Webpage · 2026

SWE-bench CLI leaderboard

Snorkel AI

URLhttps://snorkel.ai/leaderboard/swe-bench-cli/
TopicsReplicHAI / Agent Evals / 02 Software engineering & coding
Tagsagent-eval, gap-sweep-2026-11

Abstract

Measures: Validated multi-file code changes in open-source repos via CLI agents. Metric: % resolved.

BibTeX

@misc{snorkel_ai_swe-bench_2026,
	title = {{SWE}-bench {CLI} leaderboard},
	url = {https://snorkel.ai/leaderboard/swe-bench-cli/},
	abstract = {Measures: Validated multi-file code changes in open-source repos via CLI agents. Metric: \% resolved.},
	author = {{Snorkel AI}},
	year = {2026},
	keywords = {agent-eval, gap-sweep-2026-11},
}