# Muse Spark vs Yi-34B

> Muse Spark is the stronger model overall, scoring 50.6 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/muse-spark-vs-yi-34b
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 89.8% for Muse Spark and 14.7% for Yi-34B.
- Yi-34B has downloadable open weights; the other is API-only.

## Snapshot

| | Muse Spark | Yi-34B |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 50.6 | 27.8 |
| Rank | 46 | 329 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Muse Spark: 46.2 (#69)
- Yi-34B: 32.3 (#274)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Coding | 1481 | 1112 |
| SciCode | 51.5% | — |

## Reasoning

- Muse Spark: 35.9 (#67)
- Yi-34B: 21.2 (#226)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1474 | 1104 |
| Epoch Capabilities Index | 152.04 | 117.39 |
| CritPt | 11.3% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- Muse Spark: 47.8 (#66)
- Yi-34B: 21.6 (#282)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Math | 1455 | 1114 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| MATH Level 5 | — | 5.1% |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
| GSM8K | — | 76% |

## Knowledge

- Muse Spark: 65.7 (#13)
- Yi-34B: 7.5 (#309)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| GPQA Diamond | 89.8% | 14.7% |
| LMArena Expert | 1457 | 1061 |
| Humanity's Last Exam | 40.6% | — |
| MMLU | — | 76.3% |

## Multimodal

- Muse Spark: 43.4 (#24)
- Yi-34B: —

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |

## Multilingual

- Muse Spark: 56.1 (#24)
- Yi-34B: 29.7 (#264)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Non-English | 1464 | 1079 |
| LMArena Chinese | 1509 | 1176 |
| LMArena French | 1497 | 1081 |
| LMArena German | 1497 | 1042 |
| LMArena Korean | 1459 | 959 |
| LMArena Russian | 1466 | 1050 |
| LMArena Spanish | 1472 | 1070 |
| LMArena Japanese | — | 993 |

## Instruction Following

- Muse Spark: 75.9 (#51)
- Yi-34B: 56.2 (#274)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1442 | 1091 |

## Long Context

- Muse Spark: 44.4 (#69)
- Yi-34B: 33.2 (#264)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1451 | 1094 |

## Writing & Preference

- Muse Spark: 66.0 (#39)
- Yi-34B: 34.1 (#273)

| Benchmark | Muse Spark | Yi-34B |
|---|---|---|
| LMArena Text | 1474 | 1129 |
| LMArena Creative Writing | 1459 | 1108 |
| LMArena Multi-Turn | 1477 | 1113 |

## FAQ

### Is Muse Spark better than Yi-34B?

Muse Spark is the stronger model overall, scoring 50.6 to 27.8 on the Noometry Index.

### Is Muse Spark or Yi-34B better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 32.3 in the Noometry coding category.

### How many benchmarks do Muse Spark and Yi-34B share?

18 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Yi-34B has 23.