OpenAI’s new “Deep Research” blows ChatGPT o3-mini and DeepSeek out of the water with 26.6% accuracy in the world’s hardest “AI exam” — but it skipped the line

February 5, 2025

Deep Research holds a significant lead ahead of ChatGPT o3-mini and DeepSeek’s R1 V3-powered model in the world’s hardest AI exam, with a 26.6% accuracy score.

Source: Read MoreÂ / Windows Central

Previous ArticleMonster Hunter Wilds has received updated PC Spec requirements and a new PC Benchmark program to help players test them out

Next Article Salesforce will reportedly lay off 1,000 employees while hiring extra AI marketing roles to bolster agentic product sales

Leave A Reply