List your company

ResearchFormerly WizWand

Human Alignment Evaluation on Human Judgment Dataset

0.166Coherence RMSEAgentEval

Evaluation results

Method	Links
AgentEval2025.12		0.166	0.137	0.308	0.24	0.591	0.497	0.201	0.163	0.919	0.8
G-Eval2025.12		1.093	0.91	0.67	0.54	1.505	1.397	1.233	1.047	1.489	1.39
1-to-52025.12		1.296	0.85	0.45	0.39	1.63	1.53	1.32	1.12	1.51	1.41