Computer program · 2024

Inspect Evals

UK AISI and contributors

URLhttps://github.com/UKGovernmentBEIS/inspect_evals
TopicsReplicHAI / Agent Evals / 10 Harnesses, leaderboards & methodology
Tagsagent-eval

Abstract

Measures: Community implementations of many agent benchmarks. Metric: -.

BibTeX

@misc{uk_aisi_and_contributors_inspect_2024,
	title = {Inspect {Evals}},
	url = {https://github.com/UKGovernmentBEIS/inspect_evals},
	abstract = {Measures: Community implementations of many agent benchmarks. Metric: -.},
	author = {{UK AISI and contributors}},
	year = {2024},
	keywords = {agent-eval},
}