Updated
Which AI model writes the most accessibility and UX issues?
As of Sep 27, 2026, Claude Sonnet 5 had the highest rate of accessibility and UX issues, 54% above the all-model rate (1.54), statistically tied with 4 other models. GPT-5.5 had the lowest, 51% below average (0.49), statistically tied with Claude Fable 5 and GPT-5.6 Sol.
| Rank | Model | Rate |
|---|---|---|
| 1= (statistically tied) | GPT-5.5 | 0.49 |
| 2= (statistically tied) | Claude Fable 5 | 0.67 |
| 3= (statistically tied) | GPT-5.6 Sol | 0.70 |
| 4= (statistically tied) | Claude Opus 4.8 | 1.03 |
| 5= (statistically tied) | GPT-6 Astra | 1.08 |
| 6= (statistically tied) | Claude Fable 5.1 | 1.21 |
| 7= (statistically tied) | Claude Opus 5 | 1.40 |
| 8= (statistically tied) | Claude Sonnet 5 | 1.54 |
1.00 = all-model rate · lower is better · = statistically tied