vidore
baseline-results / openbmb_VisRAG-Ret_metrics.json
QuentinJG's picture
Rename visrag-ret_metrics.json to openbmb_VisRAG-Ret_metrics.json
577eb00 verified
{
"metadata": {
"timestamp": "2025-03-13T15:23:57.734843",
"vidore_benchmark_version": "5.0.1.dev5+g1548c2d.d20250313"
},
"metrics": {
"vidore/restaurant_esg_reports_beir": {
"ndcg_at_1": 0.48718,
"ndcg_at_3": 0.51987,
"ndcg_at_5": 0.53707,
"ndcg_at_10": 0.58691,
"ndcg_at_20": 0.60769,
"ndcg_at_50": 0.6397,
"ndcg_at_100": 0.65482,
"map_at_1": 0.36186,
"map_at_3": 0.4602,
"map_at_5": 0.48616,
"map_at_10": 0.51598,
"map_at_20": 0.52449,
"map_at_50": 0.53241,
"map_at_100": 0.5362,
"recall_at_1": 0.36186,
"recall_at_3": 0.52821,
"recall_at_5": 0.59359,
"recall_at_10": 0.70563,
"recall_at_20": 0.76315,
"recall_at_50": 0.88615,
"recall_at_100": 0.94866,
"precision_at_1": 0.5,
"precision_at_3": 0.27564,
"precision_at_5": 0.19231,
"precision_at_10": 0.13077,
"precision_at_20": 0.07596,
"precision_at_50": 0.03808,
"precision_at_100": 0.02192,
"mrr_at_1": 0.5,
"mrr_at_3": 0.5769230769230769,
"mrr_at_5": 0.5865384615384615,
"mrr_at_10": 0.6023733211233211,
"mrr_at_20": 0.6069520757020757,
"mrr_at_50": 0.6103908065114961,
"mrr_at_100": 0.6106960568167464,
"naucs_at_1_max": 0.015424312502453706,
"naucs_at_1_std": -0.13924671268887046,
"naucs_at_1_diff1": 0.774635283388261,
"naucs_at_3_max": 0.08232812603721668,
"naucs_at_3_std": 0.14582513042567308,
"naucs_at_3_diff1": 0.3413749493398797,
"naucs_at_5_max": 0.04733940764311593,
"naucs_at_5_std": 0.201486754820981,
"naucs_at_5_diff1": 0.1679332256651539,
"naucs_at_10_max": 0.15213696092763468,
"naucs_at_10_std": 0.25898837879862296,
"naucs_at_10_diff1": -0.0032105086289669817,
"naucs_at_20_max": 0.1701364069679977,
"naucs_at_20_std": 0.3491634058276955,
"naucs_at_20_diff1": -0.10811392645442519,
"naucs_at_50_max": 0.22116549189926218,
"naucs_at_50_std": 0.40046893166130704,
"naucs_at_50_diff1": -0.22625061791645093,
"naucs_at_100_max": 0.23011945384723256,
"naucs_at_100_std": 0.42936675975120925,
"naucs_at_100_diff1": -0.2960643771988182
},
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
"ndcg_at_1": 0.54375,
"ndcg_at_3": 0.52916,
"ndcg_at_5": 0.54779,
"ndcg_at_10": 0.58771,
"ndcg_at_20": 0.61859,
"ndcg_at_50": 0.64913,
"ndcg_at_100": 0.66185,
"map_at_1": 0.33558,
"map_at_3": 0.4307,
"map_at_5": 0.46539,
"map_at_10": 0.49662,
"map_at_20": 0.51175,
"map_at_50": 0.52171,
"map_at_100": 0.52497,
"recall_at_1": 0.33558,
"recall_at_3": 0.49142,
"recall_at_5": 0.5656,
"recall_at_10": 0.67964,
"recall_at_20": 0.77075,
"recall_at_50": 0.87085,
"recall_at_100": 0.91455,
"precision_at_1": 0.54375,
"precision_at_3": 0.32292,
"precision_at_5": 0.24625,
"precision_at_10": 0.16063,
"precision_at_20": 0.09688,
"precision_at_50": 0.04762,
"precision_at_100": 0.02675,
"mrr_at_1": 0.54375,
"mrr_at_3": 0.6177083333333331,
"mrr_at_5": 0.6317708333333332,
"mrr_at_10": 0.6458953373015872,
"mrr_at_20": 0.6501168388392652,
"mrr_at_50": 0.6516168070330217,
"mrr_at_100": 0.6516168070330217,
"naucs_at_1_max": 0.17394147030363272,
"naucs_at_1_std": -0.36673902241284584,
"naucs_at_1_diff1": 0.43317554550130327,
"naucs_at_3_max": 0.10230735338450472,
"naucs_at_3_std": -0.16796141270319767,
"naucs_at_3_diff1": -0.0021937249263731763,
"naucs_at_5_max": 0.06165269158937461,
"naucs_at_5_std": -0.16213659251057302,
"naucs_at_5_diff1": -0.09605836244564413,
"naucs_at_10_max": 0.04062826287163538,
"naucs_at_10_std": -0.10386324001578753,
"naucs_at_10_diff1": -0.19533141678260185,
"naucs_at_20_max": -0.023024941185161928,
"naucs_at_20_std": -0.0808216300079185,
"naucs_at_20_diff1": -0.2571645591830793,
"naucs_at_50_max": -0.06194972750127154,
"naucs_at_50_std": 0.023927949244181214,
"naucs_at_50_diff1": -0.28301815335673003,
"naucs_at_100_max": -0.10101655678389299,
"naucs_at_100_std": 0.08336119059224785,
"naucs_at_100_diff1": -0.2955701804119539
},
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
"ndcg_at_1": 0.63793,
"ndcg_at_3": 0.61396,
"ndcg_at_5": 0.59648,
"ndcg_at_10": 0.55957,
"ndcg_at_20": 0.58035,
"ndcg_at_50": 0.64249,
"ndcg_at_100": 0.68124,
"map_at_1": 0.07146,
"map_at_3": 0.16727,
"map_at_5": 0.22845,
"map_at_10": 0.29412,
"map_at_20": 0.35326,
"map_at_50": 0.41154,
"map_at_100": 0.43875,
"recall_at_1": 0.07146,
"recall_at_3": 0.2114,
"recall_at_5": 0.31582,
"recall_at_10": 0.44705,
"recall_at_20": 0.59174,
"recall_at_50": 0.77882,
"recall_at_100": 0.90011,
"precision_at_1": 0.63793,
"precision_at_3": 0.58046,
"precision_at_5": 0.53448,
"precision_at_10": 0.4069,
"precision_at_20": 0.31121,
"precision_at_50": 0.19621,
"precision_at_100": 0.1269,
"mrr_at_1": 0.6379310344827587,
"mrr_at_3": 0.735632183908046,
"mrr_at_5": 0.7502873563218392,
"mrr_at_10": 0.7584975369458129,
"mrr_at_20": 0.7607245484400658,
"mrr_at_50": 0.7607245484400658,
"mrr_at_100": 0.7607245484400658,
"naucs_at_1_max": 0.30951896933248446,
"naucs_at_1_std": 0.0009385908345415833,
"naucs_at_1_diff1": 0.12207984020363619,
"naucs_at_3_max": 0.3174256751774014,
"naucs_at_3_std": 0.07401442252929685,
"naucs_at_3_diff1": 0.0813575535006513,
"naucs_at_5_max": 0.3929619603728344,
"naucs_at_5_std": 0.1689559171748497,
"naucs_at_5_diff1": 0.04881016825842116,
"naucs_at_10_max": 0.4375324160420264,
"naucs_at_10_std": 0.2657788992938007,
"naucs_at_10_diff1": -0.08210009736139143,
"naucs_at_20_max": 0.435316184966006,
"naucs_at_20_std": 0.3991338622440554,
"naucs_at_20_diff1": -0.0429704940007693,
"naucs_at_50_max": 0.3483632241805499,
"naucs_at_50_std": 0.33986582587288133,
"naucs_at_50_diff1": 0.0168280192203874,
"naucs_at_100_max": 0.28796239161632026,
"naucs_at_100_std": 0.27465381207019524,
"naucs_at_100_diff1": 0.04462948923164142
},
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
"ndcg_at_1": 0.42105,
"ndcg_at_3": 0.40524,
"ndcg_at_5": 0.45864,
"ndcg_at_10": 0.50339,
"ndcg_at_20": 0.52015,
"ndcg_at_50": 0.55124,
"ndcg_at_100": 0.58182,
"map_at_1": 0.20117,
"map_at_3": 0.29694,
"map_at_5": 0.34743,
"map_at_10": 0.38591,
"map_at_20": 0.39764,
"map_at_50": 0.40953,
"map_at_100": 0.41648,
"recall_at_1": 0.20117,
"recall_at_3": 0.35925,
"recall_at_5": 0.49808,
"recall_at_10": 0.6391,
"recall_at_20": 0.69492,
"recall_at_50": 0.79371,
"recall_at_100": 0.91345,
"precision_at_1": 0.42105,
"precision_at_3": 0.26901,
"precision_at_5": 0.24561,
"precision_at_10": 0.16842,
"precision_at_20": 0.09912,
"precision_at_50": 0.05298,
"precision_at_100": 0.03316,
"mrr_at_1": 0.42105263157894735,
"mrr_at_3": 0.5058479532163742,
"mrr_at_5": 0.5330409356725145,
"mrr_at_10": 0.5501461988304093,
"mrr_at_20": 0.5501461988304093,
"mrr_at_50": 0.5521026864735273,
"mrr_at_100": 0.5529842660756151,
"naucs_at_1_max": 0.2681727937415602,
"naucs_at_1_std": 0.26125468443050986,
"naucs_at_1_diff1": 0.1925487726366543,
"naucs_at_3_max": 0.15154876755279928,
"naucs_at_3_std": 0.187284520490265,
"naucs_at_3_diff1": 0.13314931121987555,
"naucs_at_5_max": 0.06746755549674449,
"naucs_at_5_std": 0.17211166986401807,
"naucs_at_5_diff1": 0.09922461829032554,
"naucs_at_10_max": 0.1173297532733523,
"naucs_at_10_std": 0.2334653355769548,
"naucs_at_10_diff1": 0.13391976394738275,
"naucs_at_20_max": -0.004406787213674995,
"naucs_at_20_std": 0.2228534925354155,
"naucs_at_20_diff1": 0.0419546501642916,
"naucs_at_50_max": -0.09092484597679043,
"naucs_at_50_std": 0.2015080134456558,
"naucs_at_50_diff1": -0.06928136029689304,
"naucs_at_100_max": -0.14425251784397497,
"naucs_at_100_std": 0.2117646090542283,
"naucs_at_100_diff1": -0.12598719754364754
},
"vidore/synthetic_axa_filtered_v1.0": {
"ndcg_at_1": 0.38889,
"ndcg_at_3": 0.5418,
"ndcg_at_5": 0.50473,
"ndcg_at_10": 0.53634,
"ndcg_at_20": 0.56481,
"ndcg_at_50": 0.60088,
"ndcg_at_100": 0.62788,
"map_at_1": 0.19085,
"map_at_3": 0.33844,
"map_at_5": 0.34887,
"map_at_10": 0.3905,
"map_at_20": 0.41424,
"map_at_50": 0.42936,
"map_at_100": 0.43807,
"recall_at_1": 0.19085,
"recall_at_3": 0.52023,
"recall_at_5": 0.53824,
"recall_at_10": 0.68819,
"recall_at_20": 0.76306,
"recall_at_50": 0.85789,
"recall_at_100": 0.93331,
"precision_at_1": 0.38889,
"precision_at_3": 0.38889,
"precision_at_5": 0.26667,
"precision_at_10": 0.2,
"precision_at_20": 0.13333,
"precision_at_50": 0.06889,
"precision_at_100": 0.04222,
"mrr_at_1": 0.3888888888888889,
"mrr_at_3": 0.5740740740740741,
"mrr_at_5": 0.587962962962963,
"mrr_at_10": 0.6033950617283952,
"mrr_at_20": 0.6033950617283952,
"mrr_at_50": 0.6033950617283952,
"mrr_at_100": 0.6033950617283952,
"naucs_at_1_max": 0.14105650005960155,
"naucs_at_1_std": -0.01993661989253736,
"naucs_at_1_diff1": 0.43542988491270046,
"naucs_at_3_max": -0.22826796699446616,
"naucs_at_3_std": -0.004572665724137645,
"naucs_at_3_diff1": 0.07496811347896108,
"naucs_at_5_max": -0.3852842673944422,
"naucs_at_5_std": -0.15791921982494983,
"naucs_at_5_diff1": 0.2052446052071864,
"naucs_at_10_max": -0.3499853580695824,
"naucs_at_10_std": -0.07324394708860461,
"naucs_at_10_diff1": 0.06796721460372077,
"naucs_at_20_max": -0.360118573152839,
"naucs_at_20_std": -0.15283583044728602,
"naucs_at_20_diff1": 0.26460065509124203,
"naucs_at_50_max": -0.38416433266363276,
"naucs_at_50_std": -0.1571206204390072,
"naucs_at_50_diff1": 0.4313242188093156,
"naucs_at_100_max": -0.4149515845406916,
"naucs_at_100_std": -0.19401302943385454,
"naucs_at_100_diff1": 0.49450789205035006
},
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.39912,
"ndcg_at_3": 0.43071,
"ndcg_at_5": 0.46444,
"ndcg_at_10": 0.4968,
"ndcg_at_20": 0.52854,
"ndcg_at_50": 0.56102,
"ndcg_at_100": 0.58233,
"map_at_1": 0.17982,
"map_at_3": 0.30157,
"map_at_5": 0.34561,
"map_at_10": 0.38009,
"map_at_20": 0.39814,
"map_at_50": 0.41046,
"map_at_100": 0.41606,
"recall_at_1": 0.17982,
"recall_at_3": 0.4008,
"recall_at_5": 0.50897,
"recall_at_10": 0.62213,
"recall_at_20": 0.72976,
"recall_at_50": 0.83655,
"recall_at_100": 0.915,
"precision_at_1": 0.39912,
"precision_at_3": 0.30263,
"precision_at_5": 0.25175,
"precision_at_10": 0.16886,
"precision_at_20": 0.10636,
"precision_at_50": 0.05632,
"precision_at_100": 0.03329,
"mrr_at_1": 0.3991228070175439,
"mrr_at_3": 0.5160818713450291,
"mrr_at_5": 0.5342836257309941,
"mrr_at_10": 0.5459934558618768,
"mrr_at_20": 0.5499615268119828,
"mrr_at_50": 0.5520170407199186,
"mrr_at_100": 0.5523559958857708,
"naucs_at_1_max": 0.15755765375477634,
"naucs_at_1_std": 0.1937615823895248,
"naucs_at_1_diff1": 0.20176410519897442,
"naucs_at_3_max": 0.21637882247590812,
"naucs_at_3_std": 0.21919003966069206,
"naucs_at_3_diff1": 0.09426673538244577,
"naucs_at_5_max": 0.17022232642187712,
"naucs_at_5_std": 0.20399998951672477,
"naucs_at_5_diff1": 0.07433346087483172,
"naucs_at_10_max": 0.17445157988680682,
"naucs_at_10_std": 0.19671403249308644,
"naucs_at_10_diff1": 0.042552504976369365,
"naucs_at_20_max": 0.0564754707494715,
"naucs_at_20_std": 0.14487480859508034,
"naucs_at_20_diff1": -0.050996649070789594,
"naucs_at_50_max": -0.032342844885820655,
"naucs_at_50_std": 0.0919650425307495,
"naucs_at_50_diff1": -0.1049317890928347,
"naucs_at_100_max": -0.0813860336462654,
"naucs_at_100_std": 0.07405564056158524,
"naucs_at_100_diff1": -0.15314098265443818
},
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.40278,
"ndcg_at_3": 0.45413,
"ndcg_at_5": 0.45175,
"ndcg_at_10": 0.49692,
"ndcg_at_20": 0.53744,
"ndcg_at_50": 0.57505,
"ndcg_at_100": 0.60205,
"map_at_1": 0.20688,
"map_at_3": 0.30245,
"map_at_5": 0.32956,
"map_at_10": 0.37191,
"map_at_20": 0.39679,
"map_at_50": 0.41224,
"map_at_100": 0.42049,
"recall_at_1": 0.20688,
"recall_at_3": 0.39577,
"recall_at_5": 0.462,
"recall_at_10": 0.6319,
"recall_at_20": 0.73905,
"recall_at_50": 0.83135,
"recall_at_100": 0.90763,
"precision_at_1": 0.40278,
"precision_at_3": 0.30556,
"precision_at_5": 0.23889,
"precision_at_10": 0.17917,
"precision_at_20": 0.125,
"precision_at_50": 0.06639,
"precision_at_100": 0.04097,
"mrr_at_1": 0.4027777777777778,
"mrr_at_3": 0.5300925925925926,
"mrr_at_5": 0.5564814814814815,
"mrr_at_10": 0.5736221340388007,
"mrr_at_20": 0.5763117283950616,
"mrr_at_50": 0.5763117283950616,
"mrr_at_100": 0.5763117283950616,
"naucs_at_1_max": 0.20656968495031644,
"naucs_at_1_std": 0.0817297457698203,
"naucs_at_1_diff1": 0.2238136061191017,
"naucs_at_3_max": 0.25163264129737517,
"naucs_at_3_std": 0.17030727986741342,
"naucs_at_3_diff1": 0.03578498764457108,
"naucs_at_5_max": 0.08903441500332349,
"naucs_at_5_std": 0.04568596558397242,
"naucs_at_5_diff1": -0.009941530139102166,
"naucs_at_10_max": -0.020546119491255295,
"naucs_at_10_std": 0.008887544287522966,
"naucs_at_10_diff1": -0.09432640328513163,
"naucs_at_20_max": -0.1319344233352006,
"naucs_at_20_std": -0.044221131984674825,
"naucs_at_20_diff1": -0.06538820564150717,
"naucs_at_50_max": -0.18743175691838732,
"naucs_at_50_std": -0.0972663161231581,
"naucs_at_50_diff1": -0.017105606627328275,
"naucs_at_100_max": -0.2325355500441028,
"naucs_at_100_std": -0.15406419774878136,
"naucs_at_100_diff1": -0.018290038816855033
},
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
"ndcg_at_1": 0.43438,
"ndcg_at_3": 0.45593,
"ndcg_at_5": 0.47695,
"ndcg_at_10": 0.5166,
"ndcg_at_20": 0.54502,
"ndcg_at_50": 0.57616,
"ndcg_at_100": 0.59352,
"map_at_1": 0.27154,
"map_at_3": 0.36745,
"map_at_5": 0.39714,
"map_at_10": 0.42629,
"map_at_20": 0.43946,
"map_at_50": 0.44896,
"map_at_100": 0.45239,
"recall_at_1": 0.27154,
"recall_at_3": 0.44101,
"recall_at_5": 0.51211,
"recall_at_10": 0.62263,
"recall_at_20": 0.70666,
"recall_at_50": 0.81063,
"recall_at_100": 0.87902,
"precision_at_1": 0.43438,
"precision_at_3": 0.27917,
"precision_at_5": 0.21531,
"precision_at_10": 0.14359,
"precision_at_20": 0.08672,
"precision_at_50": 0.04341,
"precision_at_100": 0.02502,
"mrr_at_1": 0.434375,
"mrr_at_3": 0.5317708333333331,
"mrr_at_5": 0.5496614583333328,
"mrr_at_10": 0.5630952380952378,
"mrr_at_20": 0.5669521784558423,
"mrr_at_50": 0.5688358670627492,
"mrr_at_100": 0.5692193060123717,
"naucs_at_1_max": 0.2666912240570166,
"naucs_at_1_std": 0.05389058257999144,
"naucs_at_1_diff1": 0.4321239157776483,
"naucs_at_3_max": 0.17727410640755303,
"naucs_at_3_std": 0.01577475274662206,
"naucs_at_3_diff1": 0.09089286579349252,
"naucs_at_5_max": 0.13070625524250945,
"naucs_at_5_std": 0.01198523787261333,
"naucs_at_5_diff1": -0.013247813819131482,
"naucs_at_10_max": 0.08901372928565265,
"naucs_at_10_std": 0.0242424061104149,
"naucs_at_10_diff1": -0.0824662153065525,
"naucs_at_20_max": 0.046509940234363965,
"naucs_at_20_std": 0.023421019939509093,
"naucs_at_20_diff1": -0.13765222771211638,
"naucs_at_50_max": -0.016368222256068723,
"naucs_at_50_std": 0.017686339762030524,
"naucs_at_50_diff1": -0.18185950361763814,
"naucs_at_100_max": -0.05809760099241634,
"naucs_at_100_std": -0.0007126993337199372,
"naucs_at_100_diff1": -0.20245463094499655
},
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.52586,
"ndcg_at_3": 0.49942,
"ndcg_at_5": 0.48681,
"ndcg_at_10": 0.46438,
"ndcg_at_20": 0.49413,
"ndcg_at_50": 0.56018,
"ndcg_at_100": 0.60792,
"map_at_1": 0.05323,
"map_at_3": 0.12858,
"map_at_5": 0.17351,
"map_at_10": 0.22551,
"map_at_20": 0.27667,
"map_at_50": 0.3298,
"map_at_100": 0.35718,
"recall_at_1": 0.05323,
"recall_at_3": 0.16936,
"recall_at_5": 0.25112,
"recall_at_10": 0.37154,
"recall_at_20": 0.52494,
"recall_at_50": 0.7231,
"recall_at_100": 0.86824,
"precision_at_1": 0.52586,
"precision_at_3": 0.4727,
"precision_at_5": 0.43966,
"precision_at_10": 0.35,
"precision_at_20": 0.27651,
"precision_at_50": 0.17888,
"precision_at_100": 0.12013,
"mrr_at_1": 0.5258620689655172,
"mrr_at_3": 0.6163793103448275,
"mrr_at_5": 0.6372844827586207,
"mrr_at_10": 0.6511271893814995,
"mrr_at_20": 0.6548831549338646,
"mrr_at_50": 0.6554856928251602,
"mrr_at_100": 0.6556279827912883,
"naucs_at_1_max": 0.1755971141206357,
"naucs_at_1_std": 0.18264029674960228,
"naucs_at_1_diff1": 0.06925322234490841,
"naucs_at_3_max": 0.2812764433128787,
"naucs_at_3_std": 0.2690356636124753,
"naucs_at_3_diff1": 0.016089000880329198,
"naucs_at_5_max": 0.283989396373602,
"naucs_at_5_std": 0.29562037646588923,
"naucs_at_5_diff1": 0.009509118422791094,
"naucs_at_10_max": 0.23668581693373705,
"naucs_at_10_std": 0.2844259803726197,
"naucs_at_10_diff1": -0.07126374015391594,
"naucs_at_20_max": 0.2076351063428368,
"naucs_at_20_std": 0.2991176793010035,
"naucs_at_20_diff1": -0.08337920885811372,
"naucs_at_50_max": 0.1238437265668122,
"naucs_at_50_std": 0.2430342456930391,
"naucs_at_50_diff1": -0.05232657907650674,
"naucs_at_100_max": 0.05825862012096387,
"naucs_at_100_std": 0.19337982478846943,
"naucs_at_100_diff1": -0.020634764162514304
},
"vidore/arxivqa_test_subsampled": {
"ndcg_at_1": 0.736,
"ndcg_at_3": 0.79238,
"ndcg_at_5": 0.80581,
"ndcg_at_10": 0.82083,
"ndcg_at_20": 0.82784,
"ndcg_at_50": 0.83516,
"ndcg_at_100": 0.83776,
"map_at_1": 0.736,
"map_at_3": 0.77867,
"map_at_5": 0.78627,
"map_at_10": 0.79255,
"map_at_20": 0.79443,
"map_at_50": 0.79568,
"map_at_100": 0.79591,
"recall_at_1": 0.736,
"recall_at_3": 0.832,
"recall_at_5": 0.864,
"recall_at_10": 0.91,
"recall_at_20": 0.938,
"recall_at_50": 0.974,
"recall_at_100": 0.99,
"precision_at_1": 0.736,
"precision_at_3": 0.27733,
"precision_at_5": 0.1728,
"precision_at_10": 0.091,
"precision_at_20": 0.0469,
"precision_at_50": 0.01948,
"precision_at_100": 0.0099,
"mrr_at_1": 0.736,
"mrr_at_3": 0.7786666666666667,
"mrr_at_5": 0.7862666666666667,
"mrr_at_10": 0.7925476190476194,
"mrr_at_20": 0.7944328455428302,
"mrr_at_50": 0.7956750456398185,
"mrr_at_100": 0.7959050774896889,
"naucs_at_1_max": 0.6486039470733347,
"naucs_at_1_std": -0.11010636593726965,
"naucs_at_1_diff1": 0.8885840835549293,
"naucs_at_3_max": 0.6259037134406845,
"naucs_at_3_std": -0.18474484765973373,
"naucs_at_3_diff1": 0.8376660720153996,
"naucs_at_5_max": 0.6215153325368371,
"naucs_at_5_std": -0.17638817773226517,
"naucs_at_5_diff1": 0.8335253456221203,
"naucs_at_10_max": 0.5732648615001562,
"naucs_at_10_std": -0.2490196078431399,
"naucs_at_10_diff1": 0.787851436871045,
"naucs_at_20_max": 0.5872112285774529,
"naucs_at_20_std": -0.18579259660853667,
"naucs_at_20_diff1": 0.8300502996897676,
"naucs_at_50_max": 0.8495654672125184,
"naucs_at_50_std": 0.27152912447029887,
"naucs_at_50_diff1": 0.8371399841988043,
"naucs_at_100_max": 0.9183006535947666,
"naucs_at_100_std": 0.49262371615312944,
"naucs_at_100_diff1": 0.8921568627450854
},
"vidore/docvqa_test_subsampled": {
"ndcg_at_1": 0.34368,
"ndcg_at_3": 0.40479,
"ndcg_at_5": 0.42673,
"ndcg_at_10": 0.45035,
"ndcg_at_20": 0.46746,
"ndcg_at_50": 0.48358,
"ndcg_at_100": 0.49656,
"map_at_1": 0.34368,
"map_at_3": 0.38987,
"map_at_5": 0.40207,
"map_at_10": 0.41179,
"map_at_20": 0.41664,
"map_at_50": 0.41935,
"map_at_100": 0.42051,
"recall_at_1": 0.34368,
"recall_at_3": 0.44789,
"recall_at_5": 0.50111,
"recall_at_10": 0.57428,
"recall_at_20": 0.6408,
"recall_at_50": 0.72062,
"recall_at_100": 0.80044,
"precision_at_1": 0.34368,
"precision_at_3": 0.1493,
"precision_at_5": 0.10022,
"precision_at_10": 0.05743,
"precision_at_20": 0.03204,
"precision_at_50": 0.01441,
"precision_at_100": 0.008,
"mrr_at_1": 0.3436807095343681,
"mrr_at_3": 0.3898743532889875,
"mrr_at_5": 0.4020694752402069,
"mrr_at_10": 0.4117877380072501,
"mrr_at_20": 0.4166391095440233,
"mrr_at_50": 0.4194072008524503,
"mrr_at_100": 0.42066245247914874,
"naucs_at_1_max": 0.6937621431789922,
"naucs_at_1_std": 0.3966932403411503,
"naucs_at_1_diff1": 0.7145229983797862,
"naucs_at_3_max": 0.7320406126458378,
"naucs_at_3_std": 0.45563802569337475,
"naucs_at_3_diff1": 0.6143081963671839,
"naucs_at_5_max": 0.6880199080240672,
"naucs_at_5_std": 0.44498830503027725,
"naucs_at_5_diff1": 0.5636895248104472,
"naucs_at_10_max": 0.7395456562744627,
"naucs_at_10_std": 0.5421201928794931,
"naucs_at_10_diff1": 0.5433914071660855,
"naucs_at_20_max": 0.7099358788663228,
"naucs_at_20_std": 0.505428632850115,
"naucs_at_20_diff1": 0.5026852667645294,
"naucs_at_50_max": 0.7044396744042806,
"naucs_at_50_std": 0.5292950459939872,
"naucs_at_50_diff1": 0.48465037492486385,
"naucs_at_100_max": 0.6982871591556156,
"naucs_at_100_std": 0.5542470657836935,
"naucs_at_100_diff1": 0.4520088087347075
},
"vidore/infovqa_test_subsampled": {
"ndcg_at_1": 0.76923,
"ndcg_at_3": 0.83858,
"ndcg_at_5": 0.85026,
"ndcg_at_10": 0.86321,
"ndcg_at_20": 0.86616,
"ndcg_at_50": 0.86899,
"ndcg_at_100": 0.86929,
"map_at_1": 0.76923,
"map_at_3": 0.82254,
"map_at_5": 0.82901,
"map_at_10": 0.83467,
"map_at_20": 0.83541,
"map_at_50": 0.83587,
"map_at_100": 0.8359,
"recall_at_1": 0.76923,
"recall_at_3": 0.88462,
"recall_at_5": 0.91296,
"recall_at_10": 0.95142,
"recall_at_20": 0.96356,
"recall_at_50": 0.97773,
"recall_at_100": 0.97976,
"precision_at_1": 0.76923,
"precision_at_3": 0.29487,
"precision_at_5": 0.18259,
"precision_at_10": 0.09514,
"precision_at_20": 0.04818,
"precision_at_50": 0.01955,
"precision_at_100": 0.0098,
"mrr_at_1": 0.7692307692307693,
"mrr_at_3": 0.8225371120107962,
"mrr_at_5": 0.8290148448043184,
"mrr_at_10": 0.8346667951931113,
"mrr_at_20": 0.8354146169277593,
"mrr_at_50": 0.8358748221328831,
"mrr_at_100": 0.8359177231300928,
"naucs_at_1_max": 0.5127634005653434,
"naucs_at_1_std": -0.03567831485698759,
"naucs_at_1_diff1": 0.8320638205788135,
"naucs_at_3_max": 0.5021250200120738,
"naucs_at_3_std": -0.07399077187048693,
"naucs_at_3_diff1": 0.7752634768446268,
"naucs_at_5_max": 0.5335848645863028,
"naucs_at_5_std": -0.02593966089833383,
"naucs_at_5_diff1": 0.7661635495872359,
"naucs_at_10_max": 0.9000642537485549,
"naucs_at_10_std": 0.4822680430176945,
"naucs_at_10_diff1": 0.7890895385688544,
"naucs_at_20_max": 0.8894376823215577,
"naucs_at_20_std": 0.4867325787808216,
"naucs_at_20_diff1": 0.7414713954152902,
"naucs_at_50_max": 0.9762542810791424,
"naucs_at_50_std": 0.9525085621582665,
"naucs_at_50_diff1": 0.733736269334063,
"naucs_at_100_max": 0.9738797091870466,
"naucs_at_100_std": 0.960819563780575,
"naucs_at_100_diff1": 0.7348833700432545
},
"vidore/tabfquad_test_subsampled": {
"ndcg_at_1": 0.69286,
"ndcg_at_3": 0.75259,
"ndcg_at_5": 0.76889,
"ndcg_at_10": 0.79021,
"ndcg_at_20": 0.80681,
"ndcg_at_50": 0.81245,
"ndcg_at_100": 0.81307,
"map_at_1": 0.69286,
"map_at_3": 0.7375,
"map_at_5": 0.74661,
"map_at_10": 0.75505,
"map_at_20": 0.75979,
"map_at_50": 0.76068,
"map_at_100": 0.76074,
"recall_at_1": 0.69286,
"recall_at_3": 0.79643,
"recall_at_5": 0.83571,
"recall_at_10": 0.90357,
"recall_at_20": 0.96786,
"recall_at_50": 0.99643,
"recall_at_100": 1.0,
"precision_at_1": 0.69286,
"precision_at_3": 0.26548,
"precision_at_5": 0.16714,
"precision_at_10": 0.09036,
"precision_at_20": 0.04839,
"precision_at_50": 0.01993,
"precision_at_100": 0.01,
"mrr_at_1": 0.6928571428571428,
"mrr_at_3": 0.7375000000000002,
"mrr_at_5": 0.746607142857143,
"mrr_at_10": 0.7550481859410433,
"mrr_at_20": 0.7597886651746948,
"mrr_at_50": 0.7606781401931197,
"mrr_at_100": 0.7607430752580548,
"naucs_at_1_max": 0.6018301415698155,
"naucs_at_1_std": 0.32571196816263426,
"naucs_at_1_diff1": 0.7888873398309274,
"naucs_at_3_max": 0.6444276300161007,
"naucs_at_3_std": 0.3241186355677946,
"naucs_at_3_diff1": 0.7616114869917906,
"naucs_at_5_max": 0.6430603688016092,
"naucs_at_5_std": 0.32898001968082796,
"naucs_at_5_diff1": 0.725377572412612,
"naucs_at_10_max": 0.5787598990213383,
"naucs_at_10_std": 0.39082546598886503,
"naucs_at_10_diff1": 0.6965107030466515,
"naucs_at_20_max": 0.5347546425977789,
"naucs_at_20_std": 0.10488639900404371,
"naucs_at_20_diff1": 0.5825293080195045,
"naucs_at_50_max": 0.8692810457515607,
"naucs_at_50_std": 0.5541549953314449,
"naucs_at_50_diff1": 0.8692810457515607,
"naucs_at_100_max": 1.0,
"naucs_at_100_std": 1.0,
"naucs_at_100_diff1": 1.0
},
"vidore/tatdqa_test": {
"ndcg_at_1": 0.35115,
"ndcg_at_3": 0.45665,
"ndcg_at_5": 0.49299,
"ndcg_at_10": 0.53515,
"ndcg_at_20": 0.55722,
"ndcg_at_50": 0.57662,
"ndcg_at_100": 0.58344,
"map_at_1": 0.35115,
"map_at_3": 0.43074,
"map_at_5": 0.45094,
"map_at_10": 0.46853,
"map_at_20": 0.47464,
"map_at_50": 0.47794,
"map_at_100": 0.47855,
"recall_at_1": 0.35115,
"recall_at_3": 0.53159,
"recall_at_5": 0.61968,
"recall_at_10": 0.74909,
"recall_at_20": 0.83597,
"recall_at_50": 0.93135,
"recall_at_100": 0.97327,
"precision_at_1": 0.35115,
"precision_at_3": 0.1772,
"precision_at_5": 0.12394,
"precision_at_10": 0.07491,
"precision_at_20": 0.0418,
"precision_at_50": 0.01863,
"precision_at_100": 0.00973,
"mrr_at_1": 0.35297691373025514,
"mrr_at_3": 0.431652490886999,
"mrr_at_5": 0.45188335358444764,
"mrr_at_10": 0.4694830179945614,
"mrr_at_20": 0.47559566338222015,
"mrr_at_50": 0.47890243738258254,
"mrr_at_100": 0.47950989875566846,
"naucs_at_1_max": 0.16045300557832828,
"naucs_at_1_std": -0.18712590459385856,
"naucs_at_1_diff1": 0.5440702710166525,
"naucs_at_3_max": 0.20647987331228912,
"naucs_at_3_std": -0.12049997692079921,
"naucs_at_3_diff1": 0.4450522896579701,
"naucs_at_5_max": 0.2514186053554693,
"naucs_at_5_std": -0.07250138069379193,
"naucs_at_5_diff1": 0.43314416061424443,
"naucs_at_10_max": 0.31938596426902055,
"naucs_at_10_std": -0.03160768541250311,
"naucs_at_10_diff1": 0.4063667061259836,
"naucs_at_20_max": 0.37555947710006393,
"naucs_at_20_std": 0.07079816177576714,
"naucs_at_20_diff1": 0.4080320503888041,
"naucs_at_50_max": 0.37314614111817646,
"naucs_at_50_std": 0.15009417772189595,
"naucs_at_50_diff1": 0.3940999242861563,
"naucs_at_100_max": 0.5170529950663407,
"naucs_at_100_std": 0.41066786010599293,
"naucs_at_100_diff1": 0.41541021771983067
},
"vidore/shiftproject_test": {
"ndcg_at_1": 0.44,
"ndcg_at_3": 0.59095,
"ndcg_at_5": 0.61204,
"ndcg_at_10": 0.6477,
"ndcg_at_20": 0.6722,
"ndcg_at_50": 0.67625,
"ndcg_at_100": 0.678,
"map_at_1": 0.44,
"map_at_3": 0.55333,
"map_at_5": 0.56533,
"map_at_10": 0.58014,
"map_at_20": 0.58646,
"map_at_50": 0.58714,
"map_at_100": 0.58733,
"recall_at_1": 0.44,
"recall_at_3": 0.7,
"recall_at_5": 0.75,
"recall_at_10": 0.86,
"recall_at_20": 0.96,
"recall_at_50": 0.98,
"recall_at_100": 0.99,
"precision_at_1": 0.44,
"precision_at_3": 0.23333,
"precision_at_5": 0.15,
"precision_at_10": 0.086,
"precision_at_20": 0.048,
"precision_at_50": 0.0196,
"precision_at_100": 0.0099,
"mrr_at_1": 0.44,
"mrr_at_3": 0.5533333333333333,
"mrr_at_5": 0.5653333333333334,
"mrr_at_10": 0.580138888888889,
"mrr_at_20": 0.5864581566094724,
"mrr_at_50": 0.5871363175290126,
"mrr_at_100": 0.5873286252213203,
"naucs_at_1_max": -0.004671921490838898,
"naucs_at_1_std": -0.12310121626559477,
"naucs_at_1_diff1": 0.3854335229942058,
"naucs_at_3_max": 0.06802377949918934,
"naucs_at_3_std": -0.11448387677895848,
"naucs_at_3_diff1": 0.31131327688704724,
"naucs_at_5_max": -0.021580324437466547,
"naucs_at_5_std": -0.21312401883830379,
"naucs_at_5_diff1": 0.41149136577707984,
"naucs_at_10_max": -0.1736871276153512,
"naucs_at_10_std": -0.35710821671054294,
"naucs_at_10_diff1": 0.2720659553831241,
"naucs_at_20_max": 0.22934173669468105,
"naucs_at_20_std": -0.1219654528478032,
"naucs_at_20_diff1": 0.7864145658263278,
"naucs_at_50_max": 0.6790382819794637,
"naucs_at_50_std": 0.613678804855281,
"naucs_at_50_diff1": 0.795751633986937,
"naucs_at_100_max": 0.35807656395892007,
"naucs_at_100_std": 0.35807656395892007,
"naucs_at_100_diff1": 0.8692810457516374
},
"vidore/syntheticDocQA_artificial_intelligence_test": {
"ndcg_at_1": 0.88,
"ndcg_at_3": 0.93547,
"ndcg_at_5": 0.94365,
"ndcg_at_10": 0.94365,
"ndcg_at_20": 0.94644,
"ndcg_at_50": 0.94644,
"ndcg_at_100": 0.94644,
"map_at_1": 0.88,
"map_at_3": 0.92333,
"map_at_5": 0.92783,
"map_at_10": 0.92783,
"map_at_20": 0.92874,
"map_at_50": 0.92874,
"map_at_100": 0.92874,
"recall_at_1": 0.88,
"recall_at_3": 0.97,
"recall_at_5": 0.99,
"recall_at_10": 0.99,
"recall_at_20": 1.0,
"recall_at_50": 1.0,
"recall_at_100": 1.0,
"precision_at_1": 0.88,
"precision_at_3": 0.32333,
"precision_at_5": 0.198,
"precision_at_10": 0.099,
"precision_at_20": 0.05,
"precision_at_50": 0.02,
"precision_at_100": 0.01,
"mrr_at_1": 0.88,
"mrr_at_3": 0.9233333333333335,
"mrr_at_5": 0.9278333333333335,
"mrr_at_10": 0.9278333333333335,
"mrr_at_20": 0.9287424242424244,
"mrr_at_50": 0.9287424242424244,
"mrr_at_100": 0.9287424242424244,
"naucs_at_1_max": 0.33646197900095476,
"naucs_at_1_std": -0.10101813553929312,
"naucs_at_1_diff1": 0.8668071905822462,
"naucs_at_3_max": 0.8513849984438244,
"naucs_at_3_std": 0.7424525365701778,
"naucs_at_3_diff1": 0.664021164021167,
"naucs_at_5_max": 1.0,
"naucs_at_5_std": 1.0,
"naucs_at_5_diff1": 0.8692810457516413,
"naucs_at_10_max": 1.0,
"naucs_at_10_std": 1.0,
"naucs_at_10_diff1": 0.8692810457516413,
"naucs_at_20_max": 1.0,
"naucs_at_20_std": 1.0,
"naucs_at_20_diff1": 1.0,
"naucs_at_50_max": null,
"naucs_at_50_std": null,
"naucs_at_50_diff1": null,
"naucs_at_100_max": null,
"naucs_at_100_std": null,
"naucs_at_100_diff1": null
},
"vidore/syntheticDocQA_energy_test": {
"ndcg_at_1": 0.86,
"ndcg_at_3": 0.92047,
"ndcg_at_5": 0.92047,
"ndcg_at_10": 0.92381,
"ndcg_at_20": 0.92381,
"ndcg_at_50": 0.92587,
"ndcg_at_100": 0.92927,
"map_at_1": 0.86,
"map_at_3": 0.90667,
"map_at_5": 0.90667,
"map_at_10": 0.9081,
"map_at_20": 0.9081,
"map_at_50": 0.90845,
"map_at_100": 0.9088,
"recall_at_1": 0.86,
"recall_at_3": 0.96,
"recall_at_5": 0.96,
"recall_at_10": 0.97,
"recall_at_20": 0.97,
"recall_at_50": 0.98,
"recall_at_100": 1.0,
"precision_at_1": 0.86,
"precision_at_3": 0.32,
"precision_at_5": 0.192,
"precision_at_10": 0.097,
"precision_at_20": 0.0485,
"precision_at_50": 0.0196,
"precision_at_100": 0.01,
"mrr_at_1": 0.86,
"mrr_at_3": 0.9066666666666667,
"mrr_at_5": 0.9066666666666667,
"mrr_at_10": 0.9080952380952381,
"mrr_at_20": 0.9080952380952381,
"mrr_at_50": 0.9084523809523809,
"mrr_at_100": 0.9087981335604287,
"naucs_at_1_max": 0.49321047526673,
"naucs_at_1_std": -0.789039767216295,
"naucs_at_1_diff1": 0.8953858944159624,
"naucs_at_3_max": 0.711251167133517,
"naucs_at_3_std": -0.4164332399626471,
"naucs_at_3_diff1": 0.8885387488328684,
"naucs_at_5_max": 0.7112511671335194,
"naucs_at_5_std": -0.41643323996264636,
"naucs_at_5_diff1": 0.8885387488328625,
"naucs_at_10_max": 0.7075941487706191,
"naucs_at_10_std": -0.5961718020541499,
"naucs_at_10_diff1": 0.8513849984438217,
"naucs_at_20_max": 0.7075941487706191,
"naucs_at_20_std": -0.5961718020541499,
"naucs_at_20_diff1": 0.8513849984438217,
"naucs_at_50_max": 0.561391223155939,
"naucs_at_50_std": -0.8085901027077392,
"naucs_at_50_diff1": 0.7770774976657274,
"naucs_at_100_max": null,
"naucs_at_100_std": null,
"naucs_at_100_diff1": null
},
"vidore/syntheticDocQA_government_reports_test": {
"ndcg_at_1": 0.75,
"ndcg_at_3": 0.87226,
"ndcg_at_5": 0.87656,
"ndcg_at_10": 0.87958,
"ndcg_at_20": 0.88734,
"ndcg_at_50": 0.88734,
"ndcg_at_100": 0.88734,
"map_at_1": 0.75,
"map_at_3": 0.845,
"map_at_5": 0.8475,
"map_at_10": 0.84861,
"map_at_20": 0.85085,
"map_at_50": 0.85085,
"map_at_100": 0.85085,
"recall_at_1": 0.75,
"recall_at_3": 0.95,
"recall_at_5": 0.96,
"recall_at_10": 0.97,
"recall_at_20": 1.0,
"recall_at_50": 1.0,
"recall_at_100": 1.0,
"precision_at_1": 0.75,
"precision_at_3": 0.31667,
"precision_at_5": 0.192,
"precision_at_10": 0.097,
"precision_at_20": 0.05,
"precision_at_50": 0.02,
"precision_at_100": 0.01,
"mrr_at_1": 0.75,
"mrr_at_3": 0.8449999999999999,
"mrr_at_5": 0.8474999999999998,
"mrr_at_10": 0.848611111111111,
"mrr_at_20": 0.8508535353535354,
"mrr_at_50": 0.8508535353535354,
"mrr_at_100": 0.8508535353535354,
"naucs_at_1_max": 0.26982731554160105,
"naucs_at_1_std": 0.0717948717948719,
"naucs_at_1_diff1": 0.8517216117216112,
"naucs_at_3_max": 0.7134453781512629,
"naucs_at_3_std": -0.29103641456582646,
"naucs_at_3_diff1": 0.7735760971055052,
"naucs_at_5_max": 0.6418067226890778,
"naucs_at_5_std": -0.6137955182072738,
"naucs_at_5_diff1": 0.7864145658263278,
"naucs_at_10_max": 0.5659819483348872,
"naucs_at_10_std": -0.6305633364456902,
"naucs_at_10_diff1": 0.807812013694364,
"naucs_at_20_max": 1.0,
"naucs_at_20_std": 1.0,
"naucs_at_20_diff1": 1.0,
"naucs_at_50_max": null,
"naucs_at_50_std": null,
"naucs_at_50_diff1": null,
"naucs_at_100_max": null,
"naucs_at_100_std": null,
"naucs_at_100_diff1": null
},
"vidore/syntheticDocQA_healthcare_industry_test": {
"ndcg_at_1": 0.86,
"ndcg_at_3": 0.91917,
"ndcg_at_5": 0.92734,
"ndcg_at_10": 0.93365,
"ndcg_at_20": 0.93365,
"ndcg_at_50": 0.93365,
"ndcg_at_100": 0.93365,
"map_at_1": 0.86,
"map_at_3": 0.905,
"map_at_5": 0.9095,
"map_at_10": 0.912,
"map_at_20": 0.912,
"map_at_50": 0.912,
"map_at_100": 0.912,
"recall_at_1": 0.86,
"recall_at_3": 0.96,
"recall_at_5": 0.98,
"recall_at_10": 1.0,
"recall_at_20": 1.0,
"recall_at_50": 1.0,
"recall_at_100": 1.0,
"precision_at_1": 0.86,
"precision_at_3": 0.32,
"precision_at_5": 0.196,
"precision_at_10": 0.1,
"precision_at_20": 0.05,
"precision_at_50": 0.02,
"precision_at_100": 0.01,
"mrr_at_1": 0.86,
"mrr_at_3": 0.9049999999999998,
"mrr_at_5": 0.9094999999999999,
"mrr_at_10": 0.9119999999999999,
"mrr_at_20": 0.9119999999999999,
"mrr_at_50": 0.9119999999999999,
"mrr_at_100": 0.9119999999999999,
"naucs_at_1_max": 0.14736039905778067,
"naucs_at_1_std": -0.5899958431481216,
"naucs_at_1_diff1": 0.8188998198697522,
"naucs_at_3_max": 0.21171802054154468,
"naucs_at_3_std": -1.2987861811391213,
"naucs_at_3_diff1": 0.8651960784313714,
"naucs_at_5_max": -0.21475256769374024,
"naucs_at_5_std": -1.7399626517273497,
"naucs_at_5_diff1": 0.9346405228758136,
"naucs_at_10_max": 1.0,
"naucs_at_10_std": 1.0,
"naucs_at_10_diff1": 1.0,
"naucs_at_20_max": 1.0,
"naucs_at_20_std": 1.0,
"naucs_at_20_diff1": 1.0,
"naucs_at_50_max": null,
"naucs_at_50_std": null,
"naucs_at_50_diff1": null,
"naucs_at_100_max": null,
"naucs_at_100_std": null,
"naucs_at_100_diff1": null
}
}
}