42.7 (#23)
- Yi-Lightning: —

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |

## Multilingual

- Muse Spark: 56.3 (#23)
- Yi-Lightning: 42.4 (#191)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1464 | 1269 |
| LMArena Chinese | 1507 | 1320 |
| LMArena French | 1497 | 1304 |
| LMArena German | 1497 | 1267 |
| LMArena Korean | 1457 | 1192 |
| LMArena Russian | 1467 | 1255 |
| LMArena Spanish | 1471 | 1315 |
| LMArena Japanese | — | 1228 |

## Instruction Following

- Muse Spark: 76.1 (#47)
- Yi-Lightning: 67.6 (#191)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1443 | 1278 |

## Long Context

- Muse Spark: 44.4 (#65)
- Yi-Lightning: 39.4 (#176)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1451 | 1297 |

## Writing & Preference

- Muse Spark: 66.2 (#37)
- Yi-Lightning: 50.4 (#178)

| Benchmark | Muse Spark | Yi-Lightning |
|---|---|---|
| LMArena Text | 1474 | 1302 |
| LMArena Creative Writing | 1460 | 1280 |
| LMArena Multi-Turn | 1477 | 1311 |

## FAQ

### Is Muse Spark better than Yi-Lightning?

Muse Spark is the stronger model overall, scoring 50.3 to 36.5 on the Noometry Index.

### Is Muse Spark or Yi-Lightning better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 27.0 in the Noometry coding category.

### How many benchmarks do Muse Spark and Yi-Lightning share?

16 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Yi-Lightning has 18.