Category: Computer Science & AI
-
Humanity’s Last Exam benchmarks expert-level AI performance
This research indicates that state-of-the-art large language models perform poorly on Humanity’s Last Exam, a multimodal benchmark of expert-level academic questions, showing a gap between current AI capabilities and the expert human frontier on closed-ended academic questions.
AI-assisted summary
-
Study identifies key chatbot features for financial modeling
This research indicates that ease of use, recommendation ability, and advanced features are important factors in chatbots for financial modeling.
AI-assisted summary