The Decoder· Jonathan Kemper·· 8 h ago
AI agents have bad taste in long-term decisions and a new benchmark proves it
AI agents have bad taste in long-term decisions and a new benchmark proves it
AI summary
A new benchmark called Taste-Bench tests how well AI agents make strategic choices during long-running tasks. Even the best model, GPT-5.6 Sol, picks the right path on just under 60 percent of simple binary questions. Thinking longer doesn't help.
Selection record
Threshold 76Media and individualsFirst 58Second 58
Not admittedSum of both 116 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：AI Agent长期决策评测基准
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com