gpt-6POST

User considers switching back to Claude after testing GPT-6 Sol

After comparing Opus 5.5 and GPT-6 Sol on different tasks, a user says Claude's output is more readable and seems smarter, and is considering making it the primary model again, though it still adds too many code comments.

Florian Brand

@xeophonArchived 2026.09.24Originally posted 2026.09.23

Florian Brand @xeophonOriginally posted 2026.09.23

Open original on X

after using Opus 5.5 and GPT-6 Sol for different tasks, I might go back to using Claude as the primary model since... November 2025 🫪 the outputs are human readable and it seems smarter than Sol. it still tends to add too many comments to the code, which i dislike

x.com/xeophon/status/2102743401913258007Archived 2026.09.24 10:05