Skip to main content

Wandbot AutoEval Plots

Created on January 18|Last edited on January 18


Model Comparison


Model Comparison RadarPlot
Answer CorrectnessAnswer FaithfulnessAnswer RelevancyContext PrecisionContext RecallRAGAS Answer Correctness ScoreRAGAS Answer Faithfulness ScoreRAGAS Answer Relevancy ScoreRAGAS Answer Similarity Score00.20.40.60.81
gpt-3.5-turbo-16k-0613gpt-4-0613gpt-4-1106-previewgpt-4-1106-preview-v1.1






Answer Correctness

















Answer Relevancy
















Answer Faithfulness
















Context Precision







Context Recall







Model Latency