Webpage · 2024

SEAL Leaderboards

Scale AI

URLhttps://scale.com/leaderboard
TopicsReplicHAI / Agent Evals / 10 Harnesses, leaderboards & methodology
Tagsagent-eval

Abstract

Measures: Private expert-built leaderboards (SWE-bench Pro, MCP-Atlas, ...). Metric: Per-benchmark.

BibTeX

@misc{scale_ai_seal_2024,
	title = {{SEAL} {Leaderboards}},
	url = {https://scale.com/leaderboard},
	abstract = {Measures: Private expert-built leaderboards (SWE-bench Pro, MCP-Atlas, ...). Metric: Per-benchmark.},
	author = {{Scale AI}},
	year = {2024},
	keywords = {agent-eval},
}