{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "name": "agent-ml-platform — evals",
  "dateModified": "2026-06-11T16:13:18.220Z",
  "eval_sets": 412,
  "golden_datasets": 184,
  "llm_as_judge": "GPT-5 + Claude 4.5 + Gemini 3 Pro",
  "human_label_pct": 18,
  "ragas_avg": 0.92,
  "safety_pass_pct": 99.6
}