Is Opus 5.5 nerfed? Thinking patterns changed on November 3

Shane Melaugh reported on X that an analysis of 1,400 Claude Code sessions by Gemini 4 Argon found the reasoning behavior of Opus 5.5 changed sharply on November 3 even though the model name stayed the same. In a quick test on a real bug, Melaugh said Opus 5.5 at high effort jumped into action too quickly and failed to find a fix after 3 full hours, while Opus 5.5 at xhigh effort paused to think and found a fix within a few minutes. Melaugh said he launched a job on bb-1 using Opus 5.5 xhigh to check the claims against his cliproxy logs in ClickHouse.

Shane Melaugh on X: "is Opus 5.5 nerfed? I just had Gemini 4 Argon analyze 1,400 Claude Code sessions and it found that on November 3, something definitely happened. the model name didn't change, but the way it does reasoning took a sharp turn." is Opus 5.5 nerfed? I just had Gemini 4 Argon analyze 1,400 Claude Code sessions and it found that on November 3, something definitely happened. the model name didn't change, but the way it does reasoning took a sharp turn. is Opus 5.5 nerfed? I just had Gemini 4 Argon analyze 1,400 Claude Code sessions and it found that on November 3, something definitely happened. the model name didn't change, but the way it does reasoning took a sharp turn. quick test on a real bug showed Opus 5.5 high jumping into action too quickly, getting confused and being unable to find a fix after 3 full hours. meanwhile Opus 5.5 xhigh takes a moment to think, finds a fix after a few minutes. @bot kick off a job in the fleet repo on bb-1 using opus 5.5 xhigh to investigate this for me. Curious how accurate the claims are. Dig through my cliproxy logs in clickhouse to see if things changed