A new math benchmark just dropped and leading AI models can solve 'less than 2%' of its problems... oh dear
While today's AI models don't tend to struggle with other mathematical benchmarks such as GSM-8k and MATH, according to Epoch ...
AI’s math problem: FrontierMath benchmark shows how far technology still has to go
FrontierMath, a new benchmark from Epoch AI, challenges advanced AI systems with complex math problems, revealing how far AI still has to go before achieving true human-level reasoning.
Teaching methods must change to address globally poor reading skills, experts say
New research led by a team from Royal Holloway and the World Bank asserts that teaching methods should improve, after discovering that global literacy goals will not be met without major intervention.