Apps · PROJECT NOTES
AgentBench
A multi-domain agent benchmark whose current function-calling edition provides containerized tasks for operating-system commands, databases, knowledge graphs, shopping and text-based household tasks.
What can you do with it?
Compare multi-turn reasoning and tool use across several controlled task domains.
What should you know before using it?
The current function-calling edition differs from the original eight-environment benchmark. Docker services can be resource intensive; the README documents ALFWorld memory/disk leakage and WebShop memory needs.
What is verified here?
This entry was reviewed against original project material. We have not independently run the software or reproduced its results. AI-development claims are author-reported; check upstream for current versions, setup requirements, and licenses.
- Resource type
- Benchmark suite
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Consult upstream documentation