results/HotpotQA.json

{
  "dataset_revision": "ab518f4d6fcca38d87c25209f94beba119d02014",
  "task_name": "HotpotQA",
  "mteb_version": "2.10.7",
  "scores": {
    "test": [
      {
        "ndcg_at_1": 0.53167,
        "ndcg_at_3": 0.40026,
        "ndcg_at_5": 0.41794,
        "ndcg_at_10": 0.43572,
        "ndcg_at_20": 0.44818,
        "ndcg_at_100": 0.46985,
        "ndcg_at_1000": 0.48897,
        "map_at_1": 0.26583,
        "map_at_3": 0.32984,
        "map_at_5": 0.34128,
        "map_at_10": 0.35012,
        "map_at_20": 0.35428,
        "map_at_100": 0.35803,
        "map_at_1000": 0.35887,
        "recall_at_1": 0.26583,
        "recall_at_3": 0.36914,
        "recall_at_5": 0.40419,
        "recall_at_10": 0.44895,
        "recall_at_20": 0.48906,
        "recall_at_100": 0.58542,
        "recall_at_1000": 0.71323,
        "accuracy": 0.26583,
        "precision_at_1": 0.53167,
        "precision_at_3": 0.24609,
        "precision_at_5": 0.16167,
        "precision_at_10": 0.08979,
        "precision_at_20": 0.04891,
        "precision_at_100": 0.01171,
        "precision_at_1000": 0.00143,
        "mrr_at_1": 0.531668,
        "mrr_at_3": 0.586766,
        "mrr_at_5": 0.595854,
        "mrr_at_10": 0.602144,
        "mrr_at_20": 0.605048,
        "mrr_at_100": 0.607029,
        "mrr_at_1000": 0.607346,
        "nauc_ndcg_at_1_max": 0.433229,
        "nauc_ndcg_at_1_std": 0.05272,
        "nauc_ndcg_at_1_diff1": 0.694146,
        "nauc_ndcg_at_3_max": 0.385363,
        "nauc_ndcg_at_3_std": 0.071543,
        "nauc_ndcg_at_3_diff1": 0.531948,
        "nauc_ndcg_at_5_max": 0.377125,
        "nauc_ndcg_at_5_std": 0.077552,
        "nauc_ndcg_at_5_diff1": 0.508338,
        "nauc_ndcg_at_10_max": 0.369576,
        "nauc_ndcg_at_10_std": 0.082616,
        "nauc_ndcg_at_10_diff1": 0.493585,
        "nauc_ndcg_at_20_max": 0.364503,
        "nauc_ndcg_at_20_std": 0.086776,
        "nauc_ndcg_at_20_diff1": 0.483721,
        "nauc_ndcg_at_100_max": 0.357907,
        "nauc_ndcg_at_100_std": 0.09626,
        "nauc_ndcg_at_100_diff1": 0.471591,
        "nauc_ndcg_at_1000_max": 0.355651,
        "nauc_ndcg_at_1000_std": 0.100939,
        "nauc_ndcg_at_1000_diff1": 0.465123,
        "nauc_map_at_1_max": 0.433229,
        "nauc_map_at_1_std": 0.05272,
        "nauc_map_at_1_diff1": 0.694146,
        "nauc_map_at_3_max": 0.363243,
        "nauc_map_at_3_std": 0.067699,
        "nauc_map_at_3_diff1": 0.500367,
        "nauc_map_at_5_max": 0.35639,
        "nauc_map_at_5_std": 0.072348,
        "nauc_map_at_5_diff1": 0.482395,
        "nauc_map_at_10_max": 0.351947,
        "nauc_map_at_10_std": 0.07463,
        "nauc_map_at_10_diff1": 0.474548,
        "nauc_map_at_20_max": 0.350042,
        "nauc_map_at_20_std": 0.075925,
        "nauc_map_at_20_diff1": 0.470969,
        "nauc_map_at_100_max": 0.348872,
        "nauc_map_at_100_std": 0.077765,
        "nauc_map_at_100_diff1": 0.468543,
        "nauc_map_at_1000_max": 0.34882,
        "nauc_map_at_1000_std": 0.078076,
        "nauc_map_at_1000_diff1": 0.468235,
        "nauc_recall_at_1_max": 0.433229,
        "nauc_recall_at_1_std": 0.05272,
        "nauc_recall_at_1_diff1": 0.694146,
        "nauc_recall_at_3_max": 0.34645,
        "nauc_recall_at_3_std": 0.080612,
        "nauc_recall_at_3_diff1": 0.429863,
        "nauc_recall_at_5_max": 0.32222,
        "nauc_recall_at_5_std": 0.091314,
        "nauc_recall_at_5_diff1": 0.373002,
        "nauc_recall_at_10_max": 0.286532,
        "nauc_recall_at_10_std": 0.10102,
        "nauc_recall_at_10_diff1": 0.314338,
        "nauc_recall_at_20_max": 0.254315,
        "nauc_recall_at_20_std": 0.109253,
        "nauc_recall_at_20_diff1": 0.264912,
        "nauc_recall_at_100_max": 0.201326,
        "nauc_recall_at_100_std": 0.145151,
        "nauc_recall_at_100_diff1": 0.179968,
        "nauc_recall_at_1000_max": 0.135616,
        "nauc_recall_at_1000_std": 0.178026,
        "nauc_recall_at_1000_diff1": 0.055121,
        "nauc_precision_at_1_max": 0.433229,
        "nauc_precision_at_1_std": 0.05272,
        "nauc_precision_at_1_diff1": 0.694146,
        "nauc_precision_at_3_max": 0.34645,
        "nauc_precision_at_3_std": 0.080612,
        "nauc_precision_at_3_diff1": 0.429863,
        "nauc_precision_at_5_max": 0.32222,
        "nauc_precision_at_5_std": 0.091314,
        "nauc_precision_at_5_diff1": 0.373002,
        "nauc_precision_at_10_max": 0.286532,
        "nauc_precision_at_10_std": 0.10102,
        "nauc_precision_at_10_diff1": 0.314338,
        "nauc_precision_at_20_max": 0.254315,
        "nauc_precision_at_20_std": 0.109253,
        "nauc_precision_at_20_diff1": 0.264912,
        "nauc_precision_at_100_max": 0.201326,
        "nauc_precision_at_100_std": 0.145151,
        "nauc_precision_at_100_diff1": 0.179968,
        "nauc_precision_at_1000_max": 0.135616,
        "nauc_precision_at_1000_std": 0.178026,
        "nauc_precision_at_1000_diff1": 0.055121,
        "nauc_mrr_at_1_max": 0.433229,
        "nauc_mrr_at_1_std": 0.05272,
        "nauc_mrr_at_1_diff1": 0.694146,
        "nauc_mrr_at_3_max": 0.443313,
        "nauc_mrr_at_3_std": 0.066702,
        "nauc_mrr_at_3_diff1": 0.65952,
        "nauc_mrr_at_5_max": 0.444078,
        "nauc_mrr_at_5_std": 0.068542,
        "nauc_mrr_at_5_diff1": 0.656499,
        "nauc_mrr_at_10_max": 0.443617,
        "nauc_mrr_at_10_std": 0.069915,
        "nauc_mrr_at_10_diff1": 0.655073,
        "nauc_mrr_at_20_max": 0.443761,
        "nauc_mrr_at_20_std": 0.070968,
        "nauc_mrr_at_20_diff1": 0.654569,
        "nauc_mrr_at_100_max": 0.443658,
        "nauc_mrr_at_100_std": 0.071312,
        "nauc_mrr_at_100_diff1": 0.654804,
        "nauc_mrr_at_1000_max": 0.4436,
        "nauc_mrr_at_1000_std": 0.071272,
        "nauc_mrr_at_1000_diff1": 0.654842,
        "hit_rate_at_1": 0.53167,
        "hit_rate_at_3": 0.6551,
        "hit_rate_at_5": 0.69507,
        "hit_rate_at_10": 0.7422,
        "hit_rate_at_20": 0.78285,
        "hit_rate_at_100": 0.86226,
        "hit_rate_at_1000": 0.93788,
        "main_score": 0.43572,
        "hf_subset": "default",
        "languages": [
          "eng-Latn"
        ]
      }
    ]
  },
  "evaluation_time": 5434.81702709198,
  "kg_co2_emissions": null,
  "date": null
}