REFUTE v2: 19-model panel · 240 judge-free MCQ axes · Truth Score v2 · generative critique + calibration (v1 retained).
BGPT
BGPT-OFFICIAL
AI & ML interests
None yet
Recent Activity
updated a Space 9 days ago
BGPT-OFFICIAL/refute-leaderboard updated a dataset 9 days ago
BGPT-OFFICIAL/refute new activity 21 days ago
BGPT-OFFICIAL/refute:Call for stress tests: try to break REFUTE (Hard-60 first)Organizations
None yet