Separating signal from noise in coding evaluations
A new analysis from OpenAI reveals issues in SWE-Bench Pro, a popular coding benchmark, raising concerns about reliability and accuracy in evaluating AI models.
TopicsAI Search
Related
GPT-5 System Card
OpenAI
This GPT-5 system card explains how a unified model routing system powers fast and smart responses using gpt-5-main, gpt-5-thinking, and lightweight versions like gpt-5-thinking-nano, optimized for different tasks and developer use.
Helping disaster response teams turn AI into action across Asia
OpenAI
AI for Disaster Response in Asia: OpenAI Workshop with Gates Foundation
How Amgen uses GPT-5
OpenAI
Learn how Amgen uses GPT-5.
OpenAI announces Frontier Alliance Partners
OpenAI
OpenAI announces Frontier Alliance Partners to help enterprises move from AI pilots to production with secure, scalable agent deployments.
EMEA Youth & Wellbeing Grant
OpenAI
Apply for the EMEA Youth & Wellbeing Grant, a €500,000 program funding NGOs and researchers advancing youth safety and wellbeing in the age of AI.
A research agenda for assessing the economic impacts of code generation models
OpenAI