Codex users report GPT-5.5 reasoning tokens clustering at 516, linked to weaker answers
A GitHub issue analyzing Codex token metadata from February 1 to June 27, 2026 found gpt-5.5 responses landing disproportionately at exactly 516 reasoning tokens, consistent with a reasoning-budget threshold. The author says it does not prove truncation. The thread drew 372 points and 152 comments.
Source
"GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance"
Published · 152 comments