UAB
Home/Trust/Simulator
Simulator
Confidence simulator

Stress-test the ranking.

See how the leader changes when provider-official, stale, relay, or backfilled evidence is excluded.
Scenarios · 5
API · /api/confidence-simulator?preset=everyday-chatbot
ScenarioLeaderScoreConfidenceTop model IDs
All public evidenceclaude-fable-5-high100high_confidenceclaude-fable-5-high, claude-opus-4-6-high, claude-opus-5-5-xhigh, claude-opus-5-5-high
Exclude provider-official dataclaude-fable-5-high100high_confidenceclaude-fable-5-high, claude-opus-4-6-high, claude-opus-5-5-xhigh, claude-opus-5-5-high
Exclude stale dataclaude-fable-5-high100high_confidenceclaude-fable-5-high, claude-opus-4-6-high, claude-opus-5-5-xhigh, claude-opus-5-5-high
Exclude relay sourcesclaude-fable-5-high100high_confidenceclaude-fable-5-high, claude-opus-4-6-high, claude-opus-5-5-xhigh, claude-opus-5-5-high
Exclude backfilled rowsclaude-fable-5-high100high_confidenceclaude-fable-5-high, claude-opus-4-6-high, claude-opus-5-5-xhigh, claude-opus-5-5-high