Spaces:

lovodkin93
/

FuseReviews-Leaderboard

Sleeping

FuseReviews-Leaderboard / FuseReviews_leaderboard.tsv

Upload FuseReviews_leaderboard.tsv

66660ac verified 12 months ago

116 Bytes

	Model Faithfulness Coverage F-1
	Flan-T5-Large 72.8 86.4 79
	Flan-T5-Large (Quark) 54 82 65.1
	GPT-4 81.6 85.6 83.6