AI models evaluated against FrontierMath include OpenAI's GPT-4o and o1-preview.
Sources
- New secret math benchmark stumps AI models and PhDs alike (arstechnica.com)
- https://epoch.ai/frontiermath/tiers-1-4/the-benchmark (epoch.ai)
- https://arxiv.org/pdf/2411.04872 (arxiv.org)
More in Technology
- The US Copyright Office is refusing to grant copyrights to images and text generated by AI, a policy that has raised concerns from organizations including the Motion Picture Association of America.
- GOSAT-2's critical operations phase concluded following successful deployment of solar arrays and powering up of bus and mission equipment.
- The working paper proposes a dual-layer transparency regime requiring AI-gatekeepers to disclose aggregate testing methodologies and standards at the collective level while providing compact certifications or scores at the individual level.
- NASA's SNAP-10A, launched in 1965, was the only nuclear reactor the United States had previously deployed in space before current lunar plans.
- UWB technology can spread a signal across gigahertz of spectrum while using only picowatts of power per hertz, causing the signal to appear as background radiation, or the noise floor, to conventional narrowband receivers.
- AI models evaluated against FrontierMath include Anthropic's Claude 3.5.