# Mistral Medium vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.6 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-vs-muse-spark
- Last updated: 2026-10-11
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Mistral Medium scores higher in 0 categories and Muse Spark in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 88.9% for Muse Spark.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Medium | Muse Spark |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 36.3 | 50.6 |
| Rank | 218 | 46 |
| Context | 262K | — |
| Input $/M | $1.50 | — |
| Output $/M | $7.50 | — |
| Weights | Open | Proprietary |

## Coding

- Mistral Medium: 34.2 (#243)
- Muse Spark: 46.2 (#69)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| SciCode | 40.2% | 51.5% |
| LMArena Coding | 1434 | 1481 |
| FrontierCode | 8% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |

## Agentic & Tool Use

- Mistral Medium: 28.3 (#90)
- Muse Spark: —

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |

## Reasoning

- Mistral Medium: 24.0 (#167)
- Muse Spark: 35.9 (#67)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| CritPt | 0% | 11.3% |
| LMArena Hard Prompts | 1426 | 1474 |
| Kagi LLM Benchmark | 50% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 152.04 |

## Math

- Mistral Medium: 28.1 (#245)
- Muse Spark: 47.8 (#66)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 88.9% |
| ProofBench | 9% | 17% |
| LMArena Math | 1408 | 1455 |
| FrontierMath (Feb 2025 set) | 0.3% | 39% |
| MATH Level 5 | 81.6% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Mistral Medium: 25.0 (#265)
- Muse Spark: 65.7 (#13)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| GPQA Diamond | 59.5% | 89.8% |
| Humanity's Last Exam | 4.5% | 40.6% |
| LMArena Expert | 1408 | 1457 |
| Vectara Hallucination Rate | 22.7% | — |

## Multimodal

- Mistral Medium: 35.3 (#88)
- Muse Spark: 43.4 (#24)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| LMArena Vision | 1172 | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- Mistral Medium: 52.1 (#91)
- Muse Spark: 56.1 (#24)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| LMArena Non-English | 1408 | 1464 |
| LMArena Chinese | 1447 | 1509 |
| LMArena French | 1459 | 1497 |
| LMArena German | 1432 | 1497 |
| LMArena Korean | 1380 | 1459 |
| LMArena Russian | 1411 | 1466 |
| LMArena Spanish | 1433 | 1472 |
| LMArena Japanese | 1378 | — |

## Instruction Following

- Mistral Medium: 73.7 (#116)
- Muse Spark: 75.9 (#51)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1398 | 1442 |

## Long Context

- Mistral Medium: 42.9 (#114)
- Muse Spark: 44.4 (#69)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1406 | 1451 |

## Writing & Preference

- Mistral Medium: 60.0 (#103)
- Muse Spark: 66.0 (#39)

| Benchmark | Mistral Medium | Muse Spark |
|---|---|---|
| LMArena Text | 1424 | 1474 |
| LMArena Creative Writing | 1391 | 1459 |
| LMArena Multi-Turn | 1418 | 1477 |
| Short-Story Creative Writing | 77.3% | — |

## FAQ

### Is Mistral Medium better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 36.3 on the Noometry Index.

### Is Mistral Medium or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 34.2 in the Noometry coding category.

### How many benchmarks do Mistral Medium and Muse Spark share?

24 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Muse Spark has 27.