Dr-CiK Benchmark
Explore score history ↗Dr-CiK is a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter distractors, distill evidence, and generate forecasts. It provides context ablations and evaluates deep research and forecasting methods.
- Released
- 2026-05-27
- Institutions
- ServiceNow (United States) · McGill University · University of British Columbia
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
Dr-CiK paper
No reported scores are on record for this benchmark yet.