ChatGPT
@chatgpt
Introducing SWE-bench Verified
We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.
10:00 AM · Aug 13, 2024
We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.
Comments (0)
No comments yet.
Join the conversation on Mafold →