LLM Alignment

Benchmarks

Dataset Name	SOTA Method	Metric
HelpSteer (test)	PD	AlpacaEval 2 WR8.34	27	1mo ago
HH-RLHF (test)	RE-CONTROL + Prompting	Win Rate80.3	21	1mo ago
UltraFeedback (test)	PD (ours)	AlpacaEval 2 Win Rate (WR)21	18	1mo ago
HH-RLHF 300 prompts	CARDS	Win/Tie Rate vs Vanilla (GPT-4o)69.8	16	1mo ago
SHP	RE-CONTROL + Prompting	Diversity89.3	15	1mo ago
Taobao Live proprietary fine-grained preference dataset	PD (ours)	Win Score1.53	13	1mo ago
Gemma-3-4B	Nash Prox	Win Rate94.33	12	25d ago
AlpacaEval	AdaBoN	Percent Batches (BWR > 0.50)100	12	1mo ago
PKU-SafeRLHF	AdaBoN	BWR (Median)49	12	1mo ago
Alpaca, BeaverTails, and TruthfulQA (test)	AlignX	Win Rate97.1	12	1mo ago
Combined Suite Setup 3	AMA Reweighting	Average Percentage Score54.38	9	1mo ago
UltraFeedback (in-domain)	GEB-π	Win Rate (KL, alpha=1)80.6	8	1mo ago
Honesty	AlignX	Truthfulness Index84	7	1mo ago
Harmlessness	AlignX	WR87.85	7	1mo ago
Helpfulness	AlignX	Truthfulness Index0.891	7	1mo ago
Base Model Evaluation Set	AlignX	Win Rate79.93	6	1mo ago
UltraFeedback 2023 (test)	MARS	Win-rate55	4	1mo ago
PKU-SafeRLHF 2024 (test)	MARS	Win Rate0.58	4	1mo ago
Anthropic HH-RLHF 2022 (test)	MARS	Win Rate62	4	1mo ago
PKU-Safety (test)	DLMA-7B	Win Rate58	2	1mo ago
HH-Harmless (test)	DLMA-7B	Win Rate59	2	1mo ago

Showing 21 of 21 rows