Evaluations
1 agent · 0 evaluators · Opus 4.7 judge · 100% sampling · last 7 days
| Self-Improvement Loop | ||
| All Settings | ||
Updated: —Scores: ≥90% · ≥75% · <75%
1 agent · 0 evaluators · Opus 4.7 judge · 100% sampling · last 7 days
| Self-Improvement Loop | ||
| All Settings | ||