Date: September 16th, 2026 8:07 PM
Author: https://i.imgur.com/YbMiOBE.png
How much does context rot cost on agentic coding tasks? We prefilled 250k–500k tokens of context and ran GPT-5.6 Sol and Claude Opus 5 on terminal-bench tasks to find out.
Sol performance drops significantly at longer contexts, even when the context is completely unrelated to the task. Opus 5 holds flat on unrelated context but degrades when the context is related.
https://x.com/sanyamsatia/status/2100019768455750124
(http://www.autoadmit.com/thread.php?thread_id=5904441&forum_id=2в#50138923)