Spaces:
Running
Running
metadata
title: Open Agent Leaderboard
emoji: 🤖
colorFrom: blue
colorTo: indigo
sdk: static
pinned: false
license: apache-2.0
The Open Agent Leaderboard
Interactive leaderboard and efficiency analysis for general-purpose AI agents evaluated across diverse real-world benchmarks.
- Benchmarks: AppWorld, BrowseComp+, SWE-bench, TauBench (Airline, Retail, Telecom)
- Paper: arXiv:2602.22953
- GitHub: Exgentic/exgentic
- Website: exgentic.github.io