{"event":{"id":"evt-20261103-gdpx","dedupe_key":"rts_milestone:rts_finding_ec54ee13f38c4fd9961c4ac34d11461f","event_type":"publication_or_official_action","title":"SemiAnalysis publishes GDPx benchmark for 206 advanced agent tasks in 11 professional domains","summary":"SemiAnalysis published GDPx v1.0 on 2 November 2026, with 206 benchmark tasks in 11 high-value professional domains. The publicly reported aggregate scores include Claude Opus 5.5 12.0, Gemini 4 Carbon 10.9 and GPT-6 Astra 9.6 under the publisher's task/grading design. These are benchmark-specific scores and publisher observations, not reliable percentages of real-world work completed or a demonstration of recursive model self-improvement. Independent reproduction and grader scrutiny remain open.","occurred_at":"2026-11-02T00:00:00.000Z","published_at":"2026-11-02T00:00:00.000Z","observed_at":"2026-11-03T05:57:37.565Z","reconstructed_at":null,"ingest_type":"live_evidence_only","locations":null,"status":"verified","confidence":0.93,"metadata":{"rts_finding_id":"rts_finding_ec54ee13f38c4fd9961c4ac34d11461f","epistemic_scope":"dated_publication_or_official_statement_only","source_bound":1,"evidence_only":1,"no_relation_onset":1,"no_civilization_snapshot":1,"global_novelty_not_exhaustively_proven":1,"original_occurrence_date_preserved":1},"created_at":"2026-11-03T06:24:56.576Z","updated_at":"2026-11-03T06:24:56.576Z"},"artifacts":[{"id":"art-20261103-gdpx","dedupe_key":"12250048d16898c04199a0ba58aed682b0f7f482b73a2f6a67035bde06c19c39","canonical_url":null,"evidence_locator":"","artifact_type":"publication","title":"SemiAnalysis publishes GDPx benchmark for 206 advanced agent tasks in 11 professional domains","summary":"SemiAnalysis published GDPx v1.0 on 2 November 2026, with 206 benchmark tasks in 11 high-value professional domains. The publicly reported aggregate scores include Claude Opus 5.5 12.0, Gemini 4 Carbon 10.9 and GPT-6 Astra 9.6 under the publisher's task/grading design. These are benchmark-specific scores and publisher observations, not reliable percentages of real-world work completed or a demonstration of recursive model self-improvement. Independent reproduction and grader scrutiny remain open.","creator_entities":[],"released_at":"2026-11-02T00:00:00.000Z","content_hash":null,"metadata":{"rts_finding_id":"rts_finding_ec54ee13f38c4fd9961c4ac34d11461f","epistemic_scope":"dated_publication_or_official_statement_only","source_bound":1,"evidence_only":1,"no_relation_onset":1,"no_civilization_snapshot":1,"global_novelty_not_exhaustively_proven":1,"original_occurrence_date_preserved":1},"created_at":"2026-11-03T06:24:56.571Z","updated_at":"2026-11-03T06:24:56.571Z","relation":"documents"}],"signals":[]}