This wasn’t unique to Claude Opus 5.5, with only GPT-6.1 Sol and Gemini 4 Argon stopping within a minute of completing the task. GPT-6 Astra submitted 3 minutes after the passing state, Claude Fable 5.1 kept going for 7 minutes, and Claude Opus 5.5 for a full 22 minutes
Claude Opus 5.5 keeps running 22 minutes after completing task
AIArtificial Analysis says Claude Opus 5.5 kept running for 22 minutes after the task reached a passing state. GPT-6.1 Sol and Gemini 4 Argon stopped within a minute, GPT-6 Astra stopped after 3 minutes, and Claude Fable 5.1 continued for 7 minutes.
Source details
Artificial Analysis · x.comPublished · added here
Original title: This wasn’t unique to Claude Opus 5.5, with only GPT-6.1 Sol and Gemini 4 Argon stopping within a minute of completing the task. GPT-6 As...