Runs of your golden datasets against evaluation metrics.
Computes real scores with real NLP — no canned results.
| Run | Dataset | Model | Status | Pass rate | Test cases | Duration | Created |
|---|---|---|---|---|---|---|---|
| Support QA — gpt-4o regression check | Customer Support QA | gpt-4o | passed | 100% | 8 | 21.81s | Jul 15, 09:30 PM |
| Enterprise Readiness — claude-sonnet-5 | Enterprise Readiness | claude-sonnet-5 | passed | 100% | 2 | 12.48s | Jul 13, 09:30 PM |
| Billing & Account — gpt-4o-mini | Billing & Account | gpt-4o-mini | passed | 100% | 6 | 9.33s | Jul 10, 09:30 PM |
| Support QA — claude-sonnet-5 | Customer Support QA | claude-sonnet-5 | failed | 13% | 8 | 44.82s | Jul 7, 09:30 PM |
| Support QA — gpt-4o baseline | Customer Support QA | gpt-4o | passed | 100% | 8 | 30.47s | Jul 4, 09:30 PM |