Home
»
Techmeme
» OpenAI says it found widespread task issues in SWE-Bench Pro, estimates ~30% of tasks are broken, and retracts its earlier recommendation to adopt the benchmark (OpenAI)
OpenAI says it found widespread task issues in SWE-Bench Pro, estimates ~30% of tasks are broken, and retracts its earlier recommendation to adopt the benchmark (OpenAI)
By
Eresh
•
July 08, 2026
•
https://www.techmeme.com/
Techmeme
•
OpenAI:
OpenAI says it found widespread task issues in SWE-Bench Pro, estimates ~30% of tasks are broken, and retracts its earlier recommendation to adopt the benchmark — Through a detailed audit, we find widespread task issues in SWE-Bench Pro and estimate that ~30% of the tasks are broken.
from Techmeme https://ift.tt/2oaw5rY
SIMILAR ARTICLES
Post a Comment