# Mistral Medium vs Muse Spark 1.3

> Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-vs-muse-spark-1-3
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Mistral Medium scores higher in 0 categories and Muse Spark 1.3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 28.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 99.2% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 36.3 | 54.8 |
| Rank | 218 | 27 |
| Context | 262K | 1.05M |
| Input $/M | $1.50 | $1.25 |
| Output $/M | $7.50 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- Mistral Medium: 34.2 (#243)
- Muse Spark 1.3: 56.6 (#21)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| SciCode | 40.2% | 59.7% |
| LMArena Coding | 1434 | 1514 |
| FrontierCode | 8% | — |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |

## Agentic & Tool Use

- Mistral Medium: 28.3 (#90)
- Muse Spark 1.3: 38.6 (#30)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 37.7% | — |
| GDP.pdf | — | 27.6% |

## Reasoning

- Mistral Medium: 24.0 (#167)
- Muse Spark 1.3: 54.0 (#27)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| CritPt | 0% | 26% |
| LMArena Hard Prompts | 1426 | 1503 |
| DTBench | 75.5% | 96.5% |
| LMCA | 26.1% | 53.9% |
| Kagi LLM Benchmark | 50% | — |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| Surface Evolver Bench | 26.9% | — |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |

## Math

- Mistral Medium: 28.1 (#245)
- Muse Spark 1.3: 73.1 (#21)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 99.2% |
| ProofBench | 9% | 58% |
| LMArena Math | 1408 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Medium: 25.0 (#265)
- Muse Spark 1.3: 42.6 (#95)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1408 | 1516 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |

## Multimodal

- Mistral Medium: 35.3 (#88)
- Muse Spark 1.3: 43.7 (#22)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1172 | 1309 |
| LMArena Document | — | 1471 |

## Multilingual

- Mistral Medium: 52.1 (#91)
- Muse Spark 1.3: 57.4 (#8)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1408 | 1481 |
| LMArena Chinese | 1447 | 1529 |
| LMArena French | 1459 | 1524 |
| LMArena German | 1432 | 1515 |
| LMArena Japanese | 1378 | 1474 |
| LMArena Korean | 1380 | 1501 |
| LMArena Russian | 1411 | 1490 |
| LMArena Spanish | 1433 | 1490 |

## Instruction Following

- Mistral Medium: 73.7 (#116)
- Muse Spark 1.3: 77.5 (#22)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1477 |

## Long Context

- Mistral Medium: 42.9 (#114)
- Muse Spark 1.3: 45.6 (#32)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1488 |

## Writing & Preference

- Mistral Medium: 60.0 (#103)
- Muse Spark 1.3: 73.6 (#9)

| Benchmark | Mistral Medium | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1424 | 1490 |
| LMArena Creative Writing | 1391 | 1455 |
| LMArena Multi-Turn | 1418 | 1482 |
| Short-Story Creative Writing | 77.3% | — |
| EQ-Bench Creative Writing | — | 1906 |

## FAQ

### Is Mistral Medium better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 36.3 on the Noometry Index.

### Which is cheaper, Mistral Medium or Muse Spark 1.3?

Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Is Mistral Medium or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 34.2 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 262K.

### How many benchmarks do Mistral Medium and Muse Spark 1.3 share?

24 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Muse Spark 1.3 has 37.