OpenAI· GPT / ChatGPT / APISeparating 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.
Visit source ↗openai.com
- Announced
- 08 Jul 2026 13:00 UTC
Other stories
OpenAI · 18 AugIntroducing ChatGPT for Teens: Built for learning, backed by protectionsOpenAI · 18 AugIntroducing ChatGPT for Teens: Built for learning, backed by protectionsOpenAI · 18 AugPartnering with CodeAI to prepare the first AI generationOpenAI · 17 AugThe Defender’s WindowOpenAI · 17 AugOpenAI joins PORTS-Pike projectOpenAI · 17 AugNew policy ideas for the Intelligence Age