Reasoning is at the core of scientific work. Beyond recalling facts, scientists generate hypotheses, test and refine them, and synthesize ideas across fields. As our models become more capable, the c… [+13641 chars]
Evaluating AI’s ability to perform scientific research tasks - OpenAI
We introduce FrontierScience, a new benchmark that evaluates AI capabilities for expert-level scientific reasoning across physics, chemistry, and biology.
Source:Openai.com
Published:

Related News

US Treasury Says It’s Canceled Booz Allen Hamilton Contracts - Bloomberg.com
The US Treasury Department said it canceled $21 million of contracts with Booz Allen Hamilton, alleging the consulting firm failed to protect taxpayer data to which it had access, including President Donald Trump’s tax returns.
Bloomberg•Daniel Flatley

Payment processors were against CSAM until Grok started making it - The Verge
For years, the payments industry was aggressive about cutting off access to websites accused of containing child sexual abuse material. Elon Musk changed that.
The Verge•Elizabeth Lopatto

TikTok blames its US problems on a power outage - The Verge
TikTok USDS says a power outage caused the issues experienced by US-based users starting this weekend, which stalled uploads and upset its For You algorithm.
The Verge•Emma Roth