Alibaba Cloud has released the Wuying-Browser-Agent-27B, an open-source browser agent that has achieved a score of 65.1% on a new 350-task web benchmark. This agent reportedly averages 37.9 steps to complete tasks, setting a new state-of-the-art for browser agents in the open-source community. AI
IMPACT This release sets a new benchmark for open-source browser agents, potentially accelerating development in web automation and AI-driven task completion.
RANK_REASON The cluster reports on a new model release and benchmark performance for an open-source agent. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
