Claude Fable 5.1 vs Muse Spark 1.3
Claude Fable 5.1 
Muse Spark 1.3 Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 63.9.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, reasoning.
- Muse Spark 1.3 (xhigh) is stronger in agents & tools, multimodal.
- Muse Spark 1.3 (xhigh) is 10× cheaper ($2.00 vs $20.00 per 1M blended).
- Muse Spark 1.3 (xhigh) streams 3.3× faster (193 vs 58 tokens per second).
| Metric | Claude Fable 5.1 (xhigh) | Muse Spark 1.3 (xhigh) |
|---|---|---|
| BenchLeader Index | 70.3 | 63.9 |
| Coding score | 71.3 | 70.8 |
| Composite score | 95.0 | 78.6 |
| Knowledge score | 84.1 | 75.0 |
| Long context score | 68.1 | 68.1 |
| Reasoning score | 76.4 | – |
| Agents & tools score | – | 60.4 |
| Multimodal score | – | 66.6 |
| Blended price $/M | $20.00 | $2.00 |
| Output speed | 58 tok/s | 193 tok/s |
| Time to first answer | 132.0 s | 40.0 s |
| Context window | 1M | 1M |
| Humanity's Last Exam | 46.5% | – |
| SciCode | 60.1% | – |
| LMArena WebDev | – | 1625 |
| LiveBench | – | 81.6% |
| LiveBench Reasoning | – | 89.7% |
| LiveBench Coding | – | 81.1% |
| LiveBench Agentic Coding | – | 64.1% |
| LiveBench Mathematics | – | 96.0% |
| LiveBench Data Analysis | – | 79.6% |
| LiveBench Language | – | 82.8% |
| AA Intelligence Index | 53.2 | 45.2 |
| AA-LCR | 83.0% | 83.0% |
| MMMU-Pro | – | 82.0% |
| AA-Omniscience | 42.4 | 23.1 |
| GPQA Diamond (AA) | 93.4% | 94.1% |
| Humanity's Last Exam (AA) | 58.7% | 47.5% |
| SciCode (AA) | 60.9% | 59.7% |
| Terminal-Bench 2.1 (Vals) | – | 72.3% |
| Vals Index | – | 60.3 |
| ARC-AGI-1 | 96.5% | – |
| ARC-AGI-2 | 90.0% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.