Hallucination rate
8.7%
-1.2 ptsvs last week
Faithfulness score
87
+0.8vs last week
Tests run
12,340
+218 this week
Critical fails
6
+1 this week
Hallucination rate over time
Lower is better · last 7 days
Model A
Model B
Model C
By domain
This week's faithfulness
Medical12 runs
91
Legal8 runs
64
Finance15 runs
82
General23 runs
88
Recent runs
12 runs · click any row for details
| Suite | Model | Metric | Score | Trend | Status | When |
|---|---|---|---|---|---|---|
Medical · drug interactions 218 cases · run-001 | Model B | Faithfulness | 94 | Pass | 2 min ago | |
Legal · contract clauses 156 cases · run-002 | Model A | Factual consistency | 87 | Pass | 14 min ago | |
Finance · earnings Q&A 412 cases · run-003 | Model A | Hallucination rate | 71 | Warning | 38 min ago | |
Medical · symptom triage 98 cases · run-004 | Model C | Answer relevance | 64 | Warning | 1h ago | |
General · world facts (v3) 600 cases · run-005 | Model B | Citation accuracy | 91 | Pass | 1h ago | |
Legal · case-law lookup 240 cases · run-006 | Model C | Faithfulness | 38 | Fail | 2h ago | |
Finance · 10-K summarization 312 cases · run-007 | Model A | Faithfulness | 82 | Pass | 3h ago | |
Medical · dosage calculation 84 cases · run-008 | Model B | Factual consistency | 96 | Pass | 4h ago | |
General · trivia (long-tail) 1,024 cases · run-009 | Model C | Hallucination rate | 52 | Warning | 5h ago | |
Legal · GDPR compliance 178 cases · run-010 | Model A | Citation accuracy | 89 | Pass | 6h ago | |
Finance · risk disclosures 290 cases · run-011 | Model B | Answer relevance | — | Running | running | |
Medical · patient education 144 cases · run-012 | Model C | Faithfulness | 33 | Fail | yesterday |