Claude Fable 5.1 vs Muse Spark 1.2
Claude Fable 5.1 
Muse Spark 1.2 Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 62.6.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, long context, reasoning.
- Muse Spark 1.2 is stronger in maths.
- Muse Spark 1.2 is 10× cheaper ($2.00 vs $20.00 per 1M blended).
- Muse Spark 1.2 streams 3.8× faster (219 vs 58 tokens per second).
| Metric | Claude Fable 5.1 (xhigh) | Muse Spark 1.2 |
|---|---|---|
| BenchLeader Index | 70.3 | 62.6 |
| Coding score | 71.3 | 66.5 |
| Composite score | 95.0 | 79.1 |
| Knowledge score | 84.1 | 76.9 |
| Long context score | 68.1 | 66.0 |
| Reasoning score | 76.4 | 70.2 |
| Maths score | – | 54.3 |
| Blended price $/M | $20.00 | $2.00 |
| Output speed | 58 tok/s | 219 tok/s |
| Time to first answer | 132.0 s | 23.7 s |
| Context window | 1M | 1.0M |
| Humanity's Last Exam | 46.5% | – |
| SimpleBench | – | 74.5% |
| SciCode | 60.1% | – |
| ProofBench | – | 43.0% |
| Epoch Capabilities Index | – | 155.5 |
| AA Intelligence Index | 53.2 | 39.8 |
| AA-LCR | 83.0% | 79.0% |
| AA-Omniscience | 42.4 | 27.2 |
| GPQA Diamond (AA) | 93.4% | 90.4% |
| Humanity's Last Exam (AA) | 58.7% | 45.5% |
| SciCode (AA) | 60.9% | 57.4% |
| IOI | – | 49.5% |
| 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.