List your company

Ranking Stability Analysis on SimpleQA and 4 Hallucination Benchmarks

0.9Kendall's WF-score
-0.0360.2070.450.693Oct 2, 2025

Evaluation results

MethodLinks
F-scoreevaluation_setting=Default2025.100.90
Correct Answer Rateevaluation_setting=Default2025.100.870
Weightedevaluation_setting=Default2025.100.870.33
Refusal Rateevaluation_setting=Default2025.100.860.18
C / Aevaluation_setting=Default2025.100.690.33
C / Aevaluation_setting=-Correct2025.100.630.61
Weightedevaluation_setting=-Correct2025.100.60.33
RIevaluation_setting=-Correct2025.100.50.33
RIevaluation_setting=-Both2025.100.490.37
Correct Answer Rateevaluation_setting=-Refusal2025.100.480.48
F-scoreevaluation_setting=-Refusal2025.100.480.48
RIevaluation_setting=Default2025.100.470.47
Refusal Rateevaluation_setting=-Correct2025.100.440.61
C / Aevaluation_setting=-Refusal2025.100.40.48
Correct Answer Rateevaluation_setting=-Both2025.100.391
F-scoreevaluation_setting=-Both2025.100.390.52
C / Aevaluation_setting=-Both2025.100.370.61
RIevaluation_setting=-Refusal2025.100.350.61
Weightedevaluation_setting=-Both2025.100.320.61
Refusal Rateevaluation_setting=-Both2025.100.31
Random Valueevaluation_setting=Default2025.100.250.61
Random Valueevaluation_setting=-Correct2025.100.250.61
Random Valueevaluation_setting=-Refusal2025.100.250.61
Random Valueevaluation_setting=-Both2025.100.250.61
Weightedevaluation_setting=-Refusal2025.100.250.37
F-scoreevaluation_setting=-Correct2025.100.10.18
Correct Answer Rateevaluation_setting=-Correct2025.1001
Refusal Rateevaluation_setting=-Refusal2025.1001