Get the latest tech news

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.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of OpenAI

OpenAI

Photo of SWE-Bench Pro

SWE-Bench Pro

Related news:

News photo

OpenAI launches GPT-Live, a full-duplex voice upgrade that lets ChatGPT talk more like a person

News photo

BofA Bankers U-Turn on OpenAI

News photo

Jittery Tech Markets; OpenAI Gets BofA Credit Line | Bloomberg Tech 7/08/2026