Muse Spark vs Step 5 Preview
Muse Spark 
Step 5 Preview Verdict
- Muse Spark and Step 5 Preview are level on quality (65.7 vs 65.0).
- Muse Spark is stronger in agents & tools, coding, human preference, instruction following, maths, multimodal.
- Step 5 Preview is stronger in composite, knowledge, long context, reasoning.
| Metric | Muse Spark | Step 5 Preview |
|---|---|---|
| BenchLeader Index | 65.7 | 65.0 |
| Agents & tools score | 66.0 | – |
| Coding score | 66.1 | – |
| Composite score | 68.7 | 84.4 |
| Human preference score | 69.2 | – |
| Instruction following score | 79.8 | – |
| Knowledge score | 64.2 | 72.0 |
| Long context score | 65.4 | 70.8 |
| Maths score | 59.9 | – |
| Multimodal score | 65.7 | 60.8 |
| Reasoning score | 68.3 | 82.1 |
| Blended price $/M | – | $1.43 |
| Context window | 262k | 1M |
| GPQA Diamond | 89.8% | – |
| OTIS Mock AIME | 88.9% | – |
| Humanity's Last Exam | 40.6% | – |
| SciCode | 51.5% | – |
| ProofBench | 17.0% | – |
| Epoch Capabilities Index | 152.1 | – |
| LMArena Text | 1488 | – |
| LMArena Hard Prompts | 1505 | – |
| LMArena Coding | 1526 | – |
| LMArena Vision | 1306 | – |
| AA Intelligence Index | 31.3 | 43.6 |
| IFBench | 75.9% | – |
| AA-LCR | 78.0% | 88.3% |
| MMMU-Pro | 80.5% | 76.4% |
| AA-Omniscience | 7.2 | 16.4 |
| Terminal-Bench Hard | 45.5% | – |
| GPQA Diamond (AA) | 88.4% | – |
| Humanity's Last Exam (AA) | 40.7% | 46.5% |
| SciCode (AA) | – | 58.9% |
| τ²-Bench Telecom (AA) | 91.5% | – |
| AIME (Vals) | 96.9% | – |
| MMLU-Pro | 87.3% | – |
| LegalBench | 84.2% | – |
| CorpFin | 65.1% | – |
| TaxEval | 77.7% | – |
| SWE-bench (Vals) | 74.4% | – |
| GPQA Diamond (Vals) | 89.7% | – |
| SWE-Bench Pro | 55.0% | – |
| MCP Atlas | 82.2% | – |
| MultiChallenge | 75.5% | – |
| PRBench Finance | 52.4% | – |
| PRBench Legal | 52.3% | – |
| MultiNRC | 59.0% | – |
| TutorBench | 68.5% | – |
| CritPt | 11.3% | 20.9% |
| GDPval (AA) | 28.8% | 53.6% |
| CaseLaw v2 | 63.1% | – |
| MedCode | 51.3% | – |
| MedScribe | 85.9% | – |
| MMMU-Pro (Vals) | 87.4% | – |
| Terminal-Bench 2.0 (Vals) | 59.5% | – |
| Vibe Code Bench v1.1 | 19.7% | – |
| FORTRESS | 20.2% | – |
| SWE-Bench Pro (private) | 44.7% | – |
| SWE Atlas: Codebase QnA | 24.2% | – |
| SWE Atlas: Test Writing | 31.1% | – |
| LMArena Maths | 1461 | – |
| LMArena Creative Writing | 1464 | – |
| LMArena Instruction Following | 1463 | – |
| LMArena Multi-turn | 1491 | – |
| LMArena Longer Queries | 1474 | – |
| LMArena Document | 1467 | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Muse Spark vs Step 5 Preview: questions
- Is Muse Spark better than Step 5 Preview?
- Muse Spark and Step 5 Preview are level on quality (65.7 vs 65.0). The BenchLeader Index combines every independent quality benchmark; Muse Spark is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which has the larger context window?
- Step 5 Preview accepts more context: 1M against 262k tokens.