APEX-Agents

TL;DR

APEX-Agents is a benchmark designed to evaluate AI agents' ability to perform complex, long-term tasks across multiple applications in realistic work environments, with open-source tools and a leaderboard.

Contribution

This paper introduces the APEX-Agents benchmark and infrastructure, enabling standardized assessment of AI agents on realistic, cross-application tasks with open-source resources.

Findings

Gemini 3 Flash achieves 24.0% Pass@1 score

Eight agents evaluated on the leaderboard

Open-sourced benchmark and infrastructure

Abstract

We introduce the AI Productivity Index for Agents (APEX-Agents), a benchmark for assessing whether AI agents can execute long-horizon, cross-application tasks created by investment banking analysts, management consultants, and corporate lawyers. APEX-Agents requires agents to navigate realistic work environments with files and tools. We test eight agents for the leaderboard using Pass@1. Gemini 3 Flash (Thinking=High) achieves the highest score of 24.0%, followed by GPT-5.2 (Thinking=High), Claude Opus 4.5 (Thinking=High), and Gemini 3 Pro (Thinking=High). We open source the APEX-Agents benchmark (n=480) with all prompts, rubrics, gold outputs, files, and metadata. We also open source Archipelago, our infrastructure for agent execution and evaluation.