METR estimated Anthropic’s AECI benchmark-score growth at 1.9× its earlier rate, with a 95% interval of 1.5×–2.8× and uncertain AI attribution.
AIHUB
METR estimates Anthropic benchmark-score growth accelerated 1.9×
METR estimated that Anthropic’s AECI benchmark scores are improving at 1.9 times the earlier rate. The reported 95% interval ranges from 1.5× to 2.8×, while the extent to which AI itself explains the acceleration remains uncertain.
The estimate offers a quantified signal of Anthropic’s benchmark progress, but its broad uncertainty interval and unclear attribution limit the conclusion.
Comments & Questions (0)
No comments yet
Be the first to comment!