Model comparison
Mistral Small 3 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 31.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
MetaSummary
- They share 18 benchmarks with published results for both. Mistral Small 3 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 25.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 88.9% for Muse Spark.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Muse Spark | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 31.2 | 50.6 |
| Released | 2025-01-30 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Mistral Small 3: 36.5 (#207), Muse Spark: 46.2 (#69)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Coding | 1246 | 1481 |
| SciCode | — | 51.5% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Muse Spark leads
Mistral Small 3: 18.9 (#273), Muse Spark: 35.9 (#67)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1474 |
| Epoch Capabilities Index | 127.07 | 152.04 |
| CritPt | — | 11.3% |
| Chess Puzzles | 0% | — |
Math Muse Spark leads
Mistral Small 3: 16.3 (#295), Muse Spark: 47.8 (#66)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 88.9% |
| LMArena Math | 1240 | 1455 |
| ProofBench | — | 17% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Mistral Small 3: 25.1 (#263), Muse Spark: 65.7 (#13)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| GPQA Diamond | 47.3% | 89.8% |
| LMArena Expert | 1202 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| Confabulations | 25.2% | — |
Multimodal Not comparable
Mistral Small 3: —, Muse Spark: 43.4 (#24)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Mistral Small 3: 37.3 (#236), Muse Spark: 56.1 (#24)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1198 | 1464 |
| LMArena Chinese | 1204 | 1509 |
| LMArena French | 1203 | 1497 |
| LMArena German | 1211 | 1497 |
| LMArena Korean | 1188 | 1459 |
| LMArena Russian | 1216 | 1466 |
| LMArena Japanese | 1111 | — |
| LMArena Spanish | — | 1472 |
Instruction Following Muse Spark leads
Mistral Small 3: 63.7 (#229), Muse Spark: 75.9 (#51)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1214 | 1442 |
Long Context Muse Spark leads
Mistral Small 3: 37.8 (#211), Muse Spark: 44.4 (#69)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1246 | 1451 |
Writing & Preference Muse Spark leads
Mistral Small 3: 32.2 (#280), Muse Spark: 66.0 (#39)
| Benchmark | Mistral Small 3 | Muse Spark |
|---|---|---|
| LMArena Text | 1234 | 1474 |
| LMArena Creative Writing | 1195 | 1459 |
| LMArena Multi-Turn | 1217 | 1477 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 31.2 on the Noometry Index.
Is Mistral Small 3 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 36.5 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Muse Spark share?
18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Muse Spark has 27.