Cosine has launched Genie, a coding agent that has achieved the top ranking on the SWE-Bench benchmark, surpassing previous leaders by a significant margin. This success is attributed to fine-tuning OpenAI's GPT-4o model on billions of tokens of synthetically generated code and runtime errors. OpenAI collaborated with Cosine on the scale and specifics of the fine-tuning process, including the dynamic sizing of LoRA adapters. Genie utilizes a four-stage workflow and is designed to output code in formats suitable for direct integration into codebases. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
RANK_REASON New coding agent (Genie) from Cosine achieves state-of-the-art results on SWE-Bench using fine-tuned GPT-4o, a significant advancement in AI coding capabilities.
