Checked fact 42788 Nov 2026Research
METR's page says it runs 6 independent runs per task, roughly 1,000 runs for the test set.
The exact words it rests on
We launch 6 independent runs for each task ... In theory, it should only take ~1 day for these ~1,000 runs to complete
What the source said when we opened it, on 8 Nov 2026.
The source
Task-completion time horizons of frontier AI models
Checked
Checked by the notis newsroom on , against the source above.
In the story
How METR's time horizon rates AI agents by human task length 8 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.