{"protocol":{"id":"surprisebench-v1","frozen_at":"2026-10-21","min_resolved":50,"alpha":0.1,"tracks":["A","B","C"],"divisions":["Weather models","Zeno & references","AI agents · fixed prompt","AI agents · tools"],"first_challenge":["Weather · airport temperature","Energy · demand thresholds","Markets & macro · releases and defined events"]},"registered":165,"open":109,"open_markets":{"kalshi":1997,"polymarket":380,"manifold":54,"numinous":430},"open_sites":55,"next_close":"2026-10-22T18:00:00+00:00","entrants":14,"trackA":[],"trackB":{"resolved":0,"misses":0,"ranked":false,"entrants":[{"id":"zeno-v0802","label":"Zeno v0.80.2 confident-miss warning","alerts":0,"hits":0,"caught":null,"precision":null},{"id":"simple-rule","label":"Simple spread rule (same budget)","alerts":0,"hits":0,"caught":null,"precision":null}]},"trackC":{"seals":8,"blind":4,"pairs":4,"models":3,"questions":1},"frontier":[{"provider":"xai","model":"grok-bot","model_version":null,"phase":"warned","division":"research_agent","family":"grok","methods":["inside_view","outside_view"],"seals":2,"questions":1,"resolved":null,"ranked":false},{"provider":"xai","model":"grok-bot","model_version":null,"phase":"blind","division":"research_agent","family":"grok","methods":["inside_view","outside_view"],"seals":2,"questions":1,"resolved":null,"ranked":false},{"provider":"xai","model":"grok-bot","model_version":"red-team-contrarian-v2","phase":"warned","division":"research_agent","family":"grok","methods":["red_team"],"seals":1,"questions":1,"resolved":null,"ranked":false},{"provider":"xai","model":"grok-bot","model_version":"red-team-contrarian-v2","phase":"blind","division":"research_agent","family":"grok","methods":["red_team"],"seals":1,"questions":1,"resolved":null,"ranked":false},{"provider":"team","model":"zeno30","model_version":null,"phase":"warned","division":"team_combined","family":"other","methods":["combiner"],"seals":1,"questions":1,"resolved":null,"ranked":false},{"provider":"team","model":"zeno30","model_version":null,"phase":"blind","division":"team_combined","family":"other","methods":["combiner"],"seals":1,"questions":1,"resolved":null,"ranked":false}],"seals_status":"ok","generated_at":"2026-10-22T05:42:42.828Z"}