Model comparison
Muse Spark 1.2 vs Step 3
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 40.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
StepFunSummary
- They share 14 benchmarks with published results for both. Muse Spark 1.2 scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 28.4.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.2 | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 50.3 | 40.5 |
| Released | 2026-08-05 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $4.25 | — |
| Results tracked | 31 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Muse Spark 1.2: 49.2 (#51), Step 3: 40.1 (#147)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Coding | 1495 | 1367 |
| DeepSWE | 54.9% | — |
| LMArena WebDev | 1533 | — |
| FrontierSWE | 12% | — |
| SciCode | 56.4% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Not comparable
Muse Spark 1.2: 29.4 (#87), Step 3: —
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |
Reasoning Muse Spark 1.2 leads
Muse Spark 1.2: 51.3 (#34), Step 3: 28.4 (#105)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1486 | 1355 |
| SimpleBench | 74.5% | — |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 79.2% | — |
| CritPt | 17.7% | — |
| DTBench | 94.7% | — |
| LMCA | 48.4% | — |
| Epoch Capabilities Index | 154.87 | — |
Math Muse Spark 1.2 leads
Muse Spark 1.2: 46.4 (#70), Step 3: 37.6 (#148)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Math | 1471 | 1366 |
| ProofBench | 43% | — |
Knowledge Muse Spark 1.2 leads
Muse Spark 1.2: 54.1 (#53), Step 3: 36.8 (#164)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Expert | 1480 | 1333 |
| SimpleQA Verified | 60.3% | — |
Multimodal Muse Spark 1.2 leads
Muse Spark 1.2: 43.4 (#25), Step 3: 35.5 (#86)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Vision | 1305 | 1177 |
Multilingual Muse Spark 1.2 leads
Muse Spark 1.2: 57.1 (#11), Step 3: 46.3 (#159)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Non-English | 1478 | 1327 |
| LMArena Chinese | 1511 | 1397 |
| LMArena Russian | 1487 | 1331 |
| LMArena Spanish | 1498 | 1371 |
| LMArena French | 1513 | — |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
Instruction Following Muse Spark 1.2 leads
Muse Spark 1.2: 76.7 (#36), Step 3: 70.4 (#164)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1461 | 1332 |
Long Context Muse Spark 1.2 leads
Muse Spark 1.2: 45.2 (#48), Step 3: 40.3 (#157)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1475 | 1326 |
Writing & Preference Muse Spark 1.2 leads
Muse Spark 1.2: 72.3 (#14), Step 3: 54.3 (#151)
| Benchmark | Muse Spark 1.2 | Step 3 |
|---|---|---|
| LMArena Text | 1482 | 1350 |
| LMArena Creative Writing | 1449 | 1321 |
| LMArena Multi-Turn | 1494 | 1341 |
| EQ-Bench Creative Writing | 1840 | — |
Frequently asked questions
Is Muse Spark 1.2 better than Step 3?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 40.5 on the Noometry Index.
Is Muse Spark 1.2 or Step 3 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 40.1 in the Noometry coding category.
How many benchmarks do Muse Spark 1.2 and Step 3 share?
14 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Step 3 has 17.