Datacurve

OpenAI reviewed the SWE-Bench Pro AI coding test and found roughly 30% of its tasks are flawed, leading the company to withdraw its endorsement. The problems include overly strict or vague task requir…

Datacurve released a new AI coding benchmark called DeepSWE on Monday that shows a wide performance gap between leading models, with OpenAI's GPT-5.5 scoring 70% — 16 points ahead of its nearest compe…