List your company

Groundedness on RagTruth

0.57Kendall's TauJury-on-Demand
0.050.1850.320.455Dec 1, 2025

Evaluation results

MethodLinks
Jury-on-Demand2025.120.570.03
Gemini 2.5 FlashJudge Model=Gemini 2.5 Flash2025.120.560.03
GPT-OSS-120BJudge Model=GPT-OSS-120B2025.120.520.05
GPT-OSS-20BJudge Model=GPT-OSS-20B2025.120.510.05
Gemini 2.5 ProJudge Model=Gemini 2.5 Pro2025.120.490.05
Claude 3.7Judge Model=Claude 3.72025.120.40.06
Gemini 2.0 FlashJudge Model=Gemini 2.0 Flash2025.120.30.04
Gemma 3Judge Model=Gemma 32025.120.140.05
DeepSeek R1Judge Model=DeepSeek R12025.120.140.07
LLAMA 3.2Judge Model=LL-3.22025.120.120.05
Phi 4Judge Model=Phi 42025.120.070.09