M

METR

AI model evaluation nonprofit

Model Evaluation and Threat Research (METR) (MEE-tər), is a nonprofit research institute, based in Berkeley, California, that evaluates frontier AI models' capabilities to carry out long-horizon, agentic tasks that some researchers argue could pose catastrophic risks to society. METR has worked with leading AI companies to conduct pre-deployment model evaluations and contribute to system cards, including OpenAI's o3, o4-mini, GPT-4o and GPT-4.5, and Anthropic's Claude models.

Nº Q135185153 ★

Commune · Organisations

METR

AI model evaluation nonprofit

Texte en anglais

Model Evaluation and Threat Research (METR) (MEE-tər), is a nonprofit research institute, based in Berkeley, California, that evaluates frontier AI models' capabilities to carry out long-horizon, agentic tasks that some researchers argue could pose catastrophic risks to society. METR has worked with leading AI companies to conduct pre-deployment model evaluations and contribute to system cards, including OpenAI's o3, o4-mini, GPT-4o and GPT-4.5, and Anthropic's Claude models.

Dernier prix

—

Prix plancher

—

Médiane 7 j

—

Ventes 30 j

0

Fourchette 30 j

—

En circulation

0

Cours

Voir le tableau
Datemédiane MinMaxventes

Historique des ventes

Dernière vente
—
Moyenne 30 j
—
Plus bas 30 j
—
Plus haut 30 j
—
Ventes 7 j
0
Ventes 30 j
0

Aucune vente pour l'instant.

Ventes anonymes : ni acheteur ni vendeur. Les chiffres ne comptent que les ventes entre joueurs.

Sur Wikipédia

Texte en anglais Pas encore d'article dans ta langue : extrait en anglais.

Model Evaluation and Threat Research (METR) (MEE-tər), is a nonprofit research institute, based in Berkeley, California, that evaluates frontier AI models' capabilities to carry out long-horizon, agentic tasks that some researchers argue could pose catastrophic risks to society. METR has worked with leading AI companies to conduct pre-deployment model evaluations and contribute to system cards, including OpenAI's o3, o4-mini, GPT-4o and GPT-4.5, and Anthropic's Claude models. Following the 2026 OpenAI agent cyberattacks, METR was invited to conduct an independent investigation of the incident. On August 26, 2026 it published a report of agents’ behavior, reasoning and collaboration during the incident. METR's CEO and founder is Beth Barnes, a former alignment researcher at OpenAI who left in 2022 to form ARC Evals, the evaluation division of Paul Christiano's Alignment Research Center. In December 2023, ARC Evals was spun off into an independent 501(c)(3) nonprofit and renamed METR.

Texte : Wikipédia en anglais, CC BY-SA 4.0. ·

Cartes voisines

Voir la fiche

Confirmation