Truverai reads the communication, scores 32 sub-metrics grouped into eight metrics, and reports a composite out of 100. Quoted material is excluded, and non-speaker content is removed first.
Each evaluation is run three times and the median run is published, so a single unusual run cannot become the result.
Truverai scores are reproducible within a published lock: engine v4.7, prompt hash 1a6c25c7e25ddbf8, model google/gemini-3-flash-preview at temperature 0, and a median of three runs. That is reproducibility within a fixed configuration, not a claim that a different language model would return the same number.
Truverai evaluates how a communication is presented, not whether a belief is objectively true, and it scores what was said rather than who said it. Plan and payment tier do not affect scoring: anonymous, free, and paid evaluations run the identical path.
This page needs JavaScript for the full interactive view. The summary above is the same information in plain HTML.