Human Evaluation

Benchmarks

Dataset Name	SOTA Method	Metric
ESConv	KEMI	Win Rate70	36	2mo ago
VOVILLE	PAVE	Score6.18	9	14d ago
NeurIPS ICML ICLR Proposals 2025 (test)	Stepwise CoT	Wins31	6	2mo ago
CulturalVQA OOD (test)	MMBoundary	Faithfulness7.66	6	3mo ago
ScienceVQA (test)	MMBoundary	Faithfulness Score8.35	6	3mo ago
A-OKVQA (test)	MMBoundary	Faithfulness Score7.83	6	3mo ago
DeepResearch Bench 20 reports (sampled)	PTAH	Readability (Win/Tie Rate)95	5	5d ago
UltraFeedback 50 sampled questions	OTPO	Win Rate (Expert 1)62	5	3mo ago
RCC-PVD (evaluation)	Ranking	Rank Preference Rate61	4	2mo ago
Human Evaluation	Ann Brown	Trustworthiness0.86	4	3mo ago
Human Evaluation Evil Players	GRAIL Agent	Contributed Success3.78	3	1mo ago
MathQA	Ours	Accuracy89.2	3	3mo ago
50 randomly selected model responses	GPT-4.1	Clarity98	3	3mo ago
Human Evaluation Set (test)	LongDPO	Win Rate0.65	3	3mo ago
200 human-generated instructions	Olympus	Success Rate0.865	3	3mo ago
HH dataset	RRHF_DP	Win Rate59	3	3mo ago
MS MARCO (test)	RBG	Preference: FiD18	3	3mo ago
WildChat	BACO	Quality Score3.83	2	21h ago
NoveltyBench	BACO	Quality4.04	2	21h ago
Hindi spoken dialogue (test)		Naturalness4.55	2	1mo ago
K/DA and K-OMG (50 random samples)		Overall Offensiveness Score3.24	2	3mo ago
LongBench Chat	LongReward + DPO	Helpfulness Win Rate14	1	3mo ago
WMT English-Czech 2019	binmt	Preference: Much Better0.5	1	3mo ago
Tools 100 pairs	DiffLM	Win Rate88	1	3mo ago

Showing 24 of 24 rows