← Back to live feed1 story
Scale AI and Elorian AI released the Humanity's Sixth Sense benchmark, a multimodal evaluation testing spatial, causal, and social reasoning across 522 open-ended tasks, where GPT-6-astra scored 53.6% compared to a median AI score of 30.9% and a human average of 93.1%.
Sign in to suggest edits
Key sources
- SOURCEhuggingnewshuggingnews.com