data/evaluation/initial/evaluation_results_average.json

{
  "context_recall": 0.8069444444,
  "faithfulness": 0.9318181818,
  "factual_correctness": 0.373,
  "answer_relevancy": 0.9581163434,
  "context_entity_recall": 0.3598076345,
  "noise_sensitivity_relevant": 0.3017243635
}