Claude Fable 5.1 vs Muse Spark 1.1
Claude Fable 5.1 
Muse Spark 1.1 Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 64.9.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, long context, reasoning.
- Muse Spark 1.1 is stronger in agents & tools, human preference, instruction following, maths, multimodal.
- Muse Spark 1.1 is 10× cheaper ($2.00 vs $20.00 per 1M blended).
- Muse Spark 1.1 streams 3.3× faster (194 vs 58 tokens per second).
| Metric | Claude Fable 5.1 (xhigh) | Muse Spark 1.1 |
|---|---|---|
| BenchLeader Index | 70.3 | 64.9 |
| Coding score | 71.3 | 68.2 |
| Composite score | 95.0 | 72.2 |
| Knowledge score | 84.1 | 73.1 |
| Long context score | 68.1 | 65.3 |
| Reasoning score | 76.4 | 68.8 |
| Agents & tools score | – | 62.7 |
| Human preference score | – | 66.0 |
| Instruction following score | – | 77.8 |
| Maths score | – | 52.2 |
| Multimodal score | – | 64.9 |
| Blended price $/M | $20.00 | $2.00 |
| Output speed | 58 tok/s | 194 tok/s |
| Time to first answer | 132.0 s | 2.0 s |
| Context window | 1M | 1.0M |
| SimpleQA Verified | – | 57.8% |
| Humanity's Last Exam | 46.5% | – |
| SciCode | 60.1% | 58.2% |
| APEX-Agents | – | 41.9% |
| ProofBench | – | 39.0% |
| Epoch Capabilities Index | – | 154.6 |
| LMArena Text | – | 1492 |
| LMArena Hard Prompts | – | 1511 |
| LMArena Coding | – | 1531 |
| LMArena WebDev | – | 1541 |
| LMArena Vision | – | 1293 |
| LMArena Agent | – | -2.6 |
| AA Intelligence Index | 53.2 | 34.3 |
| AA-LCR | 83.0% | 77.7% |
| AA-Omniscience | 42.4 | 28.1 |
| GPQA Diamond (AA) | 93.4% | 89.8% |
| Humanity's Last Exam (AA) | 58.7% | 46.2% |
| SciCode (AA) | 60.9% | 58.8% |
| SWE-Bench Pro | – | 61.5% |
| MCP Atlas | – | 88.1% |
| MultiChallenge | – | 75.3% |
| PRBench Finance | – | 55.0% |
| PRBench Legal | – | 57.0% |
| MultiNRC | – | 65.6% |
| EQ-Bench 4 | – | 1260 |
| 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.