Read more at our blog and our paper, and visit http://
evals.openai.com to browse our open source subset. And if you’re interested in contributing, sign up here:
GENERATIVE AI
-
OpenAI Releases Open Source AI Evaluation Benchmark Suite
By
–
-
GDPval: Measuring AI’s Economic Impact on GDP
By
–
GDPval is an early step and does not cover all work that affects GDP. We aim for future GDPval iterations to progressively incorporate greater breadth, realism, interactivity, and contextual nuance. We hope this release helps facilitates future research in understanding
-

Claude Opus 4.1 Achieves Expert-Level Performance on GDPval
By
–
On GDPval, expert graders compared outputs from leading models to human expert work. Claude Opus 4.1 delivered the strongest results, with just under half of its outputs rated as good as or better than expert work. Just as striking is the pace of progress: OpenAI’s frontier
-
LLMs Shaping Politics: Comparing Models with Real-World Polls
By
–
The team envisions comparing model outputs w/real-world polls, expanding studies to other democracies, examining newer reasoning or "thinking" models, & exploring downstream effects on users. For now, the dataset helps us understand how LLMs are shaping modern political
-
LLM Behavior During 2024 US Election: Stability and Contradictions
By
–
The dataset presents a multidimensional view of LLM behavior that captures both stability & change during the first major US election since LLMs became mainstream. It essentially lets you watch these models think, stumble, & sometimes contradict themselves during the 2024
-
Perplexity Finance Standalone App Potential Explored
By
–
Saw someone using Perplexity Finance in the wild. Maybe a standalone app could be cool. pic.twitter.com/CzeUVaRkNh
— Aravind Srinivas (@AravSrinivas) 25 septembre 2025Saw someone using Perplexity Finance in the wild. Maybe a standalone app could be cool.
-
OpenAI’s Free School ChatGPT Strategy Mirrors Big Tech Expansion
By
–
Really interesting read, shows OpenAI following the expansion playbook of many of its elder Silicon Valley peers. Free Basics/Internet.org, anyone?! the-ken.com/story/openai-off…
→ View original post on X — @madhumita29, 2025-09-25 14:46 UTC
-

AI Image Recognition Won’t Replace Radiologists Soon
By
–
"AI isn't replacing radiologists" good article Expectation: rapid progress in image recognition AI will delete radiology jobs (e.g. as famously predicted by Geoff Hinton now almost a decade ago). Reality: radiology is doing great and is growing. There are a lot of imo naive
-
ChatGPT Apple Watch App: Voice-Enabled AI Assistant
By
–
ChatGPT app on Apple watch, wen? @romainhuet Would be a killer app (voice mode)
-
General-Purpose Language Models Excel at Summarization Tasks
By
–
We don't have a model specialized in summarization (yet), but the general-purpose LFMs are already very good at it!