03:52
2026-05-27
venturebeat.com
artificial-intelligence
DeepSWE blows up the AI coding leaderboard, crowns GPT-5.5
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…