# Mixtral 8x22B vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x22b-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 34.1% for Mixtral 8x22B and 89.8% for Muse Spark.
- Mixtral 8x22B has downloadable open weights; the other is API-only.

## Snapshot

| | Mixtral 8x22B | Muse Spark |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 26.7 | 50.3 |
| Rank | 330 | 41 |
| Context | 64K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Open | Proprietary |

## Coding

- Mixtral 8x22B: 23.8 (#324)
- Muse Spark: 45.6 (#65)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Coding | 1166 | 1482 |
| SciCode | — | 51.5% |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |

## Agentic & Tool Use

- Mixtral 8x22B: 22.8 (#119)
- Muse Spark: —

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| Cybench | 7.5% | — |

## Reasoning

- Mixtral 8x22B: 19.1 (#246)
- Muse Spark: 34.9 (#61)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1475 |
| Epoch Capabilities Index | 122 | 152.09 |
| CritPt | — | 11.3% |
| DTBench | 55.1% | — |
| ForecastBench | 56.3 | — |

## Math

- Mixtral 8x22B: 21.2 (#271)
- Muse Spark: 46.8 (#57)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Math | 1184 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Mixtral 8x22B: 15.1 (#288)
- Muse Spark: 65.7 (#12)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| GPQA Diamond | 34.1% | 89.8% |
| LMArena Expert | 1113 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |

## Multimodal

- Mixtral 8x22B: —
- Muse Spark: 42.7 (#23)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- Mixtral 8x22B: 32.9 (#250)
- Muse Spark: 56.3 (#23)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Non-English | 1128 | 1464 |
| LMArena Chinese | 1116 | 1507 |
| LMArena French | 1165 | 1497 |
| LMArena German | 1141 | 1497 |
| LMArena Korean | 1056 | 1457 |
| LMArena Russian | 1158 | 1467 |
| LMArena Spanish | 1150 | 1471 |
| LMArena Japanese | 1037 | — |

## Instruction Following

- Mixtral 8x22B: 57.9 (#261)
- Muse Spark: 76.1 (#47)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1147 | 1443 |
| IFEval | 72.4% | — |

## Long Context

- Mixtral 8x22B: 34.6 (#242)
- Muse Spark: 44.4 (#65)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1144 | 1451 |

## Writing & Preference

- Mixtral 8x22B: 37.1 (#257)
- Muse Spark: 66.2 (#37)

| Benchmark | Mixtral 8x22B | Muse Spark |
|---|---|---|
| LMArena Text | 1162 | 1474 |
| LMArena Creative Writing | 1141 | 1460 |
| LMArena Multi-Turn | 1130 | 1477 |
| WildBench | 71.1% | — |

## FAQ

### Is Mixtral 8x22B better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 26.7 on the Noometry Index.

### Is Mixtral 8x22B or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 23.8 in the Noometry coding category.

### How many benchmarks do Mixtral 8x22B and Muse Spark share?

18 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Muse Spark has 27.