Model comparison
Mistral Medium 3.5 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 40.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
MetaSummary
- They share 18 benchmarks with published results for both. Mistral Medium 3.5 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 40.0.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium 3.5 | Muse Spark | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 40.2 | 50.6 |
| Released | — | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 210K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Mistral Medium 3.5: 36.0 (#213), Muse Spark: 46.2 (#69)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Coding | 1461 | 1481 |
| LMArena WebDev | 1264 | — |
| SciCode | — | 51.5% |
Reasoning Muse Spark leads
Mistral Medium 3.5: 17.3 (#295), Muse Spark: 35.9 (#67)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1474 |
| Epoch Capabilities Index | 141.35 | 152.04 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| CritPt | — | 11.3% |
Math Muse Spark leads
Mistral Medium 3.5: 39.1 (#113), Muse Spark: 47.8 (#66)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Math | 1431 | 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
Mistral Medium 3.5: 40.0 (#126), Muse Spark: 65.7 (#13)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Expert | 1432 | 1457 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
Multimodal Muse Spark leads
Mistral Medium 3.5: 38.3 (#65), Muse Spark: 43.4 (#24)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Vision | 1223 | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Mistral Medium 3.5: 51.9 (#100), Muse Spark: 56.1 (#24)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1404 | 1464 |
| LMArena Chinese | 1442 | 1509 |
| LMArena French | 1448 | 1497 |
| LMArena German | 1451 | 1497 |
| LMArena Korean | 1385 | 1459 |
| LMArena Russian | 1395 | 1466 |
| LMArena Spanish | 1409 | 1472 |
Instruction Following Muse Spark leads
Mistral Medium 3.5: 74.6 (#90), Muse Spark: 75.9 (#51)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1415 | 1442 |
Long Context Muse Spark leads
Mistral Medium 3.5: 43.2 (#103), Muse Spark: 44.4 (#69)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1415 | 1451 |
Writing & Preference Muse Spark leads
Mistral Medium 3.5: 58.5 (#117), Muse Spark: 66.0 (#39)
| Benchmark | Mistral Medium 3.5 | Muse Spark |
|---|---|---|
| LMArena Text | 1421 | 1474 |
| LMArena Creative Writing | 1374 | 1459 |
| LMArena Multi-Turn | 1423 | 1477 |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 40.2 on the Noometry Index.
Is Mistral Medium 3.5 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 36.0 in the Noometry coding category.
How many benchmarks do Mistral Medium 3.5 and Muse Spark share?
18 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Muse Spark has 27.