The FrontierMath benchmark was developed by Epoch AI.
Sources
- New secret math benchmark stumps AI models and PhDs alike (arstechnica.com)
- https://epoch.ai/frontiermath (epoch.ai)
- https://epoch.ai/latest/openai-and-frontiermath (epoch.ai)
- https://ourworldindata.org/grapher/ai-frontiermath-over-time (ourworldindata.org)
- https://arxiv.org/pdf/2508.00459 (arxiv.org)
More in Technology
- The U.S. Naval Research Laboratory's SWELL experiment achieved continuous in-orbit laser power transmission for more than 100 days in 2023, delivering about 1.5 W over 1.45 meters with an end-to-end efficiency of approximately 11%.
- The Aquacade satellite program is still classified.
- The concept known as the 'information bottleneck' is proposed as a theory to help explain why deep neural networks perform successfully.
- American Memory provided electronic versions of primary-source materials in multiple formats, including manuscripts, films, sound recordings, and photographs.
- Agreement between AI models and physician majority vote on NEJM Image Challenge cases was low, with Cohen's kappa of 0.08 for both GPT-4o and Claude 3.7, and 0.24 for Doubao.
- Before the marine chronometer, ships could determine latitude from celestial observations but had no reliable way to determine longitude at sea, because no timekeeper survived shipboard conditions accurately enough.