AIThe Decoderabout 2 hours ago
OpenAI finds 30% of coding test broken
1 min read
OpenAI reviewed SWE-Bench Pro, a popular AI coding benchmark, and found roughly 30 percent of its tasks are broken. The company is withdrawing its earlier endorsement of the test.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
