Quality eval
Set up criteria, run judge-based scoring, and review results.
This is a preview with sample runs. Sign up to run evals on your own calls. →
| Run | Avg score | Status | Date |
|---|---|---|---|
Auto quality scan openai/gpt-4o-mini | 4.20 | Completed | 2026-06-23 13:50 |
accuracy regression check openai/gpt-4o-mini | 3.80 | Completed | 2026-06-22 09:14 |
tone & safety sweep anthropic/claude-haiku-4-5 | 4.60 | Completed | 2026-06-21 18:02 |
golden dataset v3 openai/gpt-4o-mini | 5.00 | Completed | 2026-06-19 11:30 |
nightly baseline openai/gpt-4o-mini | — | Failed | 2026-06-18 03:00 |