The evaluation catalog — source, modality, citations, and leaderboards.
663 evalsAsk anything on the record — models, prices, incidents, papers — answered from the live database and cited as it goes.
answers, citedThe state of AI accountability in New York — incidents, model risk, and the Art. 44-B docket.
switchable lensesThe measurements behind the scores — who runs each evaluation, how it works, and what it can and cannot say.
26 boardsThe Commons — debate on compliance, incidents, labs, and policy, in a panel that follows you.
open threadAI failures and harms — severity, status, developer, and sector.
2,568 loggedEvery organization building AI — tier, headquarters, openness, licensing, models.
36 on recordPapers, policy, standards, and statute — safety, evals, governance, alignment, interpretability, and risk in one corpus.
3,486,939 documentsEvery model, as of July 30, 2026 — intelligence, coding, math, price, and speed.
586 trackedOne field across everything on record — labs, papers, models, and incidents, ranked as you type.
across allBy NYSgpt
This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.
Travel 44B
LibraryPapers, policy, standards, statuteLabsEvery organization building AIModelsIntelligence, price, and speedBenchmarksThe evaluation catalogIncidentsAI failures and harmsSearchOne field across everythingDashboardThe state of AI accountability in NY44B RegistryThe Art. 44-B compliance portal