Agents
1/5 We hit SOTA performance on BrowseComp-Plus with 95.18% accuracy using AI21 Maestro’s agent optimization. Here’s how we automated the sea…
AI21 Labs achieved state-of-the-art performance on the BrowseComp-Plus benchmark with 95.18% accuracy using their AI21 Maestro model with agent optimization techniques. The post appears to discuss aut
AI21 Labs achieved state-of-the-art performance on the BrowseComp-Plus benchmark with 95.18% accuracy using their AI21 Maestro model with agent optimization techniques. The post appears to discuss automated web browsing or interaction capabilities enabled through their agent optimization approach, though the full details are truncated in the provided title.
Source: AI21 Labs (X) | 2026-04-30