Congress Is Suddenly Waking Up to the AI Doomsday Threat36m ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself44m ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers46m ago Introducing ChatGPT for Financial Services50m ago Tesla unveils driverless Cybercab in Japan for 1st time1h ago The AI safety vibe shift2h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.2h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff2h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut2h ago Salesforce introduces Enterprise AI Harness, AI Control Plane2h ago The Race for the Next Big Weight-Loss Drug Is On—and China Wants In3h ago How Social Media Platforms Are Identifying AI Content3h ago DeepSeek launches V4.1-Flash and retires V4-Pro, its flagship model3h ago OpenAI Wants to Know if an AI Industry Slowdown Would Even Be Legal3h ago

Congress Is Suddenly Waking Up to the AI Doomsday Threat36m ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself44m ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers46m ago Introducing ChatGPT for Financial Services50m ago Tesla unveils driverless Cybercab in Japan for 1st time1h ago The AI safety vibe shift2h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.2h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff2h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut2h ago Salesforce introduces Enterprise AI Harness, AI Control Plane2h ago The Race for the Next Big Weight-Loss Drug Is On—and China Wants In3h ago How Social Media Platforms Are Identifying AI Content3h ago DeepSeek launches V4.1-Flash and retires V4-Pro, its flagship model3h ago OpenAI Wants to Know if an AI Industry Slowdown Would Even Be Legal3h ago

Dev6 min reading time

Separating signal from noise in coding evaluations

Open AI NewsPublished Jul 8, 2026

OpenAI audited the SWE-Bench Pro coding benchmark, finding over a third of tasks flawed due to strict tests, underspecified prompts, low test coverage, or misleading instructions, impacting accurate model evaluation.

#coding-benchmarks #model-evaluation #openai #swe-bench-pro

More in Dev

Introducing the Agents API

Covered by 3 sources1d ago

Dev1 min read

Native is now the future of mobile at Shopify

Simon Willison's Weblog6h ago

Dev5 min read

AWS open-sources Pizza Bot: email-style inbox for background AI agents

The New Stack (AI)4h ago