Updated
Which AI model writes the most accessibility and UX issues?
As of Nov 14, 2026, Grok 4.7 had the highest rate of accessibility and UX issues (4.56, 356% above the all-model rate). Claude Fable 5.1 had the lowest (0.68, 32% below average), statistically tied with GPT-6 Astra and GPT-6.1 Sol.
| Rank | Model | Rate |
|---|---|---|
| 1= (statistically tied) | Claude Fable 5.1 | 0.68 |
| 2= (statistically tied) | GPT-6 Astra | 0.83 |
| 3= (statistically tied) | GPT-6.1 Sol | 0.83 |
| 4= (statistically tied) | Claude Sonnet 5.5 | 1.31 |
| 5= (statistically tied) | Claude Opus 5.5 | 1.44 |
| 6 | Grok 4.7 | 4.56 |
1.00 = all-model rate · lower is better · = statistically tied