{"event":{"id":"evt-hist-20260922-hle-diamond","dedupe_key":"benchmark_dataset_release:2026-09-22:hle-diamond-1000-question-benchmark-dataset-released-by-cais-and-scale-ai","event_type":"benchmark_dataset_release","title":"HLE-Diamond 1000-question benchmark dataset released by CAIS and Scale AI","summary":"Center for AI Safety and Scale AI introduced HLE-Diamond, a refined and cleaned 1,000-question subset of Humanity’s Last Exam with 500 reasoning and 500 expert-knowledge items. Scores described by benchmark publisher are snapshots conditional on evaluation setup; do not assert independence of all provider evaluations or future model rankings.","occurred_at":"2026-09-22T00:00:00.000Z","published_at":"2026-09-22T00:00:00.000Z","observed_at":"2026-10-17T20:20:00.000Z","reconstructed_at":"2026-10-17T20:20:00.000Z","ingest_type":"historical_backfill","locations":null,"status":"verified","confidence":0.92,"metadata":{"date_precision":"day","external_postcutoff_id":"2026-09-22-hle-diamond","evidence_only":1,"global_novelty_unproven":1,"new_relation_onset":0,"reported_claims_not_independently_audited":1},"created_at":"2026-10-18T05:48:50.515Z","updated_at":"2026-10-18T05:48:50.515Z"},"artifacts":[{"id":"art-hist-20260922-hle-diamond","dedupe_key":"fa2632ddbe1f8b4f8227eea266a3174908764e4570555114c307a6eec454ba8a","canonical_url":"https://lastexam.ai/blog/hle-diamond","evidence_locator":"","artifact_type":"original_publisher_publication","title":"HLE-Diamond 1000-question benchmark dataset released by CAIS and Scale AI","summary":"","creator_entities":[],"released_at":"2026-09-22T00:00:00.000Z","content_hash":null,"metadata":[],"created_at":"2026-10-18T05:48:50.514Z","updated_at":"2026-10-18T05:48:50.514Z","relation":"documented_by"}],"signals":[]}