GPT-5.2, Grok 4.1, and DeepSeek v3.2 compare as Santa agents(veris.ai)
veris.ai
GPT-5.2, Grok 4.1, and DeepSeek v3.2 compare as Santa agents
https://veris.ai/blog/santabench
2 comments
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.
OP here -- I work at Veris and built this. Happy to answer questions about the methodology!