GAIA2 is a dataset designed for agentic evaluation on real-life assistant tasks. It is used with the open Meta Agents Research Environments (ARE) framework to run, debug, and evaluate agents. The dataset includes scenarios for multi-step instruction following and tool-use (execution), cross-source information gathering (search), and clarification of conflicting requests (ambiguity handling). It also features temporal constraints, dynamic environment events, and multi-agent collaboration scenarios.
No results indexed yet — be the first to submit a score.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.