Model comparison
Muse Spark vs Step 3
Muse Spark is the stronger model overall, scoring 50.3 to 39.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
Meta
StepFunSummary
- They share 16 benchmarks with published results for both. Muse Spark scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 36.2.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Muse Spark | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 50.3 | 39.9 |
| Released | 2026-04-08 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 45.6 (#65), Step 3: 39.5 (#144)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Coding | 1482 | 1367 |
| SciCode | 51.5% | — |
Reasoning Muse Spark leads
Muse Spark: 34.9 (#61), Step 3: 27.6 (#102)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1475 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 11.3% | — |
| Epoch Capabilities Index | 152.09 | — |
Math Muse Spark leads
Muse Spark: 46.8 (#57), Step 3: 34.9 (#148)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Math | 1455 | 1366 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#12), Step 3: 36.2 (#161)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Expert | 1458 | 1333 |
| GPQA Diamond | 89.8% | — |
| Humanity's Last Exam | 40.6% | — |
Multimodal Muse Spark leads
Muse Spark: 42.7 (#23), Step 3: 34.9 (#81)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Vision | 1306 | 1176 |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.3 (#23), Step 3: 46.5 (#154)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Non-English | 1464 | 1327 |
| LMArena Chinese | 1507 | 1396 |
| LMArena German | 1497 | 1371 |
| LMArena Korean | 1457 | 1271 |
| LMArena Russian | 1467 | 1331 |
| LMArena Spanish | 1471 | 1372 |
| LMArena French | 1497 | — |
Instruction Following Muse Spark leads
Muse Spark: 76.1 (#47), Step 3: 70.6 (#159)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1443 | 1332 |
Long Context Muse Spark leads
Muse Spark: 44.4 (#65), Step 3: 40.3 (#152)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Longer Query | 1451 | 1326 |
Writing & Preference Muse Spark leads
Muse Spark: 66.2 (#37), Step 3: 54.5 (#146)
| Benchmark | Muse Spark | Step 3 |
|---|---|---|
| LMArena Text | 1474 | 1351 |
| LMArena Creative Writing | 1460 | 1322 |
| LMArena Multi-Turn | 1477 | 1340 |
Frequently asked questions
Is Muse Spark better than Step 3?
Muse Spark is the stronger model overall, scoring 50.3 to 39.9 on the Noometry Index.
Is Muse Spark or Step 3 better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 39.5 in the Noometry coding category.
How many benchmarks do Muse Spark and Step 3 share?
16 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Step 3 has 17.