ReportingPrimary source

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.

OpenAI Blog·Wednesday, July 8, 2026 at 1:00 PM UTC
OA
OpenAI
Frontier AI lab · OpenAI
Fetching source· Pulling live content from openai.com…
Company hub:OpenAI News →
More from OpenAI