Extend AiBenchLab with Plugins
Custom test domains, community evaluations, and industry-specific benchmarks — built on a modular plugin architecture.
Go beyond the built-in test domains.
AiBenchLab ships with 11 built-in test domains covering reasoning, coding, safety, chat, multimodal, agentic workflows, and more. Plugins let you go further — adding custom evaluation domains tailored to your specific industry, application, or compliance requirements.
Each plugin adds:
- ✓ New test domains with custom test cases specific to your industry or use case
- ✓ Domain-specific scoring criteria and pass/fail thresholds
- ✓ Full integration with the existing benchmark wizard, queue, and reporting system
- ✓ Plugin integrity validation — every plugin is verified before it can run
Plugin Starter Packs
For developers and teams who want to build their own evaluation domains, AiBenchLab provides Plugin Starter Packs — template projects with everything you need to create, test, and distribute a plugin.
Think of them like project templates: clone, customize, and you're running your own evaluation domain. The same quality and security standards that govern built-in domains apply to every plugin.
Plugin validated. Ready to run.