Docs
Technical references for the LLM intelligence hub, model catalog, citations policy, benchmark glossary, and weekly refresh process.
Intelligence hub quickstart
How to move between leaderboard rows, model profiles, news, and benchmark guides.
Citation policy
Requirements for source name, URL, retrieval date, and metric scope.
Model catalog guide
How to search by provider, license, context window, price, modality, and evidence.
Benchmark glossary
What GPQA, AIME, SWE-bench, Code Arena, MMMU, Toolathlon, and long-context metrics mean.
News curation policy
How EvalKit separates releases, research, benchmark changes, and resources.
Weekly refresh process
Manual cadence for updating benchmark snapshots every week.