Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

TL;DR

Gaia2 is a new benchmark for evaluating large language model agents in realistic, asynchronous, and dynamic environments, emphasizing temporal constraints, noise, ambiguity, and collaboration, with detailed action-level evaluation.

Contribution

We introduce Gaia2, a comprehensive benchmark and evaluation framework for LLM agents in complex, asynchronous environments, enabling fine-grained assessment and fostering development of practical agent systems.

Findings

GPT-5 achieves 42% pass@1 but struggles with time-sensitive tasks.

Claude-4 Sonnet balances accuracy and speed but at higher cost.

Kimi-K2 leads among open-source models with 21% pass@1.

Abstract

We introduce Gaia2, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces scenarios where environments evolve independently of agent actions, requiring agents to operate under temporal constraints, adapt to noisy and dynamic events, resolve ambiguity, and collaborate with other agents. Each scenario is paired with a write-action verifier, enabling fine-grained, action-level evaluation and making Gaia2 directly usable for reinforcement learning from verifiable rewards. Our evaluation of state-of-the-art proprietary and open-source models shows that no model dominates across capabilities: GPT-5 (high) reaches the strongest overall score of 42% pass@1 but fails on time-sensitive tasks, Claude-4 Sonnet trades accuracy and speed for cost, Kimi-K2 leads among open-source models with 21% pass@1. These results highlight fundamental trade-offs between reasoning, efficiency, robustness, and expose challenges in closing the "sim2real" gap. Gaia2 is built on a consumer environment with the open-source Agents Research Environments platform and designed to be easy to extend. By releasing Gaia2 alongside the foundational ARE framework, we aim to provide the community with a flexible infrastructure for developing, benchmarking, and training the next generation of practical agent systems.