Vikshy is not being updated. Updates were paused on 20 October 2026, so the news, the Score, prices and rankings here are out of date and will stay as they are. Check the labs' own sites for anything newer.
Get the Brief
The DecoderResearchMateriality 2Unconfirmed

Taste-Bench tests AI agents on long-term strategic choices

A new benchmark called Taste-Bench tests how well AI agents make strategic choices during long-running tasks. The best model, GPT-5.6 Sol, picks the right path on just under 60 percent of simple binary questions, and thinking longer does not help.

First seen 18 Oct, 08:49 UTC on The Decoder1 sourceLast update 2d ago

What the sources say

Linked, never rewritten. Official means the lab itself.

Official0

No word from The Decoder yet.

Press1

The Decoder· 18 Oct, 08:49AI agents have bad taste in long-term decisions and a new benchmark proves it

How it unfolded

Every source in the order it appeared. Times in UTC.

18 Oct 08:49The Decoder AI agents have bad taste in long-term decisions and a new benchmark proves it