Claude Fable 5.1 vs Grok 4.6
Claude Fable 5.1 
Grok 4.6 Verdict
- Claude Fable 5.1 (xhigh) leads on quality: 70.3 vs 63.8.
- Claude Fable 5.1 (xhigh) is stronger in coding, composite, knowledge, long context, reasoning.
- Grok 4.6 (medium) is 6.7× cheaper ($3.00 vs $20.00 per 1M blended).
| Metric | Claude Fable 5.1 (xhigh) | Grok 4.6 (medium) |
|---|---|---|
| BenchLeader Index | 70.3 | 63.8 |
| Coding score | 71.3 | 63.9 |
| Composite score | 95.0 | 83.2 |
| Knowledge score | 84.1 | 77.3 |
| Long context score | 68.1 | 67.1 |
| Reasoning score | 76.4 | 62.1 |
| Blended price $/M | $20.00 | $3.00 |
| Output speed | 58 tok/s | 55 tok/s |
| Time to first answer | 132.0 s | 36.7 s |
| Context window | 1M | 500k |
| Humanity's Last Exam | 46.5% | – |
| SciCode | 60.1% | 54.6% |
| AA Intelligence Index | 53.2 | 43.0 |
| AA-LCR | 83.0% | 81.0% |
| AA-Omniscience | 42.4 | 28 |
| GPQA Diamond (AA) | 93.4% | 93.5% |
| Humanity's Last Exam (AA) | 58.7% | 42.1% |
| SciCode (AA) | 60.9% | 55.9% |
| ARC-AGI-1 | 96.5% | 87.5% |
| ARC-AGI-2 | 90.0% | 61.3% |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.