Evaluations

Runs of your golden datasets against evaluation metrics.

Run evaluation

Computes real scores with real NLP — no canned results.

RunDatasetModelStatusPass rateTest casesDurationCreated
Support QA — gpt-4o regression checkCustomer Support QAgpt-4opassed100%821.81sJul 15, 09:30 PM
Enterprise Readiness — claude-sonnet-5Enterprise Readinessclaude-sonnet-5passed100%212.48sJul 13, 09:30 PM
Billing & Account — gpt-4o-miniBilling & Accountgpt-4o-minipassed100%69.33sJul 10, 09:30 PM
Support QA — claude-sonnet-5Customer Support QAclaude-sonnet-5failed13%844.82sJul 7, 09:30 PM
Support QA — gpt-4o baselineCustomer Support QAgpt-4opassed100%830.47sJul 4, 09:30 PM