List your company

ResearchFormerly WizWand

Tracing

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

TOFU, ChatDoctor, Beavertails, TruthfulQA, WMDP Macro Average

98.57TSR

10

Mar 19, 2026

100TSR

10

Mar 19, 2026

TruthfulQA (test)

96.34Truthfulness Score Rate (TSR)

10

Mar 19, 2026

Beavertails (test)

99.29Tracing Success Rate (TSR)

10

Mar 19, 2026

ChatDoctor (test)

99.75TSR

10

Mar 19, 2026

99.87TSR

10

Mar 19, 2026