analyzer_b/results/benchmark_runs.csv

timestamp,version,blueprint,page,gt_count,pred_count,tp,fp,fn,precision,recall,f1,tag_acc,count_acc,box_iou_f1,tag_mismatch,trusted_n,flagged_n,review_rate,conf_fp,conf_prec,page_workers,tile_workers,dpi,tile_size,runs,consensus,fp_filter,schedule_sec,classify_sec,detect_sec,invoke_sec,api_calls,cost_usd
2026-06-19T09:24:32,v02_tiles4,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.64,0,12,0,0.0,0,1.0,1,4,300,3000,1,1,True,0.0,0.0,941.68,,,
2026-06-19T09:24:32,v02_tiles4,355,13,9,10,4,6,5,0.4,0.4444,0.4211,1.0,0.8889,0.4211,0,10,0,0.0,6,0.4,1,4,300,3000,1,1,True,0.0,0.0,941.68,,,
2026-06-19T09:36:41,v03_tiles8,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.72,0,12,0,0.0,0,1.0,1,8,300,3000,1,1,True,0.0,0.0,288.1,,,
2026-06-19T09:36:41,v03_tiles8,355,13,9,10,5,5,4,0.5,0.5556,0.5263,1.0,0.8889,0.5263,0,10,0,0.0,5,0.5,1,8,300,3000,1,1,True,0.0,0.0,288.1,,,
2026-06-19T09:44:21,v03_tiles8,dean,4,25,21,20,1,5,0.9524,0.8,0.8696,1.0,0.84,0.8261,0,21,0,0.0,1,0.9524,1,8,300,3000,1,1,True,0.0,0.0,345.3,,,
2026-06-19T09:44:21,v03_tiles8,dean,6,66,33,31,2,35,0.9394,0.4697,0.6263,0.9677,0.5,0.5657,1,33,0,0.0,2,0.9394,1,8,300,3000,1,1,True,0.0,0.0,345.3,,,
2026-06-21T07:58:00,v10_best,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.56,0,11,1,0.0833,0,1.0,1,12,300,1800,2,2,False,0.0,0.0,718.97,,627,1.3379
2026-06-21T07:58:00,v10_best,355,13,9,15,8,7,1,0.5333,0.8889,0.6667,0.875,0.3333,0.5,1,9,6,0.4,3,0.6667,1,12,300,1800,2,2,False,0.0,0.0,718.97,,627,1.3379
2026-06-21T08:07:47,v10_best,dean,4,25,25,24,1,1,0.96,0.96,0.96,1.0,1.0,0.96,0,23,2,0.08,0,1.0,1,12,300,1800,2,2,False,0.0,0.0,583.66,,628,1.7958
2026-06-21T08:07:47,v10_best,dean,6,66,64,61,3,5,0.9531,0.9242,0.9385,0.9344,0.9697,0.9385,4,62,2,0.0312,1,0.9839,1,12,300,1800,2,2,False,0.0,0.0,583.66,,628,1.7958
2026-06-19T10:26:18,v13_recall,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.48,0,12,0,0.0,0,1.0,1,12,300,1800,2,1,True,0.0,0.0,190.94,,,
2026-06-19T10:26:18,v13_recall,355,13,9,9,7,2,2,0.7778,0.7778,0.7778,1.0,1.0,0.7778,0,9,0,0.0,2,0.7778,1,12,300,1800,2,1,True,0.0,0.0,190.94,,,
2026-06-19T10:22:23,v13_recall,dean,4,25,23,23,0,2,1.0,0.92,0.9583,1.0,0.92,0.9583,0,23,0,0.0,0,1.0,1,12,300,1800,2,1,True,0.0,0.0,244.46,,,
2026-06-19T10:22:23,v13_recall,dean,6,66,53,53,0,13,1.0,0.803,0.8908,0.9811,0.803,0.8739,1,53,0,0.0,0,1.0,1,12,300,1800,2,1,True,0.0,0.0,244.46,,,
2026-06-19T10:41:02,v14_recall_max,dean,4,25,22,22,0,3,1.0,0.88,0.9362,1.0,0.88,0.9362,0,22,0,0.0,0,1.0,1,12,300,1800,3,1,True,0.0,0.0,269.87,,,
2026-06-19T10:41:02,v14_recall_max,dean,6,66,58,57,1,9,0.9828,0.8636,0.9194,0.9649,0.8788,0.9032,2,58,0,0.0,1,0.9828,1,12,300,1800,3,1,True,0.0,0.0,269.87,,,
2026-06-19T12:02:36,v17_ultra,dean,4,25,23,23,0,2,1.0,0.92,0.9583,1.0,0.92,0.9583,0,23,0,0.0,0,1.0,1,16,300,1500,3,2,True,0.0,0.0,751.42,,,
2026-06-19T12:02:36,v17_ultra,dean,6,66,55,54,1,12,0.9818,0.8182,0.8926,0.9444,0.8333,0.843,3,55,0,0.0,1,0.9818,1,16,300,1500,3,2,True,0.0,0.0,751.42,,,
2026-06-19T13:53:01,v19_maxrecall,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.56,0,12,0,0.0,0,1.0,1,12,300,1800,3,1,False,0.0,0.0,288.82,,,
2026-06-19T13:53:01,v19_maxrecall,355,13,9,13,8,5,1,0.6154,0.8889,0.7273,1.0,0.5556,0.5455,0,4,9,0.6923,0,1.0,1,12,300,1800,3,1,False,0.0,0.0,288.82,,,
2026-06-19T13:41:37,v19_maxrecall,dean,4,25,22,22,0,3,1.0,0.88,0.9362,1.0,0.88,0.9362,0,22,0,0.0,0,1.0,1,12,300,1800,3,1,False,0.0,0.0,267.77,,,
2026-06-19T13:41:37,v19_maxrecall,dean,6,66,59,57,2,9,0.9661,0.8636,0.912,0.9649,0.8939,0.912,2,57,2,0.0339,1,0.9825,1,12,300,1800,3,1,False,0.0,0.0,267.77,,,
2026-06-19T12:18:35,v21_or_maxrecall,dean,4,25,9,8,1,17,0.8889,0.32,0.4706,1.0,0.36,0.4706,0,9,0,0.0,1,0.8889,1,8,300,1800,3,1,False,0.0,0.0,211.72,,,
2026-06-19T12:18:35,v21_or_maxrecall,dean,6,66,39,37,2,29,0.9487,0.5606,0.7048,1.0,0.5909,0.7048,0,29,10,0.2564,0,1.0,1,8,300,1800,3,1,False,0.0,0.0,211.72,,,
2026-06-19T13:03:02,v22_or_g35,dean,4,25,13,13,0,12,1.0,0.52,0.6842,1.0,0.52,0.6842,0,13,0,0.0,0,1.0,1,8,300,1800,3,1,False,0.0,0.0,405.53,,,
2026-06-19T13:03:02,v22_or_g35,dean,6,66,45,44,1,22,0.9778,0.6667,0.7928,0.9773,0.6818,0.7928,1,33,12,0.2667,0,1.0,1,8,300,1800,3,1,False,0.0,0.0,405.53,,,
2026-06-19T12:55:26,v23_or_think,dean,4,25,9,9,0,16,1.0,0.36,0.5294,1.0,0.36,0.4706,0,9,0,0.0,0,1.0,1,8,300,1800,3,1,False,0.0,0.0,609.64,,,
2026-06-19T12:55:26,v23_or_think,dean,6,66,35,35,0,31,1.0,0.5303,0.6931,0.9714,0.5303,0.6931,1,35,0,0.0,0,1.0,1,8,300,1800,3,1,False,0.0,0.0,609.64,,,
2026-06-19T13:47:34,v25_max_direct,dean,4,25,23,23,0,2,1.0,0.92,0.9583,1.0,0.92,0.9583,0,23,0,0.0,0,1.0,1,12,300,1800,3,1,False,0.0,0.0,306.92,,,
2026-06-19T13:47:34,v25_max_direct,dean,6,66,41,41,0,25,1.0,0.6212,0.7664,0.9268,0.6212,0.7664,3,39,2,0.0488,0,1.0,1,12,300,1800,3,1,False,0.0,0.0,306.92,,,
2026-06-19T15:01:21,v26_consensus,dean,4,25,24,24,0,1,1.0,0.96,0.9796,1.0,0.96,0.9796,0,23,1,0.0417,0,1.0,1,12,300,1800,2,2,False,0.0,0.0,483.74,,,
2026-06-19T15:01:21,v26_consensus,dean,6,66,64,62,2,4,0.9688,0.9394,0.9538,0.9355,0.9697,0.9538,4,63,1,0.0156,1,0.9841,1,12,300,1800,2,2,False,0.0,0.0,483.74,,,
2026-06-19T16:18:49,v27_consensus3,dean,4,25,26,24,2,1,0.9231,0.96,0.9412,1.0,0.96,0.9412,0,24,2,0.0769,0,1.0,1,12,300,1800,2,3,False,0.0,0.0,2489.85,,,
2026-06-19T16:18:49,v27_consensus3,dean,6,66,65,62,3,4,0.9538,0.9394,0.9466,0.9355,0.9848,0.9466,4,63,2,0.0308,1,0.9841,1,12,300,1800,2,3,False,0.0,0.0,2489.85,,,
2026-06-19T17:37:00,v28_adaptive,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.56,0,12,0,0.0,0,1.0,1,12,300,1800,2,2,False,0.0,0.0,599.28,,,
2026-06-19T17:37:00,v28_adaptive,355,13,9,18,9,9,0,0.5,1.0,0.6667,0.8889,0.0,0.5926,1,8,10,0.5556,2,0.75,1,12,300,1800,2,2,False,0.0,0.0,599.28,,,
2026-06-19T17:55:06,v28_adaptive,dean,4,25,25,24,1,1,0.96,0.96,0.96,1.0,1.0,0.96,0,23,2,0.08,0,1.0,1,12,300,1800,2,2,False,0.0,0.0,1083.57,,,
2026-06-19T17:55:06,v28_adaptive,dean,6,66,62,60,2,6,0.9677,0.9091,0.9375,0.9333,0.9394,0.9375,4,61,1,0.0161,1,0.9836,1,12,300,1800,2,2,False,0.0,0.0,1083.57,,,
2026-06-19T18:05:16,v29_mergefix,dean,4,25,25,24,1,1,0.96,0.96,0.96,1.0,1.0,0.96,0,23,2,0.08,0,1.0,1,12,300,1800,2,2,False,0.0,0.0,530.1,,,
2026-06-19T18:05:16,v29_mergefix,dean,6,66,63,61,2,5,0.9683,0.9242,0.9457,0.9344,0.9545,0.9457,4,62,1,0.0159,1,0.9839,1,12,300,1800,2,2,False,0.0,0.0,530.1,,,
2026-06-21T08:15:03,v30_runs1,355,2,13,13,13,0,0,1.0,1.0,1.0,0.9231,1.0,0.6154,1,12,1,0.0769,0,1.0,1,12,300,1800,1,2,False,0.0,0.0,433.28,,322,0.6635
2026-06-21T08:15:03,v30_runs1,355,13,9,14,8,6,1,0.5714,0.8889,0.6957,1.0,0.4444,0.6087,0,8,6,0.4286,2,0.75,1,12,300,1800,1,2,False,0.0,0.0,433.28,,322,0.6635
2026-06-21T08:20:56,v30_runs1,dean,4,25,24,24,0,1,1.0,0.96,0.9796,1.0,0.96,0.9796,0,23,1,0.0417,0,1.0,1,12,300,1800,1,2,False,0.0,0.0,349.09,,323,0.9144
2026-06-21T08:20:56,v30_runs1,dean,6,66,64,62,2,4,0.9688,0.9394,0.9538,0.9355,0.9697,0.9538,4,62,2,0.0312,1,0.9839,1,12,300,1800,1,2,False,0.0,0.0,349.09,,323,0.9144
2026-06-21T09:09:47,v32_adaptive_prescan,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.56,0,12,0,0.0,0,1.0,1,12,300,1800,1,2,False,0.0,0.0,513.92,,361,0.7745
2026-06-21T09:09:47,v32_adaptive_prescan,355,13,9,16,8,8,1,0.5,0.8889,0.64,1.0,0.2222,0.48,0,8,8,0.5,2,0.75,1,12,300,1800,1,2,False,0.0,0.0,513.92,,361,0.7745
2026-06-21T09:17:18,v32_adaptive_prescan,dean,4,25,26,24,2,1,0.9231,0.96,0.9412,1.0,0.96,0.902,0,23,3,0.1154,0,1.0,1,12,300,1800,1,2,False,0.0,0.0,448.85,,376,1.0887
2026-06-21T09:17:18,v32_adaptive_prescan,dean,6,66,64,61,3,5,0.9531,0.9242,0.9385,0.9344,0.9697,0.9385,4,62,2,0.0312,1,0.9839,1,12,300,1800,1,2,False,0.0,0.0,448.85,,376,1.0887
2026-06-21T09:27:42,v40_or_gpt4o_mini,dean,4,25,16,14,2,11,0.875,0.56,0.6829,1.0,0.64,0.6829,0,13,3,0.1875,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,321.87,,0,0.0
2026-06-21T09:27:42,v40_or_gpt4o_mini,dean,6,66,33,32,1,34,0.9697,0.4848,0.6465,0.9375,0.5,0.6465,2,33,0,0.0,1,0.9697,1,8,300,1800,1,2,False,0.0,0.0,321.87,,0,0.0
2026-06-21T15:06:23,v41_or_flash_lite,355,2,13,9,9,0,4,1.0,0.6923,0.8182,1.0,0.6923,0.2727,0,8,1,0.1111,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,420.59,,292,0.1023
2026-06-21T15:06:23,v41_or_flash_lite,355,13,9,9,6,3,3,0.6667,0.6667,0.6667,1.0,1.0,0.5556,0,6,3,0.3333,1,0.8333,1,8,300,1800,1,2,False,0.0,0.0,420.59,,292,0.1023
2026-06-21T15:14:40,v41_or_flash_lite,dean,4,25,22,22,0,3,1.0,0.88,0.9362,1.0,0.88,0.9362,0,21,1,0.0455,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,494.7,,292,0.1098
2026-06-21T15:14:40,v41_or_flash_lite,dean,6,66,55,51,4,15,0.9273,0.7727,0.843,0.9216,0.8333,0.843,4,52,3,0.0545,1,0.9808,1,8,300,1800,1,2,False,0.0,0.0,494.7,,292,0.1098
2026-06-21T10:31:22,v44_or_nemotron_omni,355,2,13,1,1,0,12,1.0,0.0769,0.1429,1.0,0.0769,0.0,0,0,1,1.0,0,1.0,1,6,300,1800,1,2,False,0.0,0.0,160.87,,54,0.0
2026-06-21T10:34:04,v44_or_nemotron_omni,dean,6,66,1,1,0,65,1.0,0.0152,0.0299,1.0,0.0152,0.0299,0,0,1,1.0,0,1.0,1,6,300,1800,1,2,False,0.0,0.0,156.96,,56,0.0
2026-06-21T10:51:31,v45_or_nova_lite,355,2,13,33,12,21,1,0.3636,0.9231,0.5217,0.75,0.0,0.2609,3,9,24,0.7273,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,1040.88,,146,0.0321
2026-06-21T11:04:04,v45_or_nova_lite,dean,6,66,82,45,37,21,0.5488,0.6818,0.6081,0.9556,0.7576,0.5946,2,45,37,0.4512,1,0.9778,1,8,300,1800,1,2,False,0.0,0.0,748.74,,146,0.035
2026-06-21T11:17:50,v46_or_gemma3_27b,355,2,13,11,8,3,5,0.7273,0.6154,0.6667,1.0,0.8462,0.1667,0,7,4,0.3636,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,468.86,,146,0.0112
2026-06-21T11:29:52,v46_or_gemma3_27b,dean,6,66,87,46,41,20,0.5287,0.697,0.6013,0.9565,0.6818,0.5882,2,40,47,0.5402,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,718.73,,146,0.0136
2026-06-21T14:55:07,v47_or_qwen3vl_32b,355,2,13,9,9,0,4,1.0,0.6923,0.8182,1.0,0.6923,0.3636,0,9,0,0.0,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,225.41,,258,0.0858
2026-06-21T14:55:07,v47_or_qwen3vl_32b,355,13,9,10,7,3,2,0.7,0.7778,0.7368,1.0,0.8889,0.6316,0,8,2,0.2,1,0.875,1,8,300,1800,1,2,False,0.0,0.0,225.41,,258,0.0858
2026-06-21T14:59:21,v47_or_qwen3vl_32b,dean,4,25,21,20,1,5,0.9524,0.8,0.8696,1.0,0.84,0.8261,0,21,0,0.0,1,0.9524,1,8,300,1800,1,2,False,0.0,0.0,251.78,,280,0.1023
2026-06-21T14:59:21,v47_or_qwen3vl_32b,dean,6,66,55,53,2,13,0.9636,0.803,0.876,0.9434,0.8333,0.876,3,55,0,0.0,2,0.9636,1,8,300,1800,1,2,False,0.0,0.0,251.78,,280,0.1023
2026-06-21T11:32:18,v48_or_gemini31_lite,355,2,13,15,10,5,3,0.6667,0.7692,0.7143,1.0,0.8462,0.3571,0,10,5,0.3333,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,143.28,,146,0.0694
2026-06-21T11:35:09,v48_or_gemini31_lite,dean,6,66,49,45,4,21,0.9184,0.6818,0.7826,0.9556,0.7424,0.7826,2,46,3,0.0612,1,0.9783,1,8,300,1800,1,2,False,0.0,0.0,168.72,,146,0.0811
2026-06-21T10:21:54,v50_ocr_easy,355,2,13,6,6,0,7,1.0,0.4615,0.6316,1.0,0.4615,0.4211,0,3,3,0.5,0,1.0,1,4,300,3000,1,1,True,0.0,0.0,5913.04,,0,0.0
2026-06-21T10:21:54,v50_ocr_easy,355,13,9,1,1,0,8,1.0,0.1111,0.2,0.0,0.1111,0.2,1,1,0,0.0,0,1.0,1,4,300,3000,1,1,True,0.0,0.0,5913.04,,0,0.0
2026-06-21T11:56:48,v50_ocr_easy,dean,4,25,9,9,0,16,1.0,0.36,0.5294,0.8889,0.36,0.4118,1,4,5,0.5556,0,1.0,1,4,300,3000,1,1,True,0.0,0.0,11359.78,,0,0.0
2026-06-21T11:56:48,v50_ocr_easy,dean,6,66,16,16,0,50,1.0,0.2424,0.3902,1.0,0.2424,0.3902,0,11,5,0.3125,0,1.0,1,4,300,3000,1,1,True,0.0,0.0,11359.78,,0,0.0
2026-06-21T12:12:49,v60_ensemble,355,2,13,29,12,17,1,0.4138,0.9231,0.5714,1.0,0.0,0.2857,0,16,13,0.4483,8,0.5,1,8,300,1800,1,2,False,0.0,0.0,366.9,,253,0.1048
2026-06-21T12:16:24,v60_ensemble,dean,6,66,72,54,18,12,0.75,0.8182,0.7826,0.9444,0.9091,0.7826,3,57,15,0.2083,12,0.7895,1,8,300,1800,1,2,False,0.0,0.0,422.07,,269,0.1268
2026-06-21T12:26:23,v70_sparse_qwen3vl,355,2,13,3,3,0,10,1.0,0.2308,0.375,1.0,0.2308,0.125,0,3,0,0.0,0,1.0,1,8,300,3000,1,1,True,0.0,0.0,135.0,,19,0.0066
2026-06-21T12:28:29,v70_sparse_qwen3vl,dean,6,66,19,19,0,47,1.0,0.2879,0.4471,1.0,0.2879,0.4,0,19,0,0.0,0,1.0,1,8,300,3000,1,1,True,0.0,0.0,121.36,,15,0.0063
2026-06-21T12:29:52,v71_sparse_flashlite,355,2,13,3,3,0,10,1.0,0.2308,0.375,1.0,0.2308,0.125,0,3,0,0.0,0,1.0,1,8,300,3000,1,1,True,0.0,0.0,78.05,,20,0.0085
2026-06-21T12:32:01,v71_sparse_flashlite,dean,6,66,19,19,0,47,1.0,0.2879,0.4471,1.0,0.2879,0.4471,0,19,0,0.0,0,1.0,1,8,300,3000,1,1,True,0.0,0.0,125.44,,20,0.0084
2026-06-21T12:33:51,v73_qwen3vl_reason,355,2,13,9,9,0,4,1.0,0.6923,0.8182,1.0,0.6923,0.2727,0,9,0,0.0,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,105.96,,116,0.0385
2026-06-21T12:36:30,v73_qwen3vl_reason,dean,6,66,50,48,2,18,0.96,0.7273,0.8276,0.9375,0.7576,0.8276,3,50,0,0.0,2,0.96,1,8,300,1800,1,2,False,0.0,0.0,155.63,,132,0.0489
2026-06-26T07:08:02,v80_or_glm5v,355,2,13,12,12,0,1,1.0,0.9231,0.96,1.0,0.9231,0.56,0,11,1,0.0833,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,28775.91,28779.3,292,2.0266
2026-06-26T07:08:02,v80_or_glm5v,355,13,9,18,6,12,3,0.3333,0.6667,0.4444,1.0,0.0,0.4444,0,6,12,0.6667,1,0.8333,1,8,300,1800,1,2,False,0.0,0.0,28775.91,28779.3,292,2.0266
2026-06-26T07:26:07,v80_or_glm5v,dean,4,25,24,23,1,2,0.9583,0.92,0.9388,1.0,0.96,0.9388,0,22,2,0.0833,0,1.0,1,8,300,1800,1,2,False,0.0,0.0,1082.29,1084.92,291,2.3088
2026-06-26T07:26:07,v80_or_glm5v,dean,6,66,56,54,2,12,0.9643,0.8182,0.8852,0.9444,0.8485,0.8852,3,55,1,0.0179,1,0.9818,1,8,300,1800,1,2,False,0.0,0.0,1082.29,1084.92,291,2.3088