GPT-5.2, Grok 4.1, and DeepSeek v3.2 compare as Santa agents (veris.ai) 4 points by _josh_meyer_ 6mo ago ↗ HN
[–] _josh_meyer_ 6mo ago ↗ SantaBench, a fun benchmark with a serious methodology. The task: play a cheeky Santa agent who researches users online and roasts them based on their social media.
[–] _josh_meyer_ 6mo ago ↗ OP here -- I work at Veris and built this. Happy to answer questions about the methodology!
2 comments
[ 4.1 ms ] story [ 16.9 ms ] thread