Twelve dimensions across seven providers. Re-graded as announcements land, with the market's reaction shown alongside.
Can it actually do work? · updated 2026-06-01
Limited shipped agentic product; capability lives in the open ecosystem more than in Meta AI.
Can the system take a goal and complete multi-step work autonomously (browse, write code, operate tools, recover from errors), not just answer questions? Measures shipped agentic behavior, not demos.