# Muse Spark 1.2 vs Step 5 Preview

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 47.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/muse-spark-1-2-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Muse Spark 1.2 scores higher in 8 categories and Step 5 Preview in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark 1.2 leads 54.1 to 41.2.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 1.02M.

## Snapshot

| | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 50.3 | 47.9 |
| Rank | 48 | 58 |
| Context | 1.05M | 1.02M |
| Input $/M | $1.25 | $1 |
| Output $/M | $4.25 | $2.70 |
| Weights | Proprietary | Proprietary |

## Coding

- Muse Spark 1.2: 49.2 (#51)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1533 | 1564 |
| SciCode | 56.4% | 58.9% |
| LMArena Coding | 1495 | 1480 |
| DeepSWE | 54.9% | — |
| FrontierSWE | 12% | — |
| WeirdML | 60.3% | — |

## Agentic & Tool Use

- Muse Spark 1.2: 29.4 (#87)
- Step 5 Preview: —

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |

## Reasoning

- Muse Spark 1.2: 51.3 (#34)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| CritPt | 17.7% | 20.9% |
| LMArena Hard Prompts | 1486 | 1465 |
| SimpleBench | 74.5% | — |
| NYT Connections (extended) | 79.2% | — |
| DTBench | 94.7% | — |
| LMCA | 48.4% | — |
| Epoch Capabilities Index | 154.87 | — |

## Math

- Muse Spark 1.2: 46.4 (#70)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| ProofBench | 43% | 42% |
| LMArena Math | 1471 | 1470 |

## Knowledge

- Muse Spark 1.2: 54.1 (#53)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1480 | 1470 |
| SimpleQA Verified | 60.3% | — |

## Multimodal

- Muse Spark 1.2: 43.4 (#25)
- Step 5 Preview: 41.0 (#41)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1305 | 1267 |

## Multilingual

- Muse Spark 1.2: 57.1 (#11)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1478 | 1432 |
| LMArena Chinese | 1511 | 1519 |
| LMArena Russian | 1487 | 1436 |
| LMArena Spanish | 1498 | 1439 |
| LMArena French | 1513 | — |

## Instruction Following

- Muse Spark 1.2: 76.7 (#36)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1461 | 1444 |

## Long Context

- Muse Spark 1.2: 45.2 (#48)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1475 | 1455 |

## Writing & Preference

- Muse Spark 1.2: 72.3 (#14)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Muse Spark 1.2 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1482 | 1442 |
| LMArena Creative Writing | 1449 | 1410 |
| LMArena Multi-Turn | 1494 | 1447 |
| EQ-Bench Creative Writing | 1840 | — |

## FAQ

### Is Muse Spark 1.2 better than Step 5 Preview?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 47.9 on the Noometry Index.

### Which is cheaper, Muse Spark 1.2 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 1.2 lists at $1.25 and $4.25.

### Is Muse Spark 1.2 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 49.2 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 1.02M.

### How many benchmarks do Muse Spark 1.2 and Step 5 Preview share?

18 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Step 5 Preview has 18.
