app + skill + benchmark
Inspect AI
An open-source framework for building and running language-model evaluations.
What it is
Inspect AI provides datasets, solvers, tools, scorers, logs, and sandbox support for reproducible model evaluations.
Related records
SWE-agentA research system that enables language models to resolve software engineering tasks in repositories.BrowserGymA framework and benchmark family for evaluating web agents in browser-based environments.OpenAI EvalsAn open-source framework and registry for evaluating language models and model systems.LM Evaluation HarnessA framework for evaluating language models across a broad collection of academic tasks.