Updated

Which AI model writes the most code-quality issues?

As of Sep 27, 2026, Claude Sonnet 5 had the highest rate of code-quality issues, 119% above the all-model rate (2.19). Claude Fable 5 had the lowest, 45% below average (0.55), statistically tied with Claude Fable 5.1 and GPT-5.5.

Models ranked by relative rate of code-quality issues, fewest first. Lower values are better.
RankModelRate
1= (statistically tied)Claude Fable 5
0.55
2= (statistically tied)GPT-5.6 Sol
0.87
3= (statistically tied)Claude Opus 4.8
0.88
4= (statistically tied)Claude Fable 5.1
0.88
5= (statistically tied)GPT-5.5
0.89
6= (statistically tied)GPT-6 Astra
1.19
7= (statistically tied)Claude Opus 5
1.30
8Claude Sonnet 5
2.19

1.00 = all-model rate · lower is better · = statistically tied