Our current approach to assessing risks of loss of control

A proposal for better informing the public about loss-of-control risks from frontier AI development

The key questions about internal AI development the public needs more evidence about, and a concrete proposal for how developers could work with METR to produce and share that evidence.

Read the proposal
Proposed assessments

Alignment

Our proposal is to analyze a developer’s internal incidents and whether training may suppress evidence of worse misalignment.

Read

Control

Our proposal is to analyze whether a developer’s internal agents could get away with serious harm without being caught.

Read

AI R&D acceleration

Our proposal is to analyze how much AI automation is accelerating capability growth internally.

Read

Our approach to working with AI companies

How we approach working with AI companies on projects that the public might rely on to understand risks.

Previous risk assessment exercises

Frontier Risk Report
(February to March 2026)
A pilot assessment of rogue deployment risk at frontier AI companies.
Non-public information and model access provided by:
Anthropic Google DeepMind Meta OpenAI
Read report
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
Read Report

Reviews of AI developers' risk assessments

Review of the "Risks from automated R&D" section in the Anthropic Risk Report (February 2026)
May 8, 2026

External review from METR of the "Risks from automated R&D" section in Anthropic's February 2026 Risk Report
Red-Teaming Anthropic's Internal Agent Monitoring Systems
March 26, 2026

A METR staff member spent three weeks red-teaming a subset of Anthropic's internal agent monitoring and security systems, discovering several novel vulnerabilities.
Review of the Anthropic Sabotage Risk Report: Claude Opus 4.6
March 12, 2026

External review from METR of Anthropic's Sabotage Risk Report for Claude Opus 4.6
Review of the Anthropic Summer 2025 Pilot Sabotage Risk Report
October 28, 2025

External review from METR of Anthropic's Summer 2025 Sabotage Risk Report
Summary of our gpt-oss methodology review
October 23, 2025

Details on external recommendations from METR for gpt-oss Preparedness experiments and follow-up from OpenAI.

Evaluation reports

We conduct evaluations of the autonomous capabilities of frontier AI models, with some in partnership with AI developers such as Anthropic and OpenAI. We do this both to understand the models' capabilities and to pilot third-party evaluator arrangements.

Claude Opus 5.5

September 22, 2026 •
Partnership

GPT-5.6 Sol

June 26, 2026 •
Partnership

GPT-5.1-Codex-Max

November 19, 2025 •
Partnership

GPT-5

August 7, 2025 •
Partnership

OpenAI o3 and o4-mini

April 16, 2025 •
Partnership

Claude 3.7

April 4, 2025 •
Partnership

GPT-4.5

February 27, 2025 •
Partnership

Claude 3.5 Sonnet and o1

January 31, 2025 •
Partnership

Claude 3.5 Sonnet (original)

October 30, 2024 •
Partnership

o1-preview

September 12, 2024 •
Partnership

GPT-4o

August 7, 2024 •
Partnership

GPT-4 and Claude

March 17, 2023 •
Partnership

METR does not accept compensation for this work.

Companies such as OpenAI, Anthropic, and xAI have provided access and tokens, which we use for evaluations, research, and engineering. We also occasionally evaluate models independently after they are released, without involvement from the model's developers. Recent public reports resulting from this work are above, with additional discussion in the respective system cards.