ResearchBenchmarksGeneral AI Assistant Tasks on GAIA Level 1 (val)Follow62.3AccuracyGPT-521.11631.80842.553.192Dec 7, 2025Evaluation ResultsMethodMethodLinksAccuracy95% CIBetween-Subject VarianceICCGPT-5Model=GPT-5, Web searc...Model=GPT-5, Web search=true, Trials per question=642025.1262.3—0.1850.774GPT-4oModel=GPT-4o, Web sear...Model=GPT-4o, Web search=true, Trials per question=642025.1222.7—0.10.561