I tracked Claude Code and Codex pass-rates for 95 days — what "getting dumber" actually looks like
A recent analysis tracked the pass rates of Claude Code and Codex over 95 days to assess claims of declining performance. The data revealed that while Claude Code improved significantly after an update, it has recently shown a decline below its established baseline. In contrast, Codex's performance has remained relatively flat across its updates, indicating no significant improvement over time.
- ▪Claude Code's pass rate increased from 54% to 65% after an update but has recently dropped to 52%.
- ▪The decline in Claude Code's performance is statistically significant, indicating a real change rather than just perception.
- ▪Codex's performance has remained stable, oscillating between 54% and 58% across three major updates.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3845674) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Dylan Brown Posted on May 30 I tracked Claude Code and Codex pass-rates for 95 days — what "getting dumber" actually looks like #programming #ai #machinelearning #productivity Every few weeks a thread blows up: "Is Claude Code getting worse?" Someone swears Opus got lazy after an update; someone else says it's placebo. The arguments are always vibes — nobody posts numbers. So I built a tracker.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).