Model comparison
Magistral Medium vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 35.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
MetaSummary
- They share 16 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 8.6.
- The biggest single-benchmark swing is CritPt: 0.3% for Magistral Medium and 17.7% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 35.2 | 50.3 |
| Released | 2025-03-17 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 16K | 131K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $5 | $4.25 |
| Results tracked | 22 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Magistral Medium: 39.1 (#161), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| SciCode | 39.2% | 56.4% |
| LMArena Coding | 1319 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Muse Spark 1.2: 29.4 (#87)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Magistral Medium: 8.6 (#348), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| CritPt | 0.3% | 17.7% |
| LMArena Hard Prompts | 1267 | 1486 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 79.2% |
| ARC-AGI-1 | 6.1% | — |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 154.87 |
Math Muse Spark 1.2 leads
Magistral Medium: 35.1 (#189), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1250 | 1471 |
| ProofBench | — | 43% |
Knowledge Muse Spark 1.2 leads
Magistral Medium: 33.5 (#202), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1223 | 1480 |
| SimpleQA Verified | — | 60.3% |
Multimodal Not comparable
Magistral Medium: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
Magistral Medium: 39.6 (#224), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1232 | 1478 |
| LMArena Chinese | 1227 | 1511 |
| LMArena French | 1267 | 1513 |
| LMArena Russian | 1224 | 1487 |
| LMArena Spanish | 1271 | 1498 |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
Instruction Following Muse Spark 1.2 leads
Magistral Medium: 66.0 (#211), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1461 |
Long Context Muse Spark 1.2 leads
Magistral Medium: 39.3 (#183), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1295 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Magistral Medium: 46.3 (#219), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Magistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1255 | 1482 |
| LMArena Creative Writing | 1245 | 1449 |
| LMArena Multi-Turn | 1275 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
Frequently asked questions
Is Magistral Medium better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 262K.
How many benchmarks do Magistral Medium and Muse Spark 1.2 share?
16 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Muse Spark 1.2 has 31.