Model comparison
Magistral Medium vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 35.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
MetaSummary
- They share 18 benchmarks with published results for both. Magistral Medium 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 33.5.
- The biggest single-benchmark swing is SciCode: 39.2% for Magistral Medium and 51.5% for Muse Spark.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Muse Spark | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 35.2 | 50.6 |
| Released | 2025-03-17 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Magistral Medium: 39.1 (#161), Muse Spark: 46.2 (#69)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| SciCode | 39.2% | 51.5% |
| LMArena Coding | 1319 | 1481 |
Reasoning Muse Spark leads
Magistral Medium: 8.6 (#348), Muse Spark: 35.9 (#67)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| CritPt | 0.3% | 11.3% |
| LMArena Hard Prompts | 1267 | 1474 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| Epoch Capabilities Index | — | 152.04 |
Math Muse Spark leads
Magistral Medium: 35.1 (#189), Muse Spark: 47.8 (#66)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Math | 1250 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Magistral Medium: 33.5 (#202), Muse Spark: 65.7 (#13)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Expert | 1223 | 1457 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
Multimodal Not comparable
Magistral Medium: —, Muse Spark: 43.4 (#24)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Magistral Medium: 39.6 (#224), Muse Spark: 56.1 (#24)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Non-English | 1232 | 1464 |
| LMArena Chinese | 1227 | 1509 |
| LMArena French | 1267 | 1497 |
| LMArena German | 1248 | 1497 |
| LMArena Korean | 1125 | 1459 |
| LMArena Russian | 1224 | 1466 |
| LMArena Spanish | 1271 | 1472 |
| LMArena Japanese | 1175 | — |
Instruction Following Muse Spark leads
Magistral Medium: 66.0 (#211), Muse Spark: 75.9 (#51)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1254 | 1442 |
Long Context Muse Spark leads
Magistral Medium: 39.3 (#183), Muse Spark: 44.4 (#69)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1295 | 1451 |
Writing & Preference Muse Spark leads
Magistral Medium: 46.3 (#219), Muse Spark: 66.0 (#39)
| Benchmark | Magistral Medium | Muse Spark |
|---|---|---|
| LMArena Text | 1255 | 1474 |
| LMArena Creative Writing | 1245 | 1459 |
| LMArena Multi-Turn | 1275 | 1477 |
Frequently asked questions
Is Magistral Medium better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 35.2 on the Noometry Index.
Is Magistral Medium or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 39.1 in the Noometry coding category.
How many benchmarks do Magistral Medium and Muse Spark share?
18 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Muse Spark has 27.