AgentBench

ICLR'24 benchmark: agents across AlfWorld, DB, knowledge graphs, OS, webshop; Docker Compose, function-calling interface.

evalssandboxragworkflowpython

Stars: 3.8k
Adoption surface: complex
Autonomy: headless
Recovery: none
License: ✅ open-source
Category: Evaluation and benchmarking harnesses

Repository ↗ Example: AgentBench ICLR'24 paper ↗

Related in Evaluation and benchmarking harnesses

Agent Lightning
SWE-bench
inspect_ai
WebArena
ClawBench
WebVoyager

Maintain AgentBench? Add the badge

Paste this into your README so readers can find the list and see how AgentBench compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)