AndroidWorld AI Agent Benchmark 2025: Pass@1 & Pass@k
Comprehensive, community-submitted AndroidWorld AI agent benchmark results for 2025, detailing release dates, model sizes, success rates, trajectories, and notes.
AndroidWorldAI agentbenchmarkpass@1pass@ktrajectories+3 more
AndroidWorld AI Agent Benchmark Results 2025: Pass@1 & Pass@k {androidworld-ai-agent-benchmark-2025-pass-at1-pass-atk} Table of Contents - [Overview](overview) - [Primary Results Table (Dataset 1)](primary-results) - [Legacy/Additional Re...