Introducing GPT-5.2 - OpenAI
13 hours ago · Model performance Economically valuable tasks GPT‑5.2 Thinking is the best model yet for real-world, professional use. On GDPval , an eval measuring well-specified …
GPT-5.2 Review: 70% GDPval Score Crushes Industry Experts
7 hours ago · GPT-5.2 sets a new standard with a 70.9% GDPval score, beating human experts. See how it crushes Gemini 3 Pro in coding, reasoning & pricing benchmarks now.
OpenAI releases GPT-5.2 after “code red” Google threat alert
10 hours ago · OpenAI says GPT-5.2 Thinking beats or ties “human professionals” on 70.9 percent of tasks in the GDPval benchmark (compared to 53.3 percent for Gemini 3 Pro).
OpenAI Launches GPT-5.2 for ChatGPT Users a Week After ...
8 hours ago · OpenAI says that GPT-5.2 outperforms industry professionals at knowledge work tasks spanning 44 occupations, with the model scoring 70.9 percent on the GDPval test.
GPT-5.2 Benchmarks (Explained)
1 day ago · GDPval measures this by evaluating performance on well-specified knowledge work tasks across 44 professional occupations. GPT-5.2 surprisingly beats or ties with top industry …
Are GPT-5.2's new powers enough to surpass Gemini 3? Try it ...
10 hours ago · GPT-5.2 Thinking scored 70.9% on GDPval, compared to GPT-5.1 Thinking's score of 38.8% -- meaning it excelled at typical knowledge work tasks like making …
OpenAI Launches GPT-5.2 in Rapid Response to Google's Gemini
9 hours ago · On GDPval, an evaluation measuring knowledge work across 44 occupations, GPT-5.2 Thinking scores 70.9%, nearly doubling GPT-5's 38.8% performance. That's not just a …