Updated
Which AI model writes the most type and compile errors?
As of Nov 14, 2026, GPT-6.1 Sol had the highest rate of type and compile errors (2.94, 194% above the all-model rate). GPT-6 Astra had the lowest (0.72, 28% below average), statistically tied with Claude Opus 5.5 and Claude Fable 5.1.
| Rank | Model | Rate |
|---|---|---|
| 1= (statistically tied) | GPT-6 Astra | 0.72 |
| 2= (statistically tied) | Claude Opus 5.5 | 0.78 |
| 3= (statistically tied) | Claude Fable 5.1 | 1.04 |
| 4 | GPT-6.1 Sol | 2.94 |
1.00 = all-model rate · lower is better · = statistically tied