METR publishes an independent review of at least one lab's test-environment fixes (Anthropic, Google, Meta or the UK AISI) by Nov 30
The index says: unlikely (30%). Graded on that date, right or wrong, in public.
Why the index thinks so
The labs say their test environments are now offline and monitored and have restarted testing, but the independent reviews that would confirm it have not been published. METR's Hugging Face investigation took about five weeks from disclosure to report; the reviews here were promised without dates.
What would move it
metr.org publications; lab posts citing a completed external review.