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 ★

Comum · Organizações

METR

AI model evaluation nonprofit

Texto em inglês

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.

Último preço

—

Preço mínimo

—

Mediana 7 d

—

Vendas 30 d

0

Faixa 30 d

—

Em circulação

0

Cotação

Ver tabela
Datamediana MínMáxvendas

Histórico de vendas

Última venda
—
Média 30 d
—
Mínima 30 d
—
Máxima 30 d
—
Vendas 7 d
0
Vendas 30 d
0

Ainda sem vendas.

Vendas anônimas: sem comprador nem vendedor. Os números contam só vendas entre jogadores.

Na Wikipédia

Texto em inglês Ainda não há artigo no seu idioma: trecho em inglês.

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.

Texto: Wikipédia em inglês, CC BY-SA 4.0. ·

Cartas próximas

Ver a ficha

Confirmação