{"baseline":[{"num_evals":190,"policy":"dreaming_zebra","rank":1,"score":1735,"std":42.6},{"num_evals":745,"policy":"pi05_droid","rank":2,"score":1608,"std":30.7},{"num_evals":941,"policy":"pi0_fast_droid","rank":3,"score":1582,"std":29.6},{"num_evals":952,"policy":"paligemma_vq_droid","rank":4,"score":1546,"std":29.9},{"num_evals":949,"policy":"paligemma_diffusion_droid","rank":5,"score":1533,"std":29.7},{"num_evals":1057,"policy":"paligemma_fast_specialist_droid","rank":6,"score":1531,"std":29.8},{"num_evals":1062,"policy":"paligemma_fast_droid","rank":7,"score":1516,"std":29.9},{"num_evals":1120,"policy":"pi0_droid","rank":8,"score":1461,"std":29.8},{"num_evals":629,"policy":"paligemma_binning_droid","rank":9,"score":786,"std":50.0}],"cache_stale":false,"generated_at":"2026-10-11T20:45:21.037761Z","label":"frodobots","largest_change":{"base_evals":1057,"base_rank":6,"base_score":1531,"policy":"paligemma_fast_specialist_droid","rank_delta":2,"score_delta":383,"without_evals":432,"without_rank":4,"without_score":1914},"max_abs_rank_delta":2,"max_abs_score_delta":468,"official_policy_eval_threshold":100,"source":"official Bradley-Terry Davidson leaderboard rerun on counted A/B evals","top_changes":[{"base_evals":1057,"base_rank":6,"base_score":1531,"policy":"paligemma_fast_specialist_droid","rank_delta":2,"score_delta":383,"without_evals":432,"without_rank":4,"without_score":1914},{"base_evals":949,"base_rank":5,"base_score":1533,"policy":"paligemma_diffusion_droid","rank_delta":-2,"score_delta":332,"without_evals":401,"without_rank":7,"without_score":1865},{"base_evals":941,"base_rank":3,"base_score":1582,"policy":"pi0_fast_droid","rank_delta":-2,"score_delta":315,"without_evals":404,"without_rank":5,"without_score":1897},{"base_evals":952,"base_rank":4,"base_score":1546,"policy":"paligemma_vq_droid","rank_delta":1,"score_delta":385,"without_evals":405,"without_rank":3,"without_score":1931},{"base_evals":1062,"base_rank":7,"base_score":1516,"policy":"paligemma_fast_droid","rank_delta":1,"score_delta":351,"without_evals":458,"without_rank":6,"without_score":1867},{"base_evals":629,"base_rank":9,"base_score":786,"policy":"paligemma_binning_droid","rank_delta":0,"score_delta":468,"without_evals":290,"without_rank":9,"without_score":1254},{"base_evals":745,"base_rank":2,"base_score":1608,"policy":"pi05_droid","rank_delta":0,"score_delta":387,"without_evals":242,"without_rank":2,"without_score":1995},{"base_evals":1120,"base_rank":8,"base_score":1461,"policy":"pi0_droid","rank_delta":0,"score_delta":380,"without_evals":507,"without_rank":8,"without_score":1841}],"without_org":[{"num_evals":144,"policy":"dreaming_zebra","rank":1,"score":2101,"std":10498.5},{"num_evals":242,"policy":"pi05_droid","rank":2,"score":1995,"std":10498.4},{"num_evals":405,"policy":"paligemma_vq_droid","rank":3,"score":1931,"std":10498.4},{"num_evals":432,"policy":"paligemma_fast_specialist_droid","rank":4,"score":1914,"std":10498.4},{"num_evals":404,"policy":"pi0_fast_droid","rank":5,"score":1897,"std":10498.4},{"num_evals":458,"policy":"paligemma_fast_droid","rank":6,"score":1867,"std":10498.4},{"num_evals":401,"policy":"paligemma_diffusion_droid","rank":7,"score":1865,"std":10498.4},{"num_evals":507,"policy":"pi0_droid","rank":8,"score":1841,"std":10498.4},{"num_evals":290,"policy":"paligemma_binning_droid","rank":9,"score":1254,"std":10498.5}]}