Agents
METR Time Horizon
A capability metric from METR that describes what an AI system can do in human terms: the length of task, measured by how long skilled humans take to do it, that a model completes with 50% success.
In depth
A capability metric from METR that describes what an AI system can do in human terms: the length of task, measured by how long skilled humans take to do it, that a model completes with 50% success. METR timed experts on software and research tasks, then fit each model's success rate against task length. The original 2025 paper put Claude 3.7 Sonnet at about 50 minutes and found the frontier horizon doubling roughly every seven months since 2019. METR keeps measuring new models, and the number is widely used as a proxy for autonomous agent capability.
Primary source: arxiv.org
Example
In practice, developers reach for METR Time Horizon when they need the capability described above as part of an AI feature or workflow.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover Agents.
FAQ
Common questions
What is METR Time Horizon?
A capability metric from METR that describes what an AI system can do in human terms: the length of task, measured by how long skilled humans take to do it, that a model completes with 50% success.
Why does METR Time Horizon matter for AI developers?
METR Time Horizon sits in the Agents part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about METR Time Horizon?
Developers Digest publishes tutorials and videos that cover Agents topics including METR Time Horizon. Check the blog and YouTube channel for hands-on walkthroughs.
Related
Related terms
Agents
Long-Horizon Tasks
Tasks that take an agent many steps and a long time to finish, measured in hours of equivalent human work rather than one prompt and reply.
Agents
Eval Harness
The infrastructure that runs evals end to end: it feeds tasks to the model or agent, records every step, applies graders, and aggregates the results into scores.
Agents
OSWorld
A benchmark that runs multimodal agents inside real virtual machines and asks them to complete open-ended computer tasks across desktop apps, file operations, and multi-app workflows.
Put this concept to work
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever