Computer program · 2024
METR Task Standard
| URL | https://github.com/METR/task-standard |
|---|---|
| Topics | ReplicHAI / Agent Evals / 10 Harnesses, leaderboards & methodology |
| Tags | agent-eval, gap-sweep-2026-11 |
Abstract
Measures: Portable format for defining agent evaluation tasks. Metric: -.
BibTeX
@misc{metr_metr_2024,
title = {{METR} {Task} {Standard}},
url = {https://github.com/METR/task-standard},
abstract = {Measures: Portable format for defining agent evaluation tasks. Metric: -.},
author = {{METR}},
year = {2024},
keywords = {agent-eval, gap-sweep-2026-11},
}