Claude Code used by 80% of developers despite GPT-5.5 producing fewer bugs
According to Cubic's State of AI Coding 2026 report analyzing thousands of daily commits, GPT-5.5 produces fewer bugs per lines changed than any other model in their dataset, yet Claude Code remains the most popular coding agent with 80% developer adoption. Opus models are the most-used model family, with Claude Fable adopted by 30% of developers within 48 hours of release. The report notes that Opus 4.8 shows a higher bug rate than Opus 4.7, for which the authors have no firm explanation.
Topics
Sources
- Press Read article
Go deeper
This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.