Model comparison
Muse Spark 1.1 vs Step 3
Muse Spark 1.1 is the stronger model overall, scoring 49.9 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 1.1 scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Spark 1.1 leads 73.6 to 54.5.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.1 | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 49.9 | 39.9 |
| Released | 2026-04-08 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $4.25 | — |
| Results tracked | 36 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Muse Spark 1.1: 50.8 (#38), Step 3: 39.5 (#144)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Coding | 1497 | 1367 |
| DeepSWE | 53.3% | — |
| LMArena WebDev | 1542 | — |
| SciCode | 58.8% | — |
Agentic & Tool Use Not comparable
Muse Spark 1.1: 33.9 (#45), Step 3: —
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| τ²-bench Banking | 40.5% | — |
| GBAEval | 7.9% | — |
| GDP.pdf | 15% | — |
| Vending-Bench 2 | 6,520 | — |
Reasoning Muse Spark 1.1 leads
Muse Spark 1.1: 45.9 (#41), Step 3: 27.6 (#102)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1486 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 84.9% | — |
| CritPt | 15.1% | — |
| DTBench | 94.4% | — |
| LMCA | 49.9% | — |
| Surface Evolver Bench | 52.5% | — |
| Epoch Capabilities Index | 154.32 | — |
Math Muse Spark 1.1 leads
Muse Spark 1.1: 44.0 (#67), Step 3: 34.9 (#148)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Math | 1477 | 1366 |
| ProofBench | 39% | — |
Knowledge Muse Spark 1.1 leads
Muse Spark 1.1: 52.8 (#55), Step 3: 36.2 (#161)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Expert | 1480 | 1333 |
| SimpleQA Verified | 57.8% | — |
Multimodal Muse Spark 1.1 leads
Muse Spark 1.1: 41.9 (#28), Step 3: 34.9 (#81)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Vision | 1292 | 1176 |
| LMArena Document | 1465 | — |
Multilingual Muse Spark 1.1 leads
Muse Spark 1.1: 56.8 (#16), Step 3: 46.5 (#154)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1471 | 1327 |
| LMArena Chinese | 1518 | 1396 |
| LMArena German | 1466 | 1371 |
| LMArena Korean | 1459 | 1271 |
| LMArena Russian | 1482 | 1331 |
| LMArena Spanish | 1471 | 1372 |
| LMArena French | 1494 | — |
| LMArena Japanese | 1445 | — |
Instruction Following Muse Spark 1.1 leads
Muse Spark 1.1: 76.8 (#36), Step 3: 70.6 (#159)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1457 | 1332 |
Long Context Muse Spark 1.1 leads
Muse Spark 1.1: 44.8 (#55), Step 3: 40.3 (#152)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1463 | 1326 |
Writing & Preference Muse Spark 1.1 leads
Muse Spark 1.1: 73.6 (#11), Step 3: 54.5 (#146)
| Benchmark | Muse Spark 1.1 | Step 3 |
|---|---|---|
| LMArena Text | 1479 | 1351 |
| LMArena Creative Writing | 1440 | 1322 |
| LMArena Multi-Turn | 1484 | 1340 |
| EQ-Bench Creative Writing | 1927 | — |
| EQ-Bench 4 | 1260 | — |
Frequently asked questions
Is Muse Spark 1.1 better than Step 3?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 39.9 on the Noometry Index.
Is Muse Spark 1.1 or Step 3 better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 50.8 versus 39.5 in the Noometry coding category.
How many benchmarks do Muse Spark 1.1 and Step 3 share?
16 benchmarks have published results for both models. Muse Spark 1.1 has 36 scored results on Noometry and Step 3 has 17.