Interactive dashboard to the empirical chapter. Every bar, every cell, every comparison rests on the same 132-response dataset: 11 models tested against 3 false narratives under 4 prompt personas. Filter, hover, explore.
Fail = repeated false info OR declined to respond. Worst at top, best at bottom. Among models tied at 8.3%, Copilot is sorted last because all of its failures are declines, not repetitions of the lie.
Green = debunk (passed). Red = repeated false info (fail). Amber = declined to respond (fail). Together red and amber make the fail rate.
Failures out of 3 claims per model × persona. Darker = more failures.
Three claims side-by-side. Bournazel (red) is the fresh, under-debunked one.
All three false claims are part of the Storm-1516 influence operation. A model that correctly names Russia, propaganda, or Storm-1516 has identified the operation, not just the content. This chart counts those textual mentions (Excel column F).
Left: overall fail rate across audits. Right: fail rate by persona (Expert excluded for comparability with NewsGuard's 3-persona design).