LLM Performance on a Real, Double-Marked GCSE Benchmark
arXiv:2606.24973v1 Announce Type: new Abstract: We introduce a dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are the UK's national exams, taken at age ~16), spanning 328 questions across five subjects and including handwritten work. We test whether off-the-shelf large language models agree with examiners as closely as the two examiners agree with each other. We find that models overwhelmingly agree well with the examiner consensus across subjects, with the top ...
arXiv cs.CL
·Malachy Fox, Kavi Samra, Paul Jung
·
// relacionados
Leia também
Blog
Amazon ups India bet with fresh $13B AI infrastructure investment
Editorial
Jalapeño: a OpenAI projeta seu primeiro chip de inferência — e usou IA para fazer isso em 9 meses
Editorial
SkillOpt: como ensinar agentes de IA a melhorar suas próprias habilidades — +23 pontos em GPT-5.5
Blog