Model comparison
Muse Spark 1.3 vs Step 5 Preview
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 47.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
StepFunSummary
- They share 18 benchmarks with published results for both. Muse Spark 1.3 scores higher in 9 categories and Step 5 Preview in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 46.1.
- The biggest single-benchmark swing is ProofBench: 58% for Muse Spark 1.3 and 42% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 1.02M.
Side by side
| Muse Spark 1.3 | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 54.8 | 47.9 |
| Released | 2026-09-02 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.25 | $1 |
| Output $ / M tokens | $4.25 | $2.70 |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Muse Spark 1.3: 56.6 (#21), Step 5 Preview: 51.8 (#36)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1657 | 1564 |
| SciCode | 59.7% | 58.9% |
| LMArena Coding | 1514 | 1480 |
| CursorBench | 41.6% | — |
Agentic & Tool Use Not comparable
Muse Spark 1.3: 38.6 (#30), Step 5 Preview: —
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| APEX-Agents | 57.8% | — |
| GDP.pdf | 27.6% | — |
Reasoning Muse Spark 1.3 leads
Muse Spark 1.3: 54.0 (#27), Step 5 Preview: 40.0 (#57)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| CritPt | 26% | 20.9% |
| LMArena Hard Prompts | 1503 | 1465 |
| NYT Connections (extended) | 85.1% | — |
| Chess Puzzles | 38% | — |
| Mystery Game Puzzles | 25% | — |
| DTBench | 96.5% | — |
| LMCA | 53.9% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.75 | — |
Math Muse Spark 1.3 leads
Muse Spark 1.3: 73.1 (#21), Step 5 Preview: 46.1 (#72)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| ProofBench | 58% | 42% |
| LMArena Math | 1494 | 1470 |
| FrontierMath (Tiers 1-3) | 74.4% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
Knowledge Muse Spark 1.3 leads
Muse Spark 1.3: 42.6 (#95), Step 5 Preview: 41.2 (#112)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1516 | 1470 |
Multimodal Muse Spark 1.3 leads
Muse Spark 1.3: 43.7 (#22), Step 5 Preview: 41.0 (#41)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1309 | 1267 |
| LMArena Document | 1471 | — |
Multilingual Muse Spark 1.3 leads
Muse Spark 1.3: 57.4 (#8), Step 5 Preview: 53.8 (#54)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1481 | 1432 |
| LMArena Chinese | 1529 | 1519 |
| LMArena Russian | 1490 | 1436 |
| LMArena Spanish | 1490 | 1439 |
| LMArena French | 1524 | — |
| LMArena German | 1515 | — |
| LMArena Japanese | 1474 | — |
| LMArena Korean | 1501 | — |
Instruction Following Muse Spark 1.3 leads
Muse Spark 1.3: 77.5 (#22), Step 5 Preview: 76.0 (#50)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1477 | 1444 |
Long Context Muse Spark 1.3 leads
Muse Spark 1.3: 45.6 (#32), Step 5 Preview: 44.5 (#64)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1488 | 1455 |
Writing & Preference Muse Spark 1.3 leads
Muse Spark 1.3: 73.6 (#9), Step 5 Preview: 62.8 (#71)
| Benchmark | Muse Spark 1.3 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1490 | 1442 |
| LMArena Creative Writing | 1455 | 1410 |
| LMArena Multi-Turn | 1482 | 1447 |
| EQ-Bench Creative Writing | 1906 | — |
Frequently asked questions
Is Muse Spark 1.3 better than Step 5 Preview?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 47.9 on the Noometry Index.
Which is cheaper, Muse Spark 1.3 or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Muse Spark 1.3 or Step 5 Preview better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 51.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 1.02M.
How many benchmarks do Muse Spark 1.3 and Step 5 Preview share?
18 benchmarks have published results for both models. Muse Spark 1.3 has 37 scored results on Noometry and Step 5 Preview has 18.