metadata
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- mteb
base_model: sbintuitions/modernbert-ja-310m
language:
- ja
- en
model-index:
- name: retrieva-jp/amber-large
results:
- dataset:
config: en
name: MTEB AmazonCounterfactualClassification (en)
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
split: test
type: mteb/amazon_counterfactual
metrics:
- type: accuracy
value: 73.3433
- type: f1
value: 67.2899
- type: f1_weighted
value: 75.7948
- type: ap
value: 36.123
- type: ap_weighted
value: 36.123
- type: main_score
value: 73.3433
task:
type: Classification
- dataset:
config: default
name: MTEB ArXivHierarchicalClusteringP2P (default)
revision: 0bbdb47bcbe3a90093699aefeed338a0f28a7ee8
split: test
type: mteb/arxiv-clustering-p2p
metrics:
- type: v_measure
value: 53.3936
- type: v_measure_std
value: 3.9726999999999997
- type: main_score
value: 53.3936
task:
type: Clustering
- dataset:
config: default
name: MTEB ArXivHierarchicalClusteringS2S (default)
revision: b73bd54100e5abfa6e3a23dcafb46fe4d2438dc3
split: test
type: mteb/arxiv-clustering-s2s
metrics:
- type: v_measure
value: 51.35999999999999
- type: v_measure_std
value: 4.9623
- type: main_score
value: 51.35999999999999
task:
type: Clustering
- dataset:
config: default
name: MTEB ArguAna (default)
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
split: test
type: mteb/arguana
metrics:
- type: ndcg_at_1
value: 26.743
- type: ndcg_at_3
value: 40.550999999999995
- type: ndcg_at_5
value: 45.550000000000004
- type: ndcg_at_10
value: 51.317
- type: ndcg_at_20
value: 53.96300000000001
- type: ndcg_at_100
value: 55.358
- type: ndcg_at_1000
value: 55.596000000000004
- type: map_at_1
value: 26.743
- type: map_at_3
value: 37.162
- type: map_at_5
value: 39.964
- type: map_at_10
value: 42.355
- type: map_at_20
value: 43.1
- type: map_at_100
value: 43.313
- type: map_at_1000
value: 43.323
- type: recall_at_1
value: 26.743
- type: recall_at_3
value: 50.356
- type: recall_at_5
value: 62.376
- type: recall_at_10
value: 80.156
- type: recall_at_20
value: 90.469
- type: recall_at_100
value: 97.724
- type: recall_at_1000
value: 99.502
- type: precision_at_1
value: 26.743
- type: precision_at_3
value: 16.785
- type: precision_at_5
value: 12.475
- type: precision_at_10
value: 8.016
- type: precision_at_20
value: 4.523
- type: precision_at_100
value: 0.9769999999999999
- type: precision_at_1000
value: 0.1
- type: mrr_at_1
value: 27.169300000000003
- type: mrr_at_3
value: 37.411100000000005
- type: mrr_at_5
value: 40.1102
- type: mrr_at_10
value: 42.493900000000004
- type: mrr_at_20
value: 43.2491
- type: mrr_at_100
value: 43.4578
- type: mrr_at_1000
value: 43.4685
- type: nauc_ndcg_at_1_max
value: -6.2333
- type: nauc_ndcg_at_1_std
value: -7.9555
- type: nauc_ndcg_at_1_diff1
value: 14.512
- type: nauc_ndcg_at_3_max
value: -2.1475999999999997
- type: nauc_ndcg_at_3_std
value: -5.8094
- type: nauc_ndcg_at_3_diff1
value: 9.136
- type: nauc_ndcg_at_5_max
value: -1.7067999999999999
- type: nauc_ndcg_at_5_std
value: -5.018800000000001
- type: nauc_ndcg_at_5_diff1
value: 9.4328
- type: nauc_ndcg_at_10_max
value: 0.7445
- type: nauc_ndcg_at_10_std
value: -3.5482
- type: nauc_ndcg_at_10_diff1
value: 11.1
- type: nauc_ndcg_at_20_max
value: 0.47200000000000003
- type: nauc_ndcg_at_20_std
value: -3.3912999999999998
- type: nauc_ndcg_at_20_diff1
value: 11.2196
- type: nauc_ndcg_at_100_max
value: -1.1079
- type: nauc_ndcg_at_100_std
value: -3.8186999999999998
- type: nauc_ndcg_at_100_diff1
value: 10.9808
- type: nauc_ndcg_at_1000_max
value: -1.3786
- type: nauc_ndcg_at_1000_std
value: -4.3135
- type: nauc_ndcg_at_1000_diff1
value: 10.9463
- type: nauc_map_at_1_max
value: -6.2333
- type: nauc_map_at_1_std
value: -7.9555
- type: nauc_map_at_1_diff1
value: 14.512
- type: nauc_map_at_3_max
value: -3.3211999999999997
- type: nauc_map_at_3_std
value: -6.2437
- type: nauc_map_at_3_diff1
value: 10.1283
- type: nauc_map_at_5_max
value: -3.0931
- type: nauc_map_at_5_std
value: -5.7626
- type: nauc_map_at_5_diff1
value: 10.3327
- type: nauc_map_at_10_max
value: -2.2469
- type: nauc_map_at_10_std
value: -5.2611
- type: nauc_map_at_10_diff1
value: 11.017100000000001
- type: nauc_map_at_20_max
value: -2.358
- type: nauc_map_at_20_std
value: -5.255
- type: nauc_map_at_20_diff1
value: 11.0437
- type: nauc_map_at_100_max
value: -2.5533
- type: nauc_map_at_100_std
value: -5.2893
- type: nauc_map_at_100_diff1
value: 11.018600000000001
- type: nauc_map_at_1000_max
value: -2.5621
- type: nauc_map_at_1000_std
value: -5.3072
- type: nauc_map_at_1000_diff1
value: 11.0196
- type: nauc_recall_at_1_max
value: -6.2333
- type: nauc_recall_at_1_std
value: -7.9555
- type: nauc_recall_at_1_diff1
value: 14.512
- type: nauc_recall_at_3_max
value: 1.2414
- type: nauc_recall_at_3_std
value: -4.6148
- type: nauc_recall_at_3_diff1
value: 6.45
- type: nauc_recall_at_5_max
value: 2.7998
- type: nauc_recall_at_5_std
value: -2.6652
- type: nauc_recall_at_5_diff1
value: 6.7526
- type: nauc_recall_at_10_max
value: 17.322100000000002
- type: nauc_recall_at_10_std
value: 5.9032
- type: nauc_recall_at_10_diff1
value: 12.881899999999998
- type: nauc_recall_at_20_max
value: 29.6782
- type: nauc_recall_at_20_std
value: 16.4192
- type: nauc_recall_at_20_diff1
value: 15.8604
- type: nauc_recall_at_100_max
value: 28.772599999999997
- type: nauc_recall_at_100_std
value: 48.7738
- type: nauc_recall_at_100_diff1
value: 15.8629
- type: nauc_recall_at_1000_max
value: 31.0293
- type: nauc_recall_at_1000_std
value: 52.7185
- type: nauc_recall_at_1000_diff1
value: 14.3646
- type: nauc_precision_at_1_max
value: -6.2333
- type: nauc_precision_at_1_std
value: -7.9555
- type: nauc_precision_at_1_diff1
value: 14.512
- type: nauc_precision_at_3_max
value: 1.2414
- type: nauc_precision_at_3_std
value: -4.6148
- type: nauc_precision_at_3_diff1
value: 6.45
- type: nauc_precision_at_5_max
value: 2.7998
- type: nauc_precision_at_5_std
value: -2.6652
- type: nauc_precision_at_5_diff1
value: 6.7526
- type: nauc_precision_at_10_max
value: 17.322100000000002
- type: nauc_precision_at_10_std
value: 5.9032
- type: nauc_precision_at_10_diff1
value: 12.881899999999998
- type: nauc_precision_at_20_max
value: 29.6782
- type: nauc_precision_at_20_std
value: 16.4192
- type: nauc_precision_at_20_diff1
value: 15.8604
- type: nauc_precision_at_100_max
value: 28.772599999999997
- type: nauc_precision_at_100_std
value: 48.7738
- type: nauc_precision_at_100_diff1
value: 15.8629
- type: nauc_precision_at_1000_max
value: 31.0293
- type: nauc_precision_at_1000_std
value: 52.7185
- type: nauc_precision_at_1000_diff1
value: 14.3646
- type: nauc_mrr_at_1_max
value: -6.0675
- type: nauc_mrr_at_1_std
value: -7.0283999999999995
- type: nauc_mrr_at_1_diff1
value: 13.1112
- type: nauc_mrr_at_3_max
value: -3.8593
- type: nauc_mrr_at_3_std
value: -5.9281
- type: nauc_mrr_at_3_diff1
value: 8.807
- type: nauc_mrr_at_5_max
value: -3.6332999999999998
- type: nauc_mrr_at_5_std
value: -5.3816999999999995
- type: nauc_mrr_at_5_diff1
value: 9.0466
- type: nauc_mrr_at_10_max
value: -2.8869
- type: nauc_mrr_at_10_std
value: -4.9811000000000005
- type: nauc_mrr_at_10_diff1
value: 9.589699999999999
- type: nauc_mrr_at_20_max
value: -2.9609
- type: nauc_mrr_at_20_std
value: -4.9429
- type: nauc_mrr_at_20_diff1
value: 9.6326
- type: nauc_mrr_at_100_max
value: -3.15
- type: nauc_mrr_at_100_std
value: -4.9643
- type: nauc_mrr_at_100_diff1
value: 9.6056
- type: nauc_mrr_at_1000_max
value: -3.159
- type: nauc_mrr_at_1000_std
value: -4.982
- type: nauc_mrr_at_1000_diff1
value: 9.6061
- type: main_score
value: 51.317
task:
type: Retrieval
- dataset:
config: default
name: MTEB AskUbuntuDupQuestions (default)
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
split: test
type: mteb/askubuntudupquestions-reranking
metrics:
- type: map
value: 58.0233
- type: mrr
value: 70.5882
- type: nAUC_map_max
value: 20.8533
- type: nAUC_map_std
value: 12.612300000000001
- type: nAUC_map_diff1
value: 1.3859
- type: nAUC_mrr_max
value: 33.692
- type: nAUC_mrr_std
value: 14.176400000000001
- type: nAUC_mrr_diff1
value: 14.2379
- type: main_score
value: 58.0233
task:
type: Reranking
- dataset:
config: default
name: MTEB BIOSSES (default)
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
split: test
type: mteb/biosses-sts
metrics:
- type: pearson
value: 83.4314
- type: spearman
value: 78.7367
- type: cosine_pearson
value: 83.4314
- type: cosine_spearman
value: 78.7367
- type: manhattan_pearson
value: 82.1388
- type: manhattan_spearman
value: 78.747
- type: euclidean_pearson
value: 82.1716
- type: euclidean_spearman
value: 78.7367
- type: main_score
value: 78.7367
task:
type: STS
- dataset:
config: default
name: MTEB Banking77Classification (default)
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
split: test
type: mteb/banking77
metrics:
- type: accuracy
value: 76.8961
- type: f1
value: 75.8746
- type: f1_weighted
value: 75.8746
- type: main_score
value: 76.8961
task:
type: Classification
- dataset:
config: default
name: MTEB BiorxivClusteringP2P.v2 (default)
revision: f5dbc242e11dd8e24def4c4268607a49e02946dc
split: test
type: mteb/biorxiv-clustering-p2p
metrics:
- type: v_measure
value: 36.2676
- type: v_measure_std
value: 0.8959
- type: main_score
value: 36.2676
task:
type: Clustering
- dataset:
config: default
name: MTEB CQADupstackGamingRetrieval (default)
revision: 4885aa143210c98657558c04aaf3dc47cfb54340
split: test
type: mteb/cqadupstack-gaming
metrics:
- type: ndcg_at_1
value: 36.489
- type: ndcg_at_3
value: 42.821999999999996
- type: ndcg_at_5
value: 44.915
- type: ndcg_at_10
value: 47.74
- type: ndcg_at_20
value: 49.613
- type: ndcg_at_100
value: 52.406
- type: ndcg_at_1000
value: 53.984
- type: map_at_1
value: 31.812
- type: map_at_3
value: 39.568
- type: map_at_5
value: 40.976
- type: map_at_10
value: 42.36
- type: map_at_20
value: 42.978
- type: map_at_100
value: 43.418
- type: map_at_1000
value: 43.488
- type: recall_at_1
value: 31.812
- type: recall_at_3
value: 47.199999999999996
- type: recall_at_5
value: 52.361999999999995
- type: recall_at_10
value: 60.535000000000004
- type: recall_at_20
value: 67.51899999999999
- type: recall_at_100
value: 81.432
- type: recall_at_1000
value: 92.935
- type: precision_at_1
value: 36.489
- type: precision_at_3
value: 19.269
- type: precision_at_5
value: 13.116
- type: precision_at_10
value: 7.818
- type: precision_at_20
value: 4.4670000000000005
- type: precision_at_100
value: 1.107
- type: precision_at_1000
value: 0.13
- type: mrr_at_1
value: 36.489
- type: mrr_at_3
value: 43.2602
- type: mrr_at_5
value: 44.4514
- type: mrr_at_10
value: 45.510600000000004
- type: mrr_at_20
value: 45.9739
- type: mrr_at_100
value: 46.3047
- type: mrr_at_1000
value: 46.3441
- type: nauc_ndcg_at_1_max
value: 32.7997
- type: nauc_ndcg_at_1_std
value: -6.2432
- type: nauc_ndcg_at_1_diff1
value: 51.348499999999994
- type: nauc_ndcg_at_3_max
value: 30.573299999999996
- type: nauc_ndcg_at_3_std
value: -5.183999999999999
- type: nauc_ndcg_at_3_diff1
value: 45.3705
- type: nauc_ndcg_at_5_max
value: 30.7409
- type: nauc_ndcg_at_5_std
value: -4.0355
- type: nauc_ndcg_at_5_diff1
value: 44.6049
- type: nauc_ndcg_at_10_max
value: 31.533699999999996
- type: nauc_ndcg_at_10_std
value: -2.8769
- type: nauc_ndcg_at_10_diff1
value: 44.3542
- type: nauc_ndcg_at_20_max
value: 32.0732
- type: nauc_ndcg_at_20_std
value: -1.872
- type: nauc_ndcg_at_20_diff1
value: 44.2475
- type: nauc_ndcg_at_100_max
value: 32.671
- type: nauc_ndcg_at_100_std
value: -1.1646999999999998
- type: nauc_ndcg_at_100_diff1
value: 44.2262
- type: nauc_ndcg_at_1000_max
value: 32.9504
- type: nauc_ndcg_at_1000_std
value: -1.0373999999999999
- type: nauc_ndcg_at_1000_diff1
value: 44.507999999999996
- type: nauc_map_at_1_max
value: 29.0809
- type: nauc_map_at_1_std
value: -6.367000000000001
- type: nauc_map_at_1_diff1
value: 51.906200000000005
- type: nauc_map_at_3_max
value: 30.127
- type: nauc_map_at_3_std
value: -6.1406
- type: nauc_map_at_3_diff1
value: 47.131099999999996
- type: nauc_map_at_5_max
value: 30.2421
- type: nauc_map_at_5_std
value: -5.4726
- type: nauc_map_at_5_diff1
value: 46.6666
- type: nauc_map_at_10_max
value: 30.826500000000003
- type: nauc_map_at_10_std
value: -4.8187
- type: nauc_map_at_10_diff1
value: 46.5314
- type: nauc_map_at_20_max
value: 31.1207
- type: nauc_map_at_20_std
value: -4.3886
- type: nauc_map_at_20_diff1
value: 46.4738
- type: nauc_map_at_100_max
value: 31.2728
- type: nauc_map_at_100_std
value: -4.2386
- type: nauc_map_at_100_diff1
value: 46.4656
- type: nauc_map_at_1000_max
value: 31.307499999999997
- type: nauc_map_at_1000_std
value: -4.213900000000001
- type: nauc_map_at_1000_diff1
value: 46.4827
- type: nauc_recall_at_1_max
value: 29.0809
- type: nauc_recall_at_1_std
value: -6.367000000000001
- type: nauc_recall_at_1_diff1
value: 51.906200000000005
- type: nauc_recall_at_3_max
value: 28.213
- type: nauc_recall_at_3_std
value: -4.8443
- type: nauc_recall_at_3_diff1
value: 40.3982
- type: nauc_recall_at_5_max
value: 28.038200000000003
- type: nauc_recall_at_5_std
value: -1.8623
- type: nauc_recall_at_5_diff1
value: 38.1102
- type: nauc_recall_at_10_max
value: 29.4193
- type: nauc_recall_at_10_std
value: 1.821
- type: nauc_recall_at_10_diff1
value: 36.262899999999995
- type: nauc_recall_at_20_max
value: 31.0056
- type: nauc_recall_at_20_std
value: 6.6465
- type: nauc_recall_at_20_diff1
value: 34.9446
- type: nauc_recall_at_100_max
value: 33.3618
- type: nauc_recall_at_100_std
value: 16.1202
- type: nauc_recall_at_100_diff1
value: 29.264699999999998
- type: nauc_recall_at_1000_max
value: 40.03
- type: nauc_recall_at_1000_std
value: 40.261
- type: nauc_recall_at_1000_diff1
value: 19.1627
- type: nauc_precision_at_1_max
value: 32.7997
- type: nauc_precision_at_1_std
value: -6.2432
- type: nauc_precision_at_1_diff1
value: 51.348499999999994
- type: nauc_precision_at_3_max
value: 30.527900000000002
- type: nauc_precision_at_3_std
value: -2.2055000000000002
- type: nauc_precision_at_3_diff1
value: 31.7838
- type: nauc_precision_at_5_max
value: 29.078
- type: nauc_precision_at_5_std
value: 1.7718
- type: nauc_precision_at_5_diff1
value: 26.0635
- type: nauc_precision_at_10_max
value: 28.903499999999998
- type: nauc_precision_at_10_std
value: 7.321
- type: nauc_precision_at_10_diff1
value: 19.4822
- type: nauc_precision_at_20_max
value: 29.5105
- type: nauc_precision_at_20_std
value: 12.931999999999999
- type: nauc_precision_at_20_diff1
value: 14.0846
- type: nauc_precision_at_100_max
value: 27.9082
- type: nauc_precision_at_100_std
value: 19.1086
- type: nauc_precision_at_100_diff1
value: 4.7168
- type: nauc_precision_at_1000_max
value: 24.2535
- type: nauc_precision_at_1000_std
value: 19.430500000000002
- type: nauc_precision_at_1000_diff1
value: -1.262
- type: nauc_mrr_at_1_max
value: 32.7997
- type: nauc_mrr_at_1_std
value: -6.2432
- type: nauc_mrr_at_1_diff1
value: 51.348499999999994
- type: nauc_mrr_at_3_max
value: 32.4347
- type: nauc_mrr_at_3_std
value: -5.0054
- type: nauc_mrr_at_3_diff1
value: 46.2024
- type: nauc_mrr_at_5_max
value: 32.7235
- type: nauc_mrr_at_5_std
value: -4.239
- type: nauc_mrr_at_5_diff1
value: 46.0496
- type: nauc_mrr_at_10_max
value: 32.7692
- type: nauc_mrr_at_10_std
value: -3.9257
- type: nauc_mrr_at_10_diff1
value: 46.009699999999995
- type: nauc_mrr_at_20_max
value: 32.8372
- type: nauc_mrr_at_20_std
value: -3.7516000000000003
- type: nauc_mrr_at_20_diff1
value: 45.9608
- type: nauc_mrr_at_100_max
value: 32.845200000000006
- type: nauc_mrr_at_100_std
value: -3.7661
- type: nauc_mrr_at_100_diff1
value: 45.988600000000005
- type: nauc_mrr_at_1000_max
value: 32.8484
- type: nauc_mrr_at_1000_std
value: -3.7553
- type: nauc_mrr_at_1000_diff1
value: 45.9936
- type: main_score
value: 47.74
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackUnixRetrieval (default)
revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53
split: test
type: mteb/cqadupstack-unix
metrics:
- type: ndcg_at_1
value: 24.813
- type: ndcg_at_3
value: 28.232000000000003
- type: ndcg_at_5
value: 30.384
- type: ndcg_at_10
value: 32.482
- type: ndcg_at_20
value: 34.627
- type: ndcg_at_100
value: 38.275
- type: ndcg_at_1000
value: 41.07
- type: map_at_1
value: 21.176000000000002
- type: map_at_3
value: 25.75
- type: map_at_5
value: 27.169999999999998
- type: map_at_10
value: 28.081
- type: map_at_20
value: 28.698
- type: map_at_100
value: 29.264000000000003
- type: map_at_1000
value: 29.38
- type: recall_at_1
value: 21.176000000000002
- type: recall_at_3
value: 30.842000000000002
- type: recall_at_5
value: 36.265
- type: recall_at_10
value: 42.531
- type: recall_at_20
value: 50.314
- type: recall_at_100
value: 68.13900000000001
- type: recall_at_1000
value: 88.252
- type: precision_at_1
value: 24.813
- type: precision_at_3
value: 12.687000000000001
- type: precision_at_5
value: 9.049
- type: precision_at_10
value: 5.401
- type: precision_at_20
value: 3.274
- type: precision_at_100
value: 0.9329999999999999
- type: precision_at_1000
value: 0.129
- type: mrr_at_1
value: 24.813399999999998
- type: mrr_at_3
value: 29.446499999999997
- type: mrr_at_5
value: 30.747799999999998
- type: mrr_at_10
value: 31.6057
- type: mrr_at_20
value: 32.2122
- type: mrr_at_100
value: 32.6663
- type: mrr_at_1000
value: 32.734
- type: nauc_ndcg_at_1_max
value: 34.191
- type: nauc_ndcg_at_1_std
value: 0.2555
- type: nauc_ndcg_at_1_diff1
value: 55.12590000000001
- type: nauc_ndcg_at_3_max
value: 31.232599999999998
- type: nauc_ndcg_at_3_std
value: 2.2289
- type: nauc_ndcg_at_3_diff1
value: 48.0837
- type: nauc_ndcg_at_5_max
value: 30.962400000000002
- type: nauc_ndcg_at_5_std
value: 3.4008999999999996
- type: nauc_ndcg_at_5_diff1
value: 46.4811
- type: nauc_ndcg_at_10_max
value: 31.446600000000004
- type: nauc_ndcg_at_10_std
value: 4.1986
- type: nauc_ndcg_at_10_diff1
value: 45.393499999999996
- type: nauc_ndcg_at_20_max
value: 32.1259
- type: nauc_ndcg_at_20_std
value: 4.8191999999999995
- type: nauc_ndcg_at_20_diff1
value: 45.5339
- type: nauc_ndcg_at_100_max
value: 31.741799999999998
- type: nauc_ndcg_at_100_std
value: 6.5873
- type: nauc_ndcg_at_100_diff1
value: 45.1915
- type: nauc_ndcg_at_1000_max
value: 32.1615
- type: nauc_ndcg_at_1000_std
value: 6.5815
- type: nauc_ndcg_at_1000_diff1
value: 45.4801
- type: nauc_map_at_1_max
value: 33.592499999999994
- type: nauc_map_at_1_std
value: -0.8531000000000001
- type: nauc_map_at_1_diff1
value: 56.7096
- type: nauc_map_at_3_max
value: 31.6479
- type: nauc_map_at_3_std
value: 1.2515999999999998
- type: nauc_map_at_3_diff1
value: 50.4096
- type: nauc_map_at_5_max
value: 31.3468
- type: nauc_map_at_5_std
value: 1.9414
- type: nauc_map_at_5_diff1
value: 49.3593
- type: nauc_map_at_10_max
value: 31.494
- type: nauc_map_at_10_std
value: 2.298
- type: nauc_map_at_10_diff1
value: 48.809799999999996
- type: nauc_map_at_20_max
value: 31.724000000000004
- type: nauc_map_at_20_std
value: 2.5317
- type: nauc_map_at_20_diff1
value: 48.825
- type: nauc_map_at_100_max
value: 31.671100000000003
- type: nauc_map_at_100_std
value: 2.8145
- type: nauc_map_at_100_diff1
value: 48.7271
- type: nauc_map_at_1000_max
value: 31.689
- type: nauc_map_at_1000_std
value: 2.8294
- type: nauc_map_at_1000_diff1
value: 48.7329
- type: nauc_recall_at_1_max
value: 33.592499999999994
- type: nauc_recall_at_1_std
value: -0.8531000000000001
- type: nauc_recall_at_1_diff1
value: 56.7096
- type: nauc_recall_at_3_max
value: 29.4439
- type: nauc_recall_at_3_std
value: 3.5302
- type: nauc_recall_at_3_diff1
value: 43.5153
- type: nauc_recall_at_5_max
value: 28.3517
- type: nauc_recall_at_5_std
value: 6.458500000000001
- type: nauc_recall_at_5_diff1
value: 39.5587
- type: nauc_recall_at_10_max
value: 29.2991
- type: nauc_recall_at_10_std
value: 8.5119
- type: nauc_recall_at_10_diff1
value: 36.1111
- type: nauc_recall_at_20_max
value: 30.984099999999998
- type: nauc_recall_at_20_std
value: 10.668
- type: nauc_recall_at_20_diff1
value: 36.5424
- type: nauc_recall_at_100_max
value: 28.0852
- type: nauc_recall_at_100_std
value: 21.938
- type: nauc_recall_at_100_diff1
value: 32.5436
- type: nauc_recall_at_1000_max
value: 33.8843
- type: nauc_recall_at_1000_std
value: 40.677099999999996
- type: nauc_recall_at_1000_diff1
value: 28.95
- type: nauc_precision_at_1_max
value: 34.191
- type: nauc_precision_at_1_std
value: 0.2555
- type: nauc_precision_at_1_diff1
value: 55.12590000000001
- type: nauc_precision_at_3_max
value: 28.9812
- type: nauc_precision_at_3_std
value: 5.745299999999999
- type: nauc_precision_at_3_diff1
value: 38.4525
- type: nauc_precision_at_5_max
value: 27.060200000000002
- type: nauc_precision_at_5_std
value: 8.4729
- type: nauc_precision_at_5_diff1
value: 32.9266
- type: nauc_precision_at_10_max
value: 25.7858
- type: nauc_precision_at_10_std
value: 9.8897
- type: nauc_precision_at_10_diff1
value: 26.1021
- type: nauc_precision_at_20_max
value: 26.243499999999997
- type: nauc_precision_at_20_std
value: 12.251
- type: nauc_precision_at_20_diff1
value: 21.073800000000002
- type: nauc_precision_at_100_max
value: 14.847199999999999
- type: nauc_precision_at_100_std
value: 18.3256
- type: nauc_precision_at_100_diff1
value: 6.4467
- type: nauc_precision_at_1000_max
value: 3.5059
- type: nauc_precision_at_1000_std
value: 12.027000000000001
- type: nauc_precision_at_1000_diff1
value: -10.6274
- type: nauc_mrr_at_1_max
value: 34.191
- type: nauc_mrr_at_1_std
value: 0.2555
- type: nauc_mrr_at_1_diff1
value: 55.12590000000001
- type: nauc_mrr_at_3_max
value: 32.2999
- type: nauc_mrr_at_3_std
value: 1.8591
- type: nauc_mrr_at_3_diff1
value: 48.5279
- type: nauc_mrr_at_5_max
value: 32.257799999999996
- type: nauc_mrr_at_5_std
value: 2.8365
- type: nauc_mrr_at_5_diff1
value: 47.6701
- type: nauc_mrr_at_10_max
value: 32.419399999999996
- type: nauc_mrr_at_10_std
value: 3.0626
- type: nauc_mrr_at_10_diff1
value: 47.1638
- type: nauc_mrr_at_20_max
value: 32.5848
- type: nauc_mrr_at_20_std
value: 3.0636
- type: nauc_mrr_at_20_diff1
value: 47.218199999999996
- type: nauc_mrr_at_100_max
value: 32.587500000000006
- type: nauc_mrr_at_100_std
value: 3.2354000000000003
- type: nauc_mrr_at_100_diff1
value: 47.295
- type: nauc_mrr_at_1000_max
value: 32.5994
- type: nauc_mrr_at_1000_std
value: 3.2392999999999996
- type: nauc_mrr_at_1000_diff1
value: 47.3153
- type: main_score
value: 32.482
task:
type: Retrieval
- dataset:
config: default
name: MTEB ClimateFEVERHardNegatives (default)
revision: 3a309e201f3c2c4b13bd4a367a8f37eee2ec1d21
split: test
type: mteb/ClimateFEVER_test_top_250_only_w_correct-v2
metrics:
- type: ndcg_at_1
value: 14.099999999999998
- type: ndcg_at_3
value: 14.298
- type: ndcg_at_5
value: 16.078
- type: ndcg_at_10
value: 19.043
- type: ndcg_at_20
value: 21.663
- type: ndcg_at_100
value: 26.514
- type: ndcg_at_1000
value: 31.15
- type: map_at_1
value: 6.518
- type: map_at_3
value: 10.218
- type: map_at_5
value: 11.450000000000001
- type: map_at_10
value: 12.701
- type: map_at_20
value: 13.502
- type: map_at_100
value: 14.329
- type: map_at_1000
value: 14.560999999999998
- type: recall_at_1
value: 6.518
- type: recall_at_3
value: 14.197000000000001
- type: recall_at_5
value: 18.443
- type: recall_at_10
value: 25.233
- type: recall_at_20
value: 32.83
- type: recall_at_100
value: 51.82
- type: recall_at_1000
value: 78.238
- type: precision_at_1
value: 14.099999999999998
- type: precision_at_3
value: 10.767
- type: precision_at_5
value: 8.780000000000001
- type: precision_at_10
value: 6.2700000000000005
- type: precision_at_20
value: 4.22
- type: precision_at_100
value: 1.422
- type: precision_at_1000
value: 0.22899999999999998
- type: mrr_at_1
value: 14.099999999999998
- type: mrr_at_3
value: 21.099999999999998
- type: mrr_at_5
value: 22.855
- type: mrr_at_10
value: 24.427799999999998
- type: mrr_at_20
value: 25.1863
- type: mrr_at_100
value: 25.682899999999997
- type: mrr_at_1000
value: 25.749499999999998
- type: nauc_ndcg_at_1_max
value: 17.3767
- type: nauc_ndcg_at_1_std
value: 9.2458
- type: nauc_ndcg_at_1_diff1
value: 16.304199999999998
- type: nauc_ndcg_at_3_max
value: 25.369999999999997
- type: nauc_ndcg_at_3_std
value: 14.0289
- type: nauc_ndcg_at_3_diff1
value: 13.3376
- type: nauc_ndcg_at_5_max
value: 25.8672
- type: nauc_ndcg_at_5_std
value: 16.2133
- type: nauc_ndcg_at_5_diff1
value: 12.6441
- type: nauc_ndcg_at_10_max
value: 27.3825
- type: nauc_ndcg_at_10_std
value: 19.1307
- type: nauc_ndcg_at_10_diff1
value: 12.8491
- type: nauc_ndcg_at_20_max
value: 28.402300000000004
- type: nauc_ndcg_at_20_std
value: 19.024
- type: nauc_ndcg_at_20_diff1
value: 12.4925
- type: nauc_ndcg_at_100_max
value: 31.1216
- type: nauc_ndcg_at_100_std
value: 21.588099999999997
- type: nauc_ndcg_at_100_diff1
value: 11.2177
- type: nauc_ndcg_at_1000_max
value: 31.4444
- type: nauc_ndcg_at_1000_std
value: 21.7737
- type: nauc_ndcg_at_1000_diff1
value: 11.9895
- type: nauc_map_at_1_max
value: 18.0146
- type: nauc_map_at_1_std
value: 10.992799999999999
- type: nauc_map_at_1_diff1
value: 18.0204
- type: nauc_map_at_3_max
value: 23.6696
- type: nauc_map_at_3_std
value: 12.947600000000001
- type: nauc_map_at_3_diff1
value: 14.0274
- type: nauc_map_at_5_max
value: 24.5524
- type: nauc_map_at_5_std
value: 15.2125
- type: nauc_map_at_5_diff1
value: 13.4579
- type: nauc_map_at_10_max
value: 25.3924
- type: nauc_map_at_10_std
value: 16.769000000000002
- type: nauc_map_at_10_diff1
value: 13.725999999999999
- type: nauc_map_at_20_max
value: 25.9845
- type: nauc_map_at_20_std
value: 16.9583
- type: nauc_map_at_20_diff1
value: 13.5333
- type: nauc_map_at_100_max
value: 26.674300000000002
- type: nauc_map_at_100_std
value: 17.769099999999998
- type: nauc_map_at_100_diff1
value: 13.095399999999998
- type: nauc_map_at_1000_max
value: 26.7523
- type: nauc_map_at_1000_std
value: 17.8361
- type: nauc_map_at_1000_diff1
value: 13.153799999999999
- type: nauc_recall_at_1_max
value: 18.0146
- type: nauc_recall_at_1_std
value: 10.992799999999999
- type: nauc_recall_at_1_diff1
value: 18.0204
- type: nauc_recall_at_3_max
value: 26.7331
- type: nauc_recall_at_3_std
value: 13.608799999999999
- type: nauc_recall_at_3_diff1
value: 10.7863
- type: nauc_recall_at_5_max
value: 26.235000000000003
- type: nauc_recall_at_5_std
value: 16.8335
- type: nauc_recall_at_5_diff1
value: 9.4389
- type: nauc_recall_at_10_max
value: 27.0233
- type: nauc_recall_at_10_std
value: 20.7401
- type: nauc_recall_at_10_diff1
value: 9.589
- type: nauc_recall_at_20_max
value: 27.3646
- type: nauc_recall_at_20_std
value: 18.7408
- type: nauc_recall_at_20_diff1
value: 8.3524
- type: nauc_recall_at_100_max
value: 31.565900000000003
- type: nauc_recall_at_100_std
value: 22.7502
- type: nauc_recall_at_100_diff1
value: 3.5892
- type: nauc_recall_at_1000_max
value: 35.854
- type: nauc_recall_at_1000_std
value: 25.2455
- type: nauc_recall_at_1000_diff1
value: 5.25
- type: nauc_precision_at_1_max
value: 17.3767
- type: nauc_precision_at_1_std
value: 9.2458
- type: nauc_precision_at_1_diff1
value: 16.304199999999998
- type: nauc_precision_at_3_max
value: 29.8514
- type: nauc_precision_at_3_std
value: 17.3344
- type: nauc_precision_at_3_diff1
value: 12.7965
- type: nauc_precision_at_5_max
value: 29.9122
- type: nauc_precision_at_5_std
value: 22.0638
- type: nauc_precision_at_5_diff1
value: 10.9401
- type: nauc_precision_at_10_max
value: 31.2731
- type: nauc_precision_at_10_std
value: 26.3173
- type: nauc_precision_at_10_diff1
value: 10.0175
- type: nauc_precision_at_20_max
value: 30.667
- type: nauc_precision_at_20_std
value: 23.4944
- type: nauc_precision_at_20_diff1
value: 8.1778
- type: nauc_precision_at_100_max
value: 30.5903
- type: nauc_precision_at_100_std
value: 25.1048
- type: nauc_precision_at_100_diff1
value: 3.2702
- type: nauc_precision_at_1000_max
value: 19.7081
- type: nauc_precision_at_1000_std
value: 17.7857
- type: nauc_precision_at_1000_diff1
value: 2.1989
- type: nauc_mrr_at_1_max
value: 17.3767
- type: nauc_mrr_at_1_std
value: 9.2458
- type: nauc_mrr_at_1_diff1
value: 16.304199999999998
- type: nauc_mrr_at_3_max
value: 24.1474
- type: nauc_mrr_at_3_std
value: 13.4213
- type: nauc_mrr_at_3_diff1
value: 14.266300000000001
- type: nauc_mrr_at_5_max
value: 23.8946
- type: nauc_mrr_at_5_std
value: 13.9119
- type: nauc_mrr_at_5_diff1
value: 13.9569
- type: nauc_mrr_at_10_max
value: 24.5762
- type: nauc_mrr_at_10_std
value: 15.343699999999998
- type: nauc_mrr_at_10_diff1
value: 13.8355
- type: nauc_mrr_at_20_max
value: 24.7856
- type: nauc_mrr_at_20_std
value: 15.1997
- type: nauc_mrr_at_20_diff1
value: 13.9615
- type: nauc_mrr_at_100_max
value: 24.913899999999998
- type: nauc_mrr_at_100_std
value: 15.2973
- type: nauc_mrr_at_100_diff1
value: 13.9054
- type: nauc_mrr_at_1000_max
value: 24.8602
- type: nauc_mrr_at_1000_std
value: 15.264800000000001
- type: nauc_mrr_at_1000_diff1
value: 13.888200000000001
- type: main_score
value: 19.043
task:
type: Retrieval
- dataset:
config: default
name: MTEB FEVERHardNegatives (default)
revision: 080c9ed6267b65029207906e815d44a9240bafca
split: test
type: mteb/FEVER_test_top_250_only_w_correct-v2
metrics:
- type: ndcg_at_1
value: 47.099999999999994
- type: ndcg_at_3
value: 57.99100000000001
- type: ndcg_at_5
value: 60.948
- type: ndcg_at_10
value: 63.754999999999995
- type: ndcg_at_20
value: 65.649
- type: ndcg_at_100
value: 67.041
- type: ndcg_at_1000
value: 67.422
- type: map_at_1
value: 44.85
- type: map_at_3
value: 54.299
- type: map_at_5
value: 55.986000000000004
- type: map_at_10
value: 57.166
- type: map_at_20
value: 57.709999999999994
- type: map_at_100
value: 57.94200000000001
- type: map_at_1000
value: 57.964000000000006
- type: recall_at_1
value: 44.85
- type: recall_at_3
value: 65.917
- type: recall_at_5
value: 73.098
- type: recall_at_10
value: 81.54
- type: recall_at_20
value: 88.725
- type: recall_at_100
value: 95.53
- type: recall_at_1000
value: 97.989
- type: precision_at_1
value: 47.099999999999994
- type: precision_at_3
value: 23.333000000000002
- type: precision_at_5
value: 15.58
- type: precision_at_10
value: 8.73
- type: precision_at_20
value: 4.784999999999999
- type: precision_at_100
value: 1.048
- type: precision_at_1000
value: 0.11
- type: mrr_at_1
value: 47.099999999999994
- type: mrr_at_3
value: 56.9833
- type: mrr_at_5
value: 58.6933
- type: mrr_at_10
value: 59.913700000000006
- type: mrr_at_20
value: 60.4366
- type: mrr_at_100
value: 60.6124
- type: mrr_at_1000
value: 60.616800000000005
- type: nauc_ndcg_at_1_max
value: 14.541100000000002
- type: nauc_ndcg_at_1_std
value: -20.9154
- type: nauc_ndcg_at_1_diff1
value: 51.640699999999995
- type: nauc_ndcg_at_3_max
value: 16.5821
- type: nauc_ndcg_at_3_std
value: -21.64
- type: nauc_ndcg_at_3_diff1
value: 43.948
- type: nauc_ndcg_at_5_max
value: 16.4971
- type: nauc_ndcg_at_5_std
value: -20.849500000000003
- type: nauc_ndcg_at_5_diff1
value: 43.0631
- type: nauc_ndcg_at_10_max
value: 15.839400000000001
- type: nauc_ndcg_at_10_std
value: -21.0278
- type: nauc_ndcg_at_10_diff1
value: 43.7884
- type: nauc_ndcg_at_20_max
value: 16.1081
- type: nauc_ndcg_at_20_std
value: -19.7606
- type: nauc_ndcg_at_20_diff1
value: 44.4262
- type: nauc_ndcg_at_100_max
value: 15.998899999999999
- type: nauc_ndcg_at_100_std
value: -19.619500000000002
- type: nauc_ndcg_at_100_diff1
value: 44.5225
- type: nauc_ndcg_at_1000_max
value: 16.069
- type: nauc_ndcg_at_1000_std
value: -19.4906
- type: nauc_ndcg_at_1000_diff1
value: 44.4003
- type: nauc_map_at_1_max
value: 12.4983
- type: nauc_map_at_1_std
value: -19.7
- type: nauc_map_at_1_diff1
value: 48.598400000000005
- type: nauc_map_at_3_max
value: 15.2542
- type: nauc_map_at_3_std
value: -20.7008
- type: nauc_map_at_3_diff1
value: 44.5092
- type: nauc_map_at_5_max
value: 15.273700000000002
- type: nauc_map_at_5_std
value: -20.3894
- type: nauc_map_at_5_diff1
value: 44.1826
- type: nauc_map_at_10_max
value: 15.004700000000001
- type: nauc_map_at_10_std
value: -20.4971
- type: nauc_map_at_10_diff1
value: 44.428200000000004
- type: nauc_map_at_20_max
value: 15.065000000000001
- type: nauc_map_at_20_std
value: -20.189799999999998
- type: nauc_map_at_20_diff1
value: 44.5691
- type: nauc_map_at_100_max
value: 15.0534
- type: nauc_map_at_100_std
value: -20.1541
- type: nauc_map_at_100_diff1
value: 44.6102
- type: nauc_map_at_1000_max
value: 15.058399999999999
- type: nauc_map_at_1000_std
value: -20.1422
- type: nauc_map_at_1000_diff1
value: 44.6041
- type: nauc_recall_at_1_max
value: 12.4983
- type: nauc_recall_at_1_std
value: -19.7
- type: nauc_recall_at_1_diff1
value: 48.598400000000005
- type: nauc_recall_at_3_max
value: 18.0779
- type: nauc_recall_at_3_std
value: -21.8811
- type: nauc_recall_at_3_diff1
value: 37.594300000000004
- type: nauc_recall_at_5_max
value: 18.074299999999997
- type: nauc_recall_at_5_std
value: -19.465
- type: nauc_recall_at_5_diff1
value: 33.3804
- type: nauc_recall_at_10_max
value: 15.118200000000002
- type: nauc_recall_at_10_std
value: -19.464000000000002
- type: nauc_recall_at_10_diff1
value: 33.4801
- type: nauc_recall_at_20_max
value: 17.180500000000002
- type: nauc_recall_at_20_std
value: -7.6669
- type: nauc_recall_at_20_diff1
value: 33.8144
- type: nauc_recall_at_100_max
value: 14.7357
- type: nauc_recall_at_100_std
value: 10.3128
- type: nauc_recall_at_100_diff1
value: 22.4137
- type: nauc_recall_at_1000_max
value: 22.8095
- type: nauc_recall_at_1000_std
value: 48.4682
- type: nauc_recall_at_1000_diff1
value: -2.0866
- type: nauc_precision_at_1_max
value: 14.541100000000002
- type: nauc_precision_at_1_std
value: -20.9154
- type: nauc_precision_at_1_diff1
value: 51.640699999999995
- type: nauc_precision_at_3_max
value: 20.513
- type: nauc_precision_at_3_std
value: -25.9636
- type: nauc_precision_at_3_diff1
value: 40.8703
- type: nauc_precision_at_5_max
value: 20.955
- type: nauc_precision_at_5_std
value: -24.482400000000002
- type: nauc_precision_at_5_diff1
value: 36.600500000000004
- type: nauc_precision_at_10_max
value: 18.8806
- type: nauc_precision_at_10_std
value: -24.901200000000003
- type: nauc_precision_at_10_diff1
value: 35.8153
- type: nauc_precision_at_20_max
value: 18.9481
- type: nauc_precision_at_20_std
value: -10.5055
- type: nauc_precision_at_20_diff1
value: 29.369
- type: nauc_precision_at_100_max
value: 14.1911
- type: nauc_precision_at_100_std
value: 7.6478
- type: nauc_precision_at_100_diff1
value: 0.9292999999999999
- type: nauc_precision_at_1000_max
value: 5.2714
- type: nauc_precision_at_1000_std
value: 9.8453
- type: nauc_precision_at_1000_diff1
value: -11.8428
- type: nauc_mrr_at_1_max
value: 14.541100000000002
- type: nauc_mrr_at_1_std
value: -20.9154
- type: nauc_mrr_at_1_diff1
value: 51.640699999999995
- type: nauc_mrr_at_3_max
value: 17.4433
- type: nauc_mrr_at_3_std
value: -22.367600000000003
- type: nauc_mrr_at_3_diff1
value: 47.6952
- type: nauc_mrr_at_5_max
value: 17.3538
- type: nauc_mrr_at_5_std
value: -22.003
- type: nauc_mrr_at_5_diff1
value: 47.3432
- type: nauc_mrr_at_10_max
value: 17.1856
- type: nauc_mrr_at_10_std
value: -22.0944
- type: nauc_mrr_at_10_diff1
value: 47.6806
- type: nauc_mrr_at_20_max
value: 17.2046
- type: nauc_mrr_at_20_std
value: -21.7914
- type: nauc_mrr_at_20_diff1
value: 47.7943
- type: nauc_mrr_at_100_max
value: 17.1348
- type: nauc_mrr_at_100_std
value: -21.8049
- type: nauc_mrr_at_100_diff1
value: 47.7973
- type: nauc_mrr_at_1000_max
value: 17.1388
- type: nauc_mrr_at_1000_std
value: -21.8013
- type: nauc_mrr_at_1000_diff1
value: 47.7986
- type: main_score
value: 63.754999999999995
task:
type: Retrieval
- dataset:
config: default
name: MTEB FiQA2018 (default)
revision: 27a168819829fe9bcd655c2df245fb19452e8e06
split: test
type: mteb/fiqa
metrics:
- type: ndcg_at_1
value: 28.549000000000003
- type: ndcg_at_3
value: 26.496
- type: ndcg_at_5
value: 27.229999999999997
- type: ndcg_at_10
value: 29.284
- type: ndcg_at_20
value: 31.747999999999998
- type: ndcg_at_100
value: 35.562
- type: ndcg_at_1000
value: 39.553
- type: map_at_1
value: 13.969999999999999
- type: map_at_3
value: 19.826
- type: map_at_5
value: 21.349999999999998
- type: map_at_10
value: 22.842000000000002
- type: map_at_20
value: 23.71
- type: map_at_100
value: 24.383
- type: map_at_1000
value: 24.587999999999997
- type: recall_at_1
value: 13.969999999999999
- type: recall_at_3
value: 23.923
- type: recall_at_5
value: 28.166000000000004
- type: recall_at_10
value: 34.657
- type: recall_at_20
value: 42.445
- type: recall_at_100
value: 58.626999999999995
- type: recall_at_1000
value: 83.154
- type: precision_at_1
value: 28.549000000000003
- type: precision_at_3
value: 17.747
- type: precision_at_5
value: 13.056000000000001
- type: precision_at_10
value: 8.333
- type: precision_at_20
value: 5.154
- type: precision_at_100
value: 1.4569999999999999
- type: precision_at_1000
value: 0.216
- type: mrr_at_1
value: 28.549400000000002
- type: mrr_at_3
value: 34.5679
- type: mrr_at_5
value: 35.7407
- type: mrr_at_10
value: 36.619
- type: mrr_at_20
value: 37.141000000000005
- type: mrr_at_100
value: 37.5101
- type: mrr_at_1000
value: 37.5778
- type: nauc_ndcg_at_1_max
value: 26.9011
- type: nauc_ndcg_at_1_std
value: -4.1662
- type: nauc_ndcg_at_1_diff1
value: 36.0761
- type: nauc_ndcg_at_3_max
value: 27.5647
- type: nauc_ndcg_at_3_std
value: 1.3891
- type: nauc_ndcg_at_3_diff1
value: 32.8922
- type: nauc_ndcg_at_5_max
value: 24.807299999999998
- type: nauc_ndcg_at_5_std
value: 2.2724
- type: nauc_ndcg_at_5_diff1
value: 31.646
- type: nauc_ndcg_at_10_max
value: 24.806800000000003
- type: nauc_ndcg_at_10_std
value: 3.9619
- type: nauc_ndcg_at_10_diff1
value: 31.943899999999996
- type: nauc_ndcg_at_20_max
value: 25.282
- type: nauc_ndcg_at_20_std
value: 4.6921
- type: nauc_ndcg_at_20_diff1
value: 31.3257
- type: nauc_ndcg_at_100_max
value: 27.206799999999998
- type: nauc_ndcg_at_100_std
value: 7.2548
- type: nauc_ndcg_at_100_diff1
value: 30.402800000000003
- type: nauc_ndcg_at_1000_max
value: 28.302699999999998
- type: nauc_ndcg_at_1000_std
value: 7.4432
- type: nauc_ndcg_at_1000_diff1
value: 30.4145
- type: nauc_map_at_1_max
value: 17.934900000000003
- type: nauc_map_at_1_std
value: -4.075
- type: nauc_map_at_1_diff1
value: 41.3467
- type: nauc_map_at_3_max
value: 22.6649
- type: nauc_map_at_3_std
value: -0.0022
- type: nauc_map_at_3_diff1
value: 35.949799999999996
- type: nauc_map_at_5_max
value: 22.2973
- type: nauc_map_at_5_std
value: 1.1874
- type: nauc_map_at_5_diff1
value: 34.765
- type: nauc_map_at_10_max
value: 23.472199999999997
- type: nauc_map_at_10_std
value: 2.6841
- type: nauc_map_at_10_diff1
value: 34.2725
- type: nauc_map_at_20_max
value: 24.009900000000002
- type: nauc_map_at_20_std
value: 2.9796
- type: nauc_map_at_20_diff1
value: 34.0755
- type: nauc_map_at_100_max
value: 24.5888
- type: nauc_map_at_100_std
value: 3.5168999999999997
- type: nauc_map_at_100_diff1
value: 33.795700000000004
- type: nauc_map_at_1000_max
value: 24.7001
- type: nauc_map_at_1000_std
value: 3.6033999999999997
- type: nauc_map_at_1000_diff1
value: 33.7896
- type: nauc_recall_at_1_max
value: 17.934900000000003
- type: nauc_recall_at_1_std
value: -4.075
- type: nauc_recall_at_1_diff1
value: 41.3467
- type: nauc_recall_at_3_max
value: 21.0507
- type: nauc_recall_at_3_std
value: 1.6584999999999999
- type: nauc_recall_at_3_diff1
value: 30.5016
- type: nauc_recall_at_5_max
value: 18.229100000000003
- type: nauc_recall_at_5_std
value: 4.2212
- type: nauc_recall_at_5_diff1
value: 26.2222
- type: nauc_recall_at_10_max
value: 18.9163
- type: nauc_recall_at_10_std
value: 7.421600000000001
- type: nauc_recall_at_10_diff1
value: 25.0319
- type: nauc_recall_at_20_max
value: 19.1985
- type: nauc_recall_at_20_std
value: 9.6619
- type: nauc_recall_at_20_diff1
value: 22.0881
- type: nauc_recall_at_100_max
value: 23.177400000000002
- type: nauc_recall_at_100_std
value: 20.3361
- type: nauc_recall_at_100_diff1
value: 17.4315
- type: nauc_recall_at_1000_max
value: 29.7752
- type: nauc_recall_at_1000_std
value: 30.336600000000004
- type: nauc_recall_at_1000_diff1
value: 13.9819
- type: nauc_precision_at_1_max
value: 26.9011
- type: nauc_precision_at_1_std
value: -4.1662
- type: nauc_precision_at_1_diff1
value: 36.0761
- type: nauc_precision_at_3_max
value: 31.3449
- type: nauc_precision_at_3_std
value: 5.3401
- type: nauc_precision_at_3_diff1
value: 23.5782
- type: nauc_precision_at_5_max
value: 29.545700000000004
- type: nauc_precision_at_5_std
value: 7.859299999999999
- type: nauc_precision_at_5_diff1
value: 17.5104
- type: nauc_precision_at_10_max
value: 31.787599999999998
- type: nauc_precision_at_10_std
value: 12.7279
- type: nauc_precision_at_10_diff1
value: 15.021899999999999
- type: nauc_precision_at_20_max
value: 31.782899999999998
- type: nauc_precision_at_20_std
value: 13.050600000000001
- type: nauc_precision_at_20_diff1
value: 12.4427
- type: nauc_precision_at_100_max
value: 33.4844
- type: nauc_precision_at_100_std
value: 17.4908
- type: nauc_precision_at_100_diff1
value: 4.0221
- type: nauc_precision_at_1000_max
value: 27.701199999999996
- type: nauc_precision_at_1000_std
value: 13.0084
- type: nauc_precision_at_1000_diff1
value: -5.0355
- type: nauc_mrr_at_1_max
value: 26.9011
- type: nauc_mrr_at_1_std
value: -4.1662
- type: nauc_mrr_at_1_diff1
value: 36.0761
- type: nauc_mrr_at_3_max
value: 26.51
- type: nauc_mrr_at_3_std
value: -1.6091000000000002
- type: nauc_mrr_at_3_diff1
value: 32.0993
- type: nauc_mrr_at_5_max
value: 26.502599999999997
- type: nauc_mrr_at_5_std
value: -0.9911
- type: nauc_mrr_at_5_diff1
value: 31.578200000000002
- type: nauc_mrr_at_10_max
value: 26.643099999999997
- type: nauc_mrr_at_10_std
value: -0.46950000000000003
- type: nauc_mrr_at_10_diff1
value: 31.572899999999997
- type: nauc_mrr_at_20_max
value: 26.511699999999998
- type: nauc_mrr_at_20_std
value: -0.4706
- type: nauc_mrr_at_20_diff1
value: 31.4157
- type: nauc_mrr_at_100_max
value: 26.5992
- type: nauc_mrr_at_100_std
value: -0.3074
- type: nauc_mrr_at_100_diff1
value: 31.397000000000002
- type: nauc_mrr_at_1000_max
value: 26.5961
- type: nauc_mrr_at_1000_std
value: -0.3261
- type: nauc_mrr_at_1000_diff1
value: 31.418200000000002
- type: main_score
value: 29.284
task:
type: Retrieval
- dataset:
config: default
name: MTEB HotpotQAHardNegatives (default)
revision: 617612fa63afcb60e3b134bed8b7216a99707c37
split: test
type: mteb/HotpotQA_test_top_250_only_w_correct-v2
metrics:
- type: ndcg_at_1
value: 51.4
- type: ndcg_at_3
value: 39.722
- type: ndcg_at_5
value: 42.335
- type: ndcg_at_10
value: 45.302
- type: ndcg_at_20
value: 47.589999999999996
- type: ndcg_at_100
value: 51.339
- type: ndcg_at_1000
value: 54.042
- type: map_at_1
value: 25.7
- type: map_at_3
value: 32.975
- type: map_at_5
value: 34.707
- type: map_at_10
value: 36.212
- type: map_at_20
value: 37.03
- type: map_at_100
value: 37.718
- type: map_at_1000
value: 37.858999999999995
- type: recall_at_1
value: 25.7
- type: recall_at_3
value: 36.95
- type: recall_at_5
value: 42.1
- type: recall_at_10
value: 49.5
- type: recall_at_20
value: 56.85
- type: recall_at_100
value: 73.5
- type: recall_at_1000
value: 91.14999999999999
- type: precision_at_1
value: 51.4
- type: precision_at_3
value: 24.633
- type: precision_at_5
value: 16.84
- type: precision_at_10
value: 9.9
- type: precision_at_20
value: 5.685
- type: precision_at_100
value: 1.47
- type: precision_at_1000
value: 0.182
- type: mrr_at_1
value: 51.4
- type: mrr_at_3
value: 57.283300000000004
- type: mrr_at_5
value: 58.568299999999994
- type: mrr_at_10
value: 59.618700000000004
- type: mrr_at_20
value: 60.046200000000006
- type: mrr_at_100
value: 60.3154
- type: mrr_at_1000
value: 60.3441
- type: nauc_ndcg_at_1_max
value: 45.0721
- type: nauc_ndcg_at_1_std
value: -4.7617
- type: nauc_ndcg_at_1_diff1
value: 60.8946
- type: nauc_ndcg_at_3_max
value: 41.3688
- type: nauc_ndcg_at_3_std
value: -0.7188
- type: nauc_ndcg_at_3_diff1
value: 46.8131
- type: nauc_ndcg_at_5_max
value: 40.6604
- type: nauc_ndcg_at_5_std
value: 0.0927
- type: nauc_ndcg_at_5_diff1
value: 45.0972
- type: nauc_ndcg_at_10_max
value: 40.6415
- type: nauc_ndcg_at_10_std
value: 1.2045
- type: nauc_ndcg_at_10_diff1
value: 43.893100000000004
- type: nauc_ndcg_at_20_max
value: 40.6535
- type: nauc_ndcg_at_20_std
value: 2.9401
- type: nauc_ndcg_at_20_diff1
value: 43.762
- type: nauc_ndcg_at_100_max
value: 42.9132
- type: nauc_ndcg_at_100_std
value: 5.8547
- type: nauc_ndcg_at_100_diff1
value: 45.0353
- type: nauc_ndcg_at_1000_max
value: 42.8897
- type: nauc_ndcg_at_1000_std
value: 5.562
- type: nauc_ndcg_at_1000_diff1
value: 45.051
- type: nauc_map_at_1_max
value: 45.0721
- type: nauc_map_at_1_std
value: -4.7617
- type: nauc_map_at_1_diff1
value: 60.8946
- type: nauc_map_at_3_max
value: 40.3619
- type: nauc_map_at_3_std
value: 0.7892
- type: nauc_map_at_3_diff1
value: 43.7742
- type: nauc_map_at_5_max
value: 39.857
- type: nauc_map_at_5_std
value: 1.3318999999999999
- type: nauc_map_at_5_diff1
value: 42.768
- type: nauc_map_at_10_max
value: 39.8836
- type: nauc_map_at_10_std
value: 1.9564000000000001
- type: nauc_map_at_10_diff1
value: 42.2925
- type: nauc_map_at_20_max
value: 39.8653
- type: nauc_map_at_20_std
value: 2.4855
- type: nauc_map_at_20_diff1
value: 42.3024
- type: nauc_map_at_100_max
value: 40.2949
- type: nauc_map_at_100_std
value: 3.0113000000000003
- type: nauc_map_at_100_diff1
value: 42.6062
- type: nauc_map_at_1000_max
value: 40.2828
- type: nauc_map_at_1000_std
value: 3.0048
- type: nauc_map_at_1000_diff1
value: 42.6009
- type: nauc_recall_at_1_max
value: 45.0721
- type: nauc_recall_at_1_std
value: -4.7617
- type: nauc_recall_at_1_diff1
value: 60.8946
- type: nauc_recall_at_3_max
value: 38.8376
- type: nauc_recall_at_3_std
value: 1.5544
- type: nauc_recall_at_3_diff1
value: 39.1529
- type: nauc_recall_at_5_max
value: 36.391400000000004
- type: nauc_recall_at_5_std
value: 3.1532999999999998
- type: nauc_recall_at_5_diff1
value: 34.660000000000004
- type: nauc_recall_at_10_max
value: 33.7108
- type: nauc_recall_at_10_std
value: 5.743
- type: nauc_recall_at_10_diff1
value: 28.9605
- type: nauc_recall_at_20_max
value: 32.0646
- type: nauc_recall_at_20_std
value: 11.411999999999999
- type: nauc_recall_at_20_diff1
value: 26.562200000000004
- type: nauc_recall_at_100_max
value: 39.3941
- type: nauc_recall_at_100_std
value: 28.2403
- type: nauc_recall_at_100_diff1
value: 26.353700000000003
- type: nauc_recall_at_1000_max
value: 43.751400000000004
- type: nauc_recall_at_1000_std
value: 55.13249999999999
- type: nauc_recall_at_1000_diff1
value: 10.1938
- type: nauc_precision_at_1_max
value: 45.0721
- type: nauc_precision_at_1_std
value: -4.7617
- type: nauc_precision_at_1_diff1
value: 60.8946
- type: nauc_precision_at_3_max
value: 38.8376
- type: nauc_precision_at_3_std
value: 1.5544
- type: nauc_precision_at_3_diff1
value: 39.1529
- type: nauc_precision_at_5_max
value: 36.391400000000004
- type: nauc_precision_at_5_std
value: 3.1532999999999998
- type: nauc_precision_at_5_diff1
value: 34.660000000000004
- type: nauc_precision_at_10_max
value: 33.7108
- type: nauc_precision_at_10_std
value: 5.743
- type: nauc_precision_at_10_diff1
value: 28.9605
- type: nauc_precision_at_20_max
value: 32.0646
- type: nauc_precision_at_20_std
value: 11.411999999999999
- type: nauc_precision_at_20_diff1
value: 26.562200000000004
- type: nauc_precision_at_100_max
value: 39.3941
- type: nauc_precision_at_100_std
value: 28.2403
- type: nauc_precision_at_100_diff1
value: 26.353700000000003
- type: nauc_precision_at_1000_max
value: 43.751400000000004
- type: nauc_precision_at_1000_std
value: 55.13249999999999
- type: nauc_precision_at_1000_diff1
value: 10.1938
- type: nauc_mrr_at_1_max
value: 45.0721
- type: nauc_mrr_at_1_std
value: -4.7617
- type: nauc_mrr_at_1_diff1
value: 60.8946
- type: nauc_mrr_at_3_max
value: 44.7879
- type: nauc_mrr_at_3_std
value: -5.1337
- type: nauc_mrr_at_3_diff1
value: 58.2349
- type: nauc_mrr_at_5_max
value: 44.6627
- type: nauc_mrr_at_5_std
value: -4.9526
- type: nauc_mrr_at_5_diff1
value: 57.7376
- type: nauc_mrr_at_10_max
value: 44.7676
- type: nauc_mrr_at_10_std
value: -4.7908
- type: nauc_mrr_at_10_diff1
value: 57.537400000000005
- type: nauc_mrr_at_20_max
value: 44.7882
- type: nauc_mrr_at_20_std
value: -4.5173
- type: nauc_mrr_at_20_diff1
value: 57.575900000000004
- type: nauc_mrr_at_100_max
value: 44.9292
- type: nauc_mrr_at_100_std
value: -4.4029
- type: nauc_mrr_at_100_diff1
value: 57.6909
- type: nauc_mrr_at_1000_max
value: 44.912800000000004
- type: nauc_mrr_at_1000_std
value: -4.429
- type: nauc_mrr_at_1000_diff1
value: 57.6896
- type: main_score
value: 45.302
task:
type: Retrieval
- dataset:
config: default
name: MTEB ImdbClassification (default)
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
split: test
type: mteb/imdb
metrics:
- type: accuracy
value: 71.792
- type: f1
value: 71.6599
- type: f1_weighted
value: 71.6599
- type: ap
value: 65.6717
- type: ap_weighted
value: 65.6717
- type: main_score
value: 71.792
task:
type: Classification
- dataset:
config: en
name: MTEB MTOPDomainClassification (en)
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
split: test
type: mteb/mtop_domain
metrics:
- type: accuracy
value: 90.798
- type: f1
value: 90.14569999999999
- type: f1_weighted
value: 90.8211
- type: main_score
value: 90.798
task:
type: Classification
- dataset:
config: en
name: MTEB MassiveIntentClassification (en)
revision: 4672e20407010da34463acc759c162ca9734bca6
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 66.4829
- type: f1
value: 64.3878
- type: f1_weighted
value: 65.2855
- type: main_score
value: 66.4829
task:
type: Classification
- dataset:
config: en
name: MTEB MassiveScenarioClassification (en)
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 71.1903
- type: f1
value: 71.0214
- type: f1_weighted
value: 70.7184
- type: main_score
value: 71.1903
task:
type: Classification
- dataset:
config: default
name: MTEB MedrxivClusteringP2P.v2 (default)
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
split: test
type: mteb/medrxiv-clustering-p2p
metrics:
- type: v_measure
value: 35.781
- type: v_measure_std
value: 0.7404
- type: main_score
value: 35.781
task:
type: Clustering
- dataset:
config: default
name: MTEB MedrxivClusteringS2S.v2 (default)
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
split: test
type: mteb/medrxiv-clustering-s2s
metrics:
- type: v_measure
value: 33.900200000000005
- type: v_measure_std
value: 0.8489
- type: main_score
value: 33.900200000000005
task:
type: Clustering
- dataset:
config: default
name: MTEB MindSmallReranking (default)
revision: 59042f120c80e8afa9cdbb224f67076cec0fc9a7
split: test
type: mteb/mind_small
metrics:
- type: map
value: 29.646499999999996
- type: mrr
value: 30.604799999999997
- type: nAUC_map_max
value: -23.3675
- type: nAUC_map_std
value: -5.0637
- type: nAUC_map_diff1
value: 13.4632
- type: nAUC_mrr_max
value: -17.5124
- type: nAUC_mrr_std
value: -2.8459000000000003
- type: nAUC_mrr_diff1
value: 12.4125
- type: main_score
value: 29.646499999999996
task:
type: Reranking
- dataset:
config: default
name: MTEB SCIDOCS (default)
revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88
split: test
type: mteb/scidocs
metrics:
- type: ndcg_at_1
value: 20
- type: ndcg_at_3
value: 15.842
- type: ndcg_at_5
value: 13.894
- type: ndcg_at_10
value: 16.926
- type: ndcg_at_20
value: 19.803
- type: ndcg_at_100
value: 25.081999999999997
- type: ndcg_at_1000
value: 30.864000000000004
- type: map_at_1
value: 4.093
- type: map_at_3
value: 7.091
- type: map_at_5
value: 8.389000000000001
- type: map_at_10
value: 9.831
- type: map_at_20
value: 10.801
- type: map_at_100
value: 11.815000000000001
- type: map_at_1000
value: 12.139999999999999
- type: recall_at_1
value: 4.093
- type: recall_at_3
value: 8.938
- type: recall_at_5
value: 12.323
- type: recall_at_10
value: 17.907
- type: recall_at_20
value: 24.708
- type: recall_at_100
value: 41.897
- type: recall_at_1000
value: 70.048
- type: precision_at_1
value: 20
- type: precision_at_3
value: 14.667
- type: precision_at_5
value: 12.120000000000001
- type: precision_at_10
value: 8.81
- type: precision_at_20
value: 6.08
- type: precision_at_100
value: 2.061
- type: precision_at_1000
value: 0.345
- type: mrr_at_1
value: 20
- type: mrr_at_3
value: 26.016699999999997
- type: mrr_at_5
value: 27.896700000000003
- type: mrr_at_10
value: 29.309800000000003
- type: mrr_at_20
value: 30.1817
- type: mrr_at_100
value: 30.642999999999997
- type: mrr_at_1000
value: 30.7072
- type: nauc_ndcg_at_1_max
value: 25.9162
- type: nauc_ndcg_at_1_std
value: 7.375800000000001
- type: nauc_ndcg_at_1_diff1
value: 21.4553
- type: nauc_ndcg_at_3_max
value: 29.9782
- type: nauc_ndcg_at_3_std
value: 11.0489
- type: nauc_ndcg_at_3_diff1
value: 17.3996
- type: nauc_ndcg_at_5_max
value: 31.5098
- type: nauc_ndcg_at_5_std
value: 13.3131
- type: nauc_ndcg_at_5_diff1
value: 18.3321
- type: nauc_ndcg_at_10_max
value: 33.3401
- type: nauc_ndcg_at_10_std
value: 16.1576
- type: nauc_ndcg_at_10_diff1
value: 16.9853
- type: nauc_ndcg_at_20_max
value: 34.343
- type: nauc_ndcg_at_20_std
value: 20.0335
- type: nauc_ndcg_at_20_diff1
value: 15.6531
- type: nauc_ndcg_at_100_max
value: 37.066500000000005
- type: nauc_ndcg_at_100_std
value: 26.8663
- type: nauc_ndcg_at_100_diff1
value: 16.4485
- type: nauc_ndcg_at_1000_max
value: 37.6377
- type: nauc_ndcg_at_1000_std
value: 28.4086
- type: nauc_ndcg_at_1000_diff1
value: 16.598
- type: nauc_map_at_1_max
value: 25.571899999999996
- type: nauc_map_at_1_std
value: 7.2567
- type: nauc_map_at_1_diff1
value: 21.1815
- type: nauc_map_at_3_max
value: 29.7213
- type: nauc_map_at_3_std
value: 9.027000000000001
- type: nauc_map_at_3_diff1
value: 17.6405
- type: nauc_map_at_5_max
value: 30.912499999999998
- type: nauc_map_at_5_std
value: 10.8177
- type: nauc_map_at_5_diff1
value: 18.2512
- type: nauc_map_at_10_max
value: 32.1247
- type: nauc_map_at_10_std
value: 13.3522
- type: nauc_map_at_10_diff1
value: 17.0684
- type: nauc_map_at_20_max
value: 32.8604
- type: nauc_map_at_20_std
value: 15.534899999999999
- type: nauc_map_at_20_diff1
value: 16.3024
- type: nauc_map_at_100_max
value: 33.9481
- type: nauc_map_at_100_std
value: 17.9563
- type: nauc_map_at_100_diff1
value: 16.5858
- type: nauc_map_at_1000_max
value: 34.104099999999995
- type: nauc_map_at_1000_std
value: 18.3399
- type: nauc_map_at_1000_diff1
value: 16.5982
- type: nauc_recall_at_1_max
value: 25.571899999999996
- type: nauc_recall_at_1_std
value: 7.2567
- type: nauc_recall_at_1_diff1
value: 21.1815
- type: nauc_recall_at_3_max
value: 31.102
- type: nauc_recall_at_3_std
value: 12.208
- type: nauc_recall_at_3_diff1
value: 15.7802
- type: nauc_recall_at_5_max
value: 33.0649
- type: nauc_recall_at_5_std
value: 15.7429
- type: nauc_recall_at_5_diff1
value: 17.3206
- type: nauc_recall_at_10_max
value: 34.0055
- type: nauc_recall_at_10_std
value: 19.4785
- type: nauc_recall_at_10_diff1
value: 13.9128
- type: nauc_recall_at_20_max
value: 34.4532
- type: nauc_recall_at_20_std
value: 26.6761
- type: nauc_recall_at_20_diff1
value: 10.6585
- type: nauc_recall_at_100_max
value: 36.5745
- type: nauc_recall_at_100_std
value: 39.6888
- type: nauc_recall_at_100_diff1
value: 11.683
- type: nauc_recall_at_1000_max
value: 33.799
- type: nauc_recall_at_1000_std
value: 44.5965
- type: nauc_recall_at_1000_diff1
value: 9.332699999999999
- type: nauc_precision_at_1_max
value: 25.9162
- type: nauc_precision_at_1_std
value: 7.375800000000001
- type: nauc_precision_at_1_diff1
value: 21.4553
- type: nauc_precision_at_3_max
value: 31.4508
- type: nauc_precision_at_3_std
value: 12.4827
- type: nauc_precision_at_3_diff1
value: 15.9863
- type: nauc_precision_at_5_max
value: 33.2365
- type: nauc_precision_at_5_std
value: 15.9467
- type: nauc_precision_at_5_diff1
value: 17.3246
- type: nauc_precision_at_10_max
value: 34.1244
- type: nauc_precision_at_10_std
value: 19.545
- type: nauc_precision_at_10_diff1
value: 14.082600000000001
- type: nauc_precision_at_20_max
value: 34.367399999999996
- type: nauc_precision_at_20_std
value: 26.530199999999997
- type: nauc_precision_at_20_diff1
value: 10.7493
- type: nauc_precision_at_100_max
value: 36.3502
- type: nauc_precision_at_100_std
value: 39.5794
- type: nauc_precision_at_100_diff1
value: 11.6971
- type: nauc_precision_at_1000_max
value: 32.6092
- type: nauc_precision_at_1000_std
value: 43.249500000000005
- type: nauc_precision_at_1000_diff1
value: 9.149899999999999
- type: nauc_mrr_at_1_max
value: 25.9162
- type: nauc_mrr_at_1_std
value: 7.375800000000001
- type: nauc_mrr_at_1_diff1
value: 21.4553
- type: nauc_mrr_at_3_max
value: 28.1601
- type: nauc_mrr_at_3_std
value: 11.7872
- type: nauc_mrr_at_3_diff1
value: 18.1467
- type: nauc_mrr_at_5_max
value: 29.1462
- type: nauc_mrr_at_5_std
value: 12.9036
- type: nauc_mrr_at_5_diff1
value: 18.834899999999998
- type: nauc_mrr_at_10_max
value: 29.837799999999998
- type: nauc_mrr_at_10_std
value: 13.2935
- type: nauc_mrr_at_10_diff1
value: 18.7271
- type: nauc_mrr_at_20_max
value: 29.808600000000002
- type: nauc_mrr_at_20_std
value: 13.7856
- type: nauc_mrr_at_20_diff1
value: 18.6675
- type: nauc_mrr_at_100_max
value: 29.7584
- type: nauc_mrr_at_100_std
value: 13.8851
- type: nauc_mrr_at_100_diff1
value: 18.601
- type: nauc_mrr_at_1000_max
value: 29.7331
- type: nauc_mrr_at_1000_std
value: 13.8237
- type: nauc_mrr_at_1000_diff1
value: 18.6124
- type: main_score
value: 16.926
task:
type: Retrieval
- dataset:
config: default
name: MTEB SICK-R (default)
revision: 20a6d6f312dd54037fe07a32d58e5e168867909d
split: test
type: mteb/sickr-sts
metrics:
- type: pearson
value: 84.7166
- type: spearman
value: 80.3972
- type: cosine_pearson
value: 84.7166
- type: cosine_spearman
value: 80.3972
- type: manhattan_pearson
value: 81.3592
- type: manhattan_spearman
value: 80.4202
- type: euclidean_pearson
value: 81.3441
- type: euclidean_spearman
value: 80.3972
- type: main_score
value: 80.3972
task:
type: STS
- dataset:
config: default
name: MTEB STS12 (default)
revision: a0d554a64d88156834ff5ae9920b964011b16384
split: test
type: mteb/sts12-sts
metrics:
- type: pearson
value: 86.7684
- type: spearman
value: 78.7071
- type: cosine_pearson
value: 86.7684
- type: cosine_spearman
value: 78.70899999999999
- type: manhattan_pearson
value: 83.7029
- type: manhattan_spearman
value: 78.7584
- type: euclidean_pearson
value: 83.604
- type: euclidean_spearman
value: 78.70899999999999
- type: main_score
value: 78.70899999999999
task:
type: STS
- dataset:
config: default
name: MTEB STS13 (default)
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
split: test
type: mteb/sts13-sts
metrics:
- type: pearson
value: 85.1773
- type: spearman
value: 86.1602
- type: cosine_pearson
value: 85.1773
- type: cosine_spearman
value: 86.1602
- type: manhattan_pearson
value: 84.7533
- type: manhattan_spearman
value: 86.0645
- type: euclidean_pearson
value: 84.8639
- type: euclidean_spearman
value: 86.1602
- type: main_score
value: 86.1602
task:
type: STS
- dataset:
config: default
name: MTEB STS14 (default)
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
split: test
type: mteb/sts14-sts
metrics:
- type: pearson
value: 82.87780000000001
- type: spearman
value: 81.2081
- type: cosine_pearson
value: 82.87780000000001
- type: cosine_spearman
value: 81.2081
- type: manhattan_pearson
value: 81.89750000000001
- type: manhattan_spearman
value: 81.2182
- type: euclidean_pearson
value: 81.917
- type: euclidean_spearman
value: 81.2081
- type: main_score
value: 81.2081
task:
type: STS
- dataset:
config: default
name: MTEB STS15 (default)
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
split: test
type: mteb/sts15-sts
metrics:
- type: pearson
value: 86.9104
- type: spearman
value: 87.5072
- type: cosine_pearson
value: 86.9104
- type: cosine_spearman
value: 87.5073
- type: manhattan_pearson
value: 86.74849999999999
- type: manhattan_spearman
value: 87.4643
- type: euclidean_pearson
value: 86.7938
- type: euclidean_spearman
value: 87.5072
- type: main_score
value: 87.5073
task:
type: STS
- dataset:
config: en-en
name: MTEB STS17 (en-en)
revision: faeb762787bd10488a50c8b5be4a3b82e411949c
split: test
type: mteb/sts17-crosslingual-sts
metrics:
- type: pearson
value: 89.4941
- type: spearman
value: 88.9712
- type: cosine_pearson
value: 89.4941
- type: cosine_spearman
value: 88.9712
- type: manhattan_pearson
value: 89.04039999999999
- type: manhattan_spearman
value: 89.05720000000001
- type: euclidean_pearson
value: 89.0296
- type: euclidean_spearman
value: 88.9712
- type: main_score
value: 88.9712
task:
type: STS
- dataset:
config: en
name: MTEB STS22.v2 (en)
revision: d31f33a128469b20e357535c39b82fb3c3f6f2bd
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: pearson
value: 66.6691
- type: spearman
value: 65.5503
- type: cosine_pearson
value: 66.6691
- type: cosine_spearman
value: 65.5503
- type: manhattan_pearson
value: 67.6732
- type: manhattan_spearman
value: 65.2781
- type: euclidean_pearson
value: 67.6466
- type: euclidean_spearman
value: 65.5503
- type: main_score
value: 65.5503
task:
type: STS
- dataset:
config: default
name: MTEB STSBenchmark (default)
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
split: test
type: mteb/stsbenchmark-sts
metrics:
- type: pearson
value: 85.8143
- type: spearman
value: 86.40339999999999
- type: cosine_pearson
value: 85.8143
- type: cosine_spearman
value: 86.40339999999999
- type: manhattan_pearson
value: 86.0569
- type: manhattan_spearman
value: 86.3744
- type: euclidean_pearson
value: 86.0947
- type: euclidean_spearman
value: 86.40339999999999
- type: main_score
value: 86.40339999999999
task:
type: STS
- dataset:
config: default
name: MTEB SprintDuplicateQuestions (default)
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
split: test
type: mteb/sprintduplicatequestions-pairclassification
metrics:
- type: similarity_accuracy
value: 99.8
- type: similarity_accuracy_threshold
value: 71.084
- type: similarity_f1
value: 89.7462
- type: similarity_f1_threshold
value: 71.084
- type: similarity_precision
value: 91.134
- type: similarity_recall
value: 88.4
- type: similarity_ap
value: 94.32199999999999
- type: cosine_accuracy
value: 99.8
- type: cosine_accuracy_threshold
value: 71.084
- type: cosine_f1
value: 89.7462
- type: cosine_f1_threshold
value: 71.084
- type: cosine_precision
value: 91.134
- type: cosine_recall
value: 88.4
- type: cosine_ap
value: 94.32199999999999
- type: manhattan_accuracy
value: 99.7941
- type: manhattan_accuracy_threshold
value: 1641.3430999999998
- type: manhattan_f1
value: 89.6245
- type: manhattan_f1_threshold
value: 1705.1424000000002
- type: manhattan_precision
value: 88.5742
- type: manhattan_recall
value: 90.7
- type: manhattan_ap
value: 94.22840000000001
- type: euclidean_accuracy
value: 99.8
- type: euclidean_accuracy_threshold
value: 76.0474
- type: euclidean_f1
value: 89.7462
- type: euclidean_f1_threshold
value: 76.0474
- type: euclidean_precision
value: 91.134
- type: euclidean_recall
value: 88.4
- type: euclidean_ap
value: 94.32199999999999
- type: dot_accuracy
value: 99.8
- type: dot_accuracy_threshold
value: 71.084
- type: dot_f1
value: 89.7462
- type: dot_f1_threshold
value: 71.084
- type: dot_precision
value: 91.134
- type: dot_recall
value: 88.4
- type: dot_ap
value: 94.32199999999999
- type: max_accuracy
value: 99.8
- type: max_f1
value: 89.7462
- type: max_precision
value: 91.134
- type: max_recall
value: 90.7
- type: max_ap
value: 94.32199999999999
- type: main_score
value: 94.32199999999999
task:
type: PairClassification
- dataset:
config: default
name: MTEB StackExchangeClustering.v2 (default)
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
split: test
type: mteb/stackexchange-clustering
metrics:
- type: v_measure
value: 53.5198
- type: v_measure_std
value: 0.6015
- type: main_score
value: 53.5198
task:
type: Clustering
- dataset:
config: default
name: MTEB StackExchangeClusteringP2P.v2 (default)
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
split: test
type: mteb/stackexchange-clustering-p2p
metrics:
- type: v_measure
value: 40.029399999999995
- type: v_measure_std
value: 0.4919
- type: main_score
value: 40.029399999999995
task:
type: Clustering
- dataset:
config: default
name: MTEB SummEvalSummarization.v2 (default)
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
split: test
type: mteb/summeval
metrics:
- type: pearson
value: 33.6198
- type: spearman
value: 30.206699999999998
- type: cosine_spearman
value: 30.206699999999998
- type: cosine_pearson
value: 33.6198
- type: dot_spearman
value: 30.206699999999998
- type: dot_pearson
value: 33.6198
- type: main_score
value: 30.206699999999998
task:
type: Summarization
- dataset:
config: default
name: MTEB TRECCOVID (default)
revision: bb9466bac8153a0349341eb1b22e06409e78ef4e
split: test
type: mteb/trec-covid
metrics:
- type: ndcg_at_1
value: 63
- type: ndcg_at_3
value: 66.47999999999999
- type: ndcg_at_5
value: 61.090999999999994
- type: ndcg_at_10
value: 56.823
- type: ndcg_at_20
value: 53.21
- type: ndcg_at_100
value: 42.365
- type: ndcg_at_1000
value: 40.819
- type: map_at_1
value: 0.186
- type: map_at_3
value: 0.527
- type: map_at_5
value: 0.762
- type: map_at_10
value: 1.275
- type: map_at_20
value: 2.177
- type: map_at_100
value: 6.935
- type: map_at_1000
value: 16.973
- type: recall_at_1
value: 0.186
- type: recall_at_3
value: 0.581
- type: recall_at_5
value: 0.8710000000000001
- type: recall_at_10
value: 1.582
- type: recall_at_20
value: 2.897
- type: recall_at_100
value: 10.546
- type: recall_at_1000
value: 38.541
- type: precision_at_1
value: 68
- type: precision_at_3
value: 70.667
- type: precision_at_5
value: 63.2
- type: precision_at_10
value: 58.4
- type: precision_at_20
value: 54.400000000000006
- type: precision_at_100
value: 42.46
- type: precision_at_1000
value: 17.657999999999998
- type: mrr_at_1
value: 68
- type: mrr_at_3
value: 79
- type: mrr_at_5
value: 79.5
- type: mrr_at_10
value: 79.8333
- type: mrr_at_20
value: 80.0152
- type: mrr_at_100
value: 80.0152
- type: mrr_at_1000
value: 80.0152
- type: nauc_ndcg_at_1_max
value: -5.9922
- type: nauc_ndcg_at_1_std
value: 0.42110000000000003
- type: nauc_ndcg_at_1_diff1
value: 23.3553
- type: nauc_ndcg_at_3_max
value: 10.2171
- type: nauc_ndcg_at_3_std
value: 17.6509
- type: nauc_ndcg_at_3_diff1
value: 14.5183
- type: nauc_ndcg_at_5_max
value: 23.7407
- type: nauc_ndcg_at_5_std
value: 37.241
- type: nauc_ndcg_at_5_diff1
value: 18.1059
- type: nauc_ndcg_at_10_max
value: 29.640300000000003
- type: nauc_ndcg_at_10_std
value: 41.2782
- type: nauc_ndcg_at_10_diff1
value: 8.6037
- type: nauc_ndcg_at_20_max
value: 40.3419
- type: nauc_ndcg_at_20_std
value: 52.5532
- type: nauc_ndcg_at_20_diff1
value: 8.1576
- type: nauc_ndcg_at_100_max
value: 51.4533
- type: nauc_ndcg_at_100_std
value: 69.6289
- type: nauc_ndcg_at_100_diff1
value: -3.2301
- type: nauc_ndcg_at_1000_max
value: 56.962900000000005
- type: nauc_ndcg_at_1000_std
value: 74.6131
- type: nauc_ndcg_at_1000_diff1
value: -8.241999999999999
- type: nauc_map_at_1_max
value: -4.668
- type: nauc_map_at_1_std
value: -10.0497
- type: nauc_map_at_1_diff1
value: 23.029700000000002
- type: nauc_map_at_3_max
value: 0.6419
- type: nauc_map_at_3_std
value: 1.0362
- type: nauc_map_at_3_diff1
value: 14.8847
- type: nauc_map_at_5_max
value: 10.632
- type: nauc_map_at_5_std
value: 14.382200000000001
- type: nauc_map_at_5_diff1
value: 17.8863
- type: nauc_map_at_10_max
value: 16.8052
- type: nauc_map_at_10_std
value: 21.084500000000002
- type: nauc_map_at_10_diff1
value: 15.3248
- type: nauc_map_at_20_max
value: 27.3457
- type: nauc_map_at_20_std
value: 34.2901
- type: nauc_map_at_20_diff1
value: 11.4443
- type: nauc_map_at_100_max
value: 49.5995
- type: nauc_map_at_100_std
value: 65.1028
- type: nauc_map_at_100_diff1
value: -1.8796
- type: nauc_map_at_1000_max
value: 60.618399999999994
- type: nauc_map_at_1000_std
value: 76.28399999999999
- type: nauc_map_at_1000_diff1
value: -13.772100000000002
- type: nauc_recall_at_1_max
value: -4.668
- type: nauc_recall_at_1_std
value: -10.0497
- type: nauc_recall_at_1_diff1
value: 23.029700000000002
- type: nauc_recall_at_3_max
value: 0.0493
- type: nauc_recall_at_3_std
value: 2.2468
- type: nauc_recall_at_3_diff1
value: 16.5914
- type: nauc_recall_at_5_max
value: 9.1725
- type: nauc_recall_at_5_std
value: 14.597999999999999
- type: nauc_recall_at_5_diff1
value: 18.6063
- type: nauc_recall_at_10_max
value: 13.672400000000001
- type: nauc_recall_at_10_std
value: 15.9268
- type: nauc_recall_at_10_diff1
value: 16.3772
- type: nauc_recall_at_20_max
value: 21.4077
- type: nauc_recall_at_20_std
value: 27.209
- type: nauc_recall_at_20_diff1
value: 14.8917
- type: nauc_recall_at_100_max
value: 42.282799999999995
- type: nauc_recall_at_100_std
value: 57.6084
- type: nauc_recall_at_100_diff1
value: 2.6269
- type: nauc_recall_at_1000_max
value: 54.055
- type: nauc_recall_at_1000_std
value: 68.8306
- type: nauc_recall_at_1000_diff1
value: -9.5473
- type: nauc_precision_at_1_max
value: -1.8693000000000002
- type: nauc_precision_at_1_std
value: -5.061800000000001
- type: nauc_precision_at_1_diff1
value: 39.6344
- type: nauc_precision_at_3_max
value: 20.2643
- type: nauc_precision_at_3_std
value: 23.1419
- type: nauc_precision_at_3_diff1
value: 20.305999999999997
- type: nauc_precision_at_5_max
value: 35.8846
- type: nauc_precision_at_5_std
value: 48.295
- type: nauc_precision_at_5_diff1
value: 22.5559
- type: nauc_precision_at_10_max
value: 39.8361
- type: nauc_precision_at_10_std
value: 46.245000000000005
- type: nauc_precision_at_10_diff1
value: 6.433800000000001
- type: nauc_precision_at_20_max
value: 47.9467
- type: nauc_precision_at_20_std
value: 57.981
- type: nauc_precision_at_20_diff1
value: 7.721699999999999
- type: nauc_precision_at_100_max
value: 55.6948
- type: nauc_precision_at_100_std
value: 71.6681
- type: nauc_precision_at_100_diff1
value: -5.4666
- type: nauc_precision_at_1000_max
value: 49.0064
- type: nauc_precision_at_1000_std
value: 56.2352
- type: nauc_precision_at_1000_diff1
value: -17.4375
- type: nauc_mrr_at_1_max
value: -1.8693000000000002
- type: nauc_mrr_at_1_std
value: -5.061800000000001
- type: nauc_mrr_at_1_diff1
value: 39.6344
- type: nauc_mrr_at_3_max
value: 7.8541
- type: nauc_mrr_at_3_std
value: 7.0844000000000005
- type: nauc_mrr_at_3_diff1
value: 44.6714
- type: nauc_mrr_at_5_max
value: 7.070600000000001
- type: nauc_mrr_at_5_std
value: 6.2793
- type: nauc_mrr_at_5_diff1
value: 43.1205
- type: nauc_mrr_at_10_max
value: 5.829899999999999
- type: nauc_mrr_at_10_std
value: 4.7435
- type: nauc_mrr_at_10_diff1
value: 42.8864
- type: nauc_mrr_at_20_max
value: 4.8414
- type: nauc_mrr_at_20_std
value: 3.7436
- type: nauc_mrr_at_20_diff1
value: 42.9607
- type: nauc_mrr_at_100_max
value: 4.8414
- type: nauc_mrr_at_100_std
value: 3.7436
- type: nauc_mrr_at_100_diff1
value: 42.9607
- type: nauc_mrr_at_1000_max
value: 4.8414
- type: nauc_mrr_at_1000_std
value: 3.7436
- type: nauc_mrr_at_1000_diff1
value: 42.9607
- type: main_score
value: 56.823
task:
type: Retrieval
- dataset:
config: default
name: MTEB Touche2020Retrieval.v3 (default)
revision: 431886eaecc48f067a3975b70d0949ea2862463c
split: test
type: mteb/webis-touche2020-v3
metrics:
- type: ndcg_at_1
value: 52.041000000000004
- type: ndcg_at_3
value: 52.178000000000004
- type: ndcg_at_5
value: 52.23100000000001
- type: ndcg_at_10
value: 47.693999999999996
- type: ndcg_at_20
value: 43.242999999999995
- type: ndcg_at_100
value: 51.503
- type: ndcg_at_1000
value: 63.939
- type: map_at_1
value: 2.407
- type: map_at_3
value: 6.193
- type: map_at_5
value: 9.617
- type: map_at_10
value: 15.279000000000002
- type: map_at_20
value: 21.498
- type: map_at_100
value: 30.198999999999998
- type: map_at_1000
value: 33.217
- type: recall_at_1
value: 2.407
- type: recall_at_3
value: 6.762
- type: recall_at_5
value: 11.392
- type: recall_at_10
value: 19.333
- type: recall_at_20
value: 30.013
- type: recall_at_100
value: 56.041
- type: recall_at_1000
value: 86.126
- type: precision_at_1
value: 61.224000000000004
- type: precision_at_3
value: 63.26500000000001
- type: precision_at_5
value: 62.449
- type: precision_at_10
value: 52.245
- type: precision_at_20
value: 42.041000000000004
- type: precision_at_100
value: 17.653
- type: precision_at_1000
value: 2.9819999999999998
- type: mrr_at_1
value: 61.224500000000006
- type: mrr_at_3
value: 74.1497
- type: mrr_at_5
value: 76.4966
- type: mrr_at_10
value: 76.7881
- type: mrr_at_20
value: 76.7881
- type: mrr_at_100
value: 76.7881
- type: mrr_at_1000
value: 76.7881
- type: nauc_ndcg_at_1_max
value: 11.4245
- type: nauc_ndcg_at_1_std
value: -14.1654
- type: nauc_ndcg_at_1_diff1
value: 8.206299999999999
- type: nauc_ndcg_at_3_max
value: 9.2585
- type: nauc_ndcg_at_3_std
value: -11.469999999999999
- type: nauc_ndcg_at_3_diff1
value: 16.437099999999997
- type: nauc_ndcg_at_5_max
value: 4.9696
- type: nauc_ndcg_at_5_std
value: -0.6109
- type: nauc_ndcg_at_5_diff1
value: 27.5214
- type: nauc_ndcg_at_10_max
value: -1.3538
- type: nauc_ndcg_at_10_std
value: -6.0539000000000005
- type: nauc_ndcg_at_10_diff1
value: 37.565799999999996
- type: nauc_ndcg_at_20_max
value: -3.3665000000000003
- type: nauc_ndcg_at_20_std
value: 0.364
- type: nauc_ndcg_at_20_diff1
value: 37.418800000000005
- type: nauc_ndcg_at_100_max
value: -7.1732000000000005
- type: nauc_ndcg_at_100_std
value: 6.9091
- type: nauc_ndcg_at_100_diff1
value: 31.342799999999997
- type: nauc_ndcg_at_1000_max
value: 4.9213
- type: nauc_ndcg_at_1000_std
value: 27.2304
- type: nauc_ndcg_at_1000_diff1
value: 26.5774
- type: nauc_map_at_1_max
value: -10.1278
- type: nauc_map_at_1_std
value: -30.9116
- type: nauc_map_at_1_diff1
value: 47.6006
- type: nauc_map_at_3_max
value: -9.9654
- type: nauc_map_at_3_std
value: -26.4025
- type: nauc_map_at_3_diff1
value: 40.3311
- type: nauc_map_at_5_max
value: -10.3545
- type: nauc_map_at_5_std
value: -21.662699999999997
- type: nauc_map_at_5_diff1
value: 46.1136
- type: nauc_map_at_10_max
value: -9.528
- type: nauc_map_at_10_std
value: -21.3903
- type: nauc_map_at_10_diff1
value: 41.5027
- type: nauc_map_at_20_max
value: -7.0028999999999995
- type: nauc_map_at_20_std
value: -15.9361
- type: nauc_map_at_20_diff1
value: 42.6171
- type: nauc_map_at_100_max
value: -2.8579
- type: nauc_map_at_100_std
value: -4.1692
- type: nauc_map_at_100_diff1
value: 35.200900000000004
- type: nauc_map_at_1000_max
value: -0.1717
- type: nauc_map_at_1000_std
value: 1.4015
- type: nauc_map_at_1000_diff1
value: 34.1462
- type: nauc_recall_at_1_max
value: -10.1278
- type: nauc_recall_at_1_std
value: -30.9116
- type: nauc_recall_at_1_diff1
value: 47.6006
- type: nauc_recall_at_3_max
value: -9.7092
- type: nauc_recall_at_3_std
value: -26.067800000000002
- type: nauc_recall_at_3_diff1
value: 44.094100000000005
- type: nauc_recall_at_5_max
value: -16.8476
- type: nauc_recall_at_5_std
value: -21.546799999999998
- type: nauc_recall_at_5_diff1
value: 51.0826
- type: nauc_recall_at_10_max
value: -19.3996
- type: nauc_recall_at_10_std
value: -23.857400000000002
- type: nauc_recall_at_10_diff1
value: 43.743900000000004
- type: nauc_recall_at_20_max
value: -17.413500000000003
- type: nauc_recall_at_20_std
value: -13.7552
- type: nauc_recall_at_20_diff1
value: 41.761900000000004
- type: nauc_recall_at_100_max
value: -13.270399999999999
- type: nauc_recall_at_100_std
value: 12.9632
- type: nauc_recall_at_100_diff1
value: 25.7781
- type: nauc_recall_at_1000_max
value: 4.5253000000000005
- type: nauc_recall_at_1000_std
value: 71.75280000000001
- type: nauc_recall_at_1000_diff1
value: 9.0837
- type: nauc_precision_at_1_max
value: 26.4969
- type: nauc_precision_at_1_std
value: -21.090600000000002
- type: nauc_precision_at_1_diff1
value: 25.671899999999997
- type: nauc_precision_at_3_max
value: 17.132
- type: nauc_precision_at_3_std
value: -14.341999999999999
- type: nauc_precision_at_3_diff1
value: 27.7326
- type: nauc_precision_at_5_max
value: 10.6548
- type: nauc_precision_at_5_std
value: 2.9193000000000002
- type: nauc_precision_at_5_diff1
value: 38.373400000000004
- type: nauc_precision_at_10_max
value: 1.3576
- type: nauc_precision_at_10_std
value: -3.8871
- type: nauc_precision_at_10_diff1
value: 33.6879
- type: nauc_precision_at_20_max
value: 4.9846
- type: nauc_precision_at_20_std
value: 16.8654
- type: nauc_precision_at_20_diff1
value: 25.1747
- type: nauc_precision_at_100_max
value: 32.9312
- type: nauc_precision_at_100_std
value: 50.7741
- type: nauc_precision_at_100_diff1
value: -19.561700000000002
- type: nauc_precision_at_1000_max
value: 44.7539
- type: nauc_precision_at_1000_std
value: 50.897800000000004
- type: nauc_precision_at_1000_diff1
value: -34.477999999999994
- type: nauc_mrr_at_1_max
value: 26.4969
- type: nauc_mrr_at_1_std
value: -21.090600000000002
- type: nauc_mrr_at_1_diff1
value: 25.671899999999997
- type: nauc_mrr_at_3_max
value: 36.031600000000005
- type: nauc_mrr_at_3_std
value: -9.915799999999999
- type: nauc_mrr_at_3_diff1
value: 32.4812
- type: nauc_mrr_at_5_max
value: 32.5212
- type: nauc_mrr_at_5_std
value: -10.443
- type: nauc_mrr_at_5_diff1
value: 31.8118
- type: nauc_mrr_at_10_max
value: 31.4955
- type: nauc_mrr_at_10_std
value: -11.698
- type: nauc_mrr_at_10_diff1
value: 30.974400000000003
- type: nauc_mrr_at_20_max
value: 31.4955
- type: nauc_mrr_at_20_std
value: -11.698
- type: nauc_mrr_at_20_diff1
value: 30.974400000000003
- type: nauc_mrr_at_100_max
value: 31.4955
- type: nauc_mrr_at_100_std
value: -11.698
- type: nauc_mrr_at_100_diff1
value: 30.974400000000003
- type: nauc_mrr_at_1000_max
value: 31.4955
- type: nauc_mrr_at_1000_std
value: -11.698
- type: nauc_mrr_at_1000_diff1
value: 30.974400000000003
- type: main_score
value: 47.693999999999996
task:
type: Retrieval
- dataset:
config: default
name: MTEB ToxicConversationsClassification (default)
revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de
split: test
type: mteb/toxic_conversations_50k
metrics:
- type: accuracy
value: 65.65429999999999
- type: f1
value: 50.530699999999996
- type: f1_weighted
value: 73.3205
- type: ap
value: 12.0938
- type: ap_weighted
value: 12.0938
- type: main_score
value: 65.65429999999999
task:
type: Classification
- dataset:
config: default
name: MTEB TweetSentimentExtractionClassification (default)
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
split: test
type: mteb/tweet_sentiment_extraction
metrics:
- type: accuracy
value: 61.7119
- type: f1
value: 61.8672
- type: f1_weighted
value: 60.762499999999996
- type: main_score
value: 61.7119
task:
type: Classification
- dataset:
config: default
name: MTEB TwentyNewsgroupsClustering.v2 (default)
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
split: test
type: mteb/twentynewsgroups-clustering
metrics:
- type: v_measure
value: 37.4338
- type: v_measure_std
value: 1.5165
- type: main_score
value: 37.4338
task:
type: Clustering
- dataset:
config: default
name: MTEB TwitterSemEval2015 (default)
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
split: test
type: mteb/twittersemeval2015-pairclassification
metrics:
- type: similarity_accuracy
value: 82.8873
- type: similarity_accuracy_threshold
value: 67.9403
- type: similarity_f1
value: 60.3641
- type: similarity_f1_threshold
value: 60.5738
- type: similarity_precision
value: 55.887600000000006
- type: similarity_recall
value: 65.62010000000001
- type: similarity_ap
value: 63.522
- type: cosine_accuracy
value: 82.8873
- type: cosine_accuracy_threshold
value: 67.9403
- type: cosine_f1
value: 60.3641
- type: cosine_f1_threshold
value: 60.5738
- type: cosine_precision
value: 55.887600000000006
- type: cosine_recall
value: 65.62010000000001
- type: cosine_ap
value: 63.522
- type: manhattan_accuracy
value: 82.8098
- type: manhattan_accuracy_threshold
value: 1739.439
- type: manhattan_f1
value: 60.1751
- type: manhattan_f1_threshold
value: 1961.5566000000001
- type: manhattan_precision
value: 54.5474
- type: manhattan_recall
value: 67.0976
- type: manhattan_ap
value: 63.42100000000001
- type: euclidean_accuracy
value: 82.8873
- type: euclidean_accuracy_threshold
value: 80.07459999999999
- type: euclidean_f1
value: 60.3641
- type: euclidean_f1_threshold
value: 88.7989
- type: euclidean_precision
value: 55.887600000000006
- type: euclidean_recall
value: 65.62010000000001
- type: euclidean_ap
value: 63.522
- type: dot_accuracy
value: 82.8873
- type: dot_accuracy_threshold
value: 67.9403
- type: dot_f1
value: 60.3641
- type: dot_f1_threshold
value: 60.5738
- type: dot_precision
value: 55.887600000000006
- type: dot_recall
value: 65.62010000000001
- type: dot_ap
value: 63.522
- type: max_accuracy
value: 82.8873
- type: max_f1
value: 60.3641
- type: max_precision
value: 55.887600000000006
- type: max_recall
value: 67.0976
- type: max_ap
value: 63.522
- type: main_score
value: 63.522
task:
type: PairClassification
- dataset:
config: default
name: MTEB TwitterURLCorpus (default)
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
split: test
type: mteb/twitterurlcorpus-pairclassification
metrics:
- type: similarity_accuracy
value: 88.7337
- type: similarity_accuracy_threshold
value: 62.43729999999999
- type: similarity_f1
value: 77.8938
- type: similarity_f1_threshold
value: 59.013400000000004
- type: similarity_precision
value: 74.31309999999999
- type: similarity_recall
value: 81.83709999999999
- type: similarity_ap
value: 85.1691
- type: cosine_accuracy
value: 88.7337
- type: cosine_accuracy_threshold
value: 62.43729999999999
- type: cosine_f1
value: 77.8938
- type: cosine_f1_threshold
value: 59.013400000000004
- type: cosine_precision
value: 74.31309999999999
- type: cosine_recall
value: 81.83709999999999
- type: cosine_ap
value: 85.1691
- type: manhattan_accuracy
value: 88.689
- type: manhattan_accuracy_threshold
value: 1888.1997999999999
- type: manhattan_f1
value: 77.8453
- type: manhattan_f1_threshold
value: 1974.1371000000001
- type: manhattan_precision
value: 74.6414
- type: manhattan_recall
value: 81.3366
- type: manhattan_ap
value: 85.0954
- type: euclidean_accuracy
value: 88.7337
- type: euclidean_accuracy_threshold
value: 86.6749
- type: euclidean_f1
value: 77.8938
- type: euclidean_f1_threshold
value: 90.53909999999999
- type: euclidean_precision
value: 74.31309999999999
- type: euclidean_recall
value: 81.83709999999999
- type: euclidean_ap
value: 85.1691
- type: dot_accuracy
value: 88.7337
- type: dot_accuracy_threshold
value: 62.43729999999999
- type: dot_f1
value: 77.8938
- type: dot_f1_threshold
value: 59.013400000000004
- type: dot_precision
value: 74.31309999999999
- type: dot_recall
value: 81.83709999999999
- type: dot_ap
value: 85.1691
- type: max_accuracy
value: 88.7337
- type: max_f1
value: 77.8938
- type: max_precision
value: 74.6414
- type: max_recall
value: 81.83709999999999
- type: max_ap
value: 85.1691
- type: main_score
value: 85.1691
task:
type: PairClassification
license: apache-2.0
RetrievaEmbedding-01: AMBER
The AMBER (Adaptive Multitask Bilingual Embedding Representations) is a text embedding model trained by Retrieva, Inc. This model is primarily designed for Japanese, but it also supports English. We trained this model on various datasets related to Japanese and English.
This model size is 315M parameters (large size).
Model Details
Model Description
The AMBER model is a text embedding model based on the sbintuitions/modernbert-ja-310m architecture, designed for Japanese text. This model was trained on a variety of datasets related to Japanese, and also includes English datasets. The model can be used for English text as well. During training, prompts (instructions) in natural language were included, allowing the model to generate embeddings tailored to specific tasks.
- Developed by: Retrieva, Inc.
- Model type: Based on the ModernBERT Architecture.
- Language(s) (NLP): Primarily Japanese (optional support for English).
- License: Apache 2.0
- Finetuned from model:
sbintuitions/modernbert-ja-310m - Model Type: Sentence Transformer
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 768 dimensions
- Similarity Function: Cosine Similarity
Uses
How to Get Started with the Model
Install Library
First install the python library using pip:
pip install sentence-transformers sentencepiece
Run Inference
Then you can load this model and run inference.
You can specify the prompt at inference time by adding an argument called prompt to model.encode.
The prompts used in the Japanese benchmark are described in jmteb/tasks, and the prompts used in the English benchmark are described in mteb/models/retrieva_en.py.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("retrieva-jp/amber-large")
# Run inference
queries = [
"自然言語処理とはなんですか？",
"株式会社レトリバについて教えて",
]
documents = [
"自然言語処理（しぜんげんごしょり、英語: Natural language processing、略称：NLP）は、人間が日常的に使っている自然言語をコンピュータに処理させる一連の技術であり、人工知能と言語学の一分野である。",
"株式会社レトリバは、自然言語処理と機械学習を核としたAI技術で組織の課題解決を支援するテクノロジー企業である。",
]
queries_embeddings = model.encode(queries, prompt_name="Retrieval-query")
documents_embeddings = model.encode(documents, prompt_name="Retrieval-passage")
similarities = model.similarity(queries_embeddings, documents_embeddings)
print(similarities.shape)
Training Details
Training Data
We used multiple datasets to train this model. We selected datasets from llm-jp-eval, llm-japanese-dataset, and hpprc/emb for Japanese datasets. For English datasets, we mainly used some of the datasets utilized in Asai et al. (2023). Additionally, we partially used the English datasets at the sentence-transformers repository and kilt-tasks. To consider cross-lingual between Japanese and English, we also used translation datasets between Japanese and English.
For Japanese, we used synthetic data created by LLM to prepare a sufficient amount of training data.
Evaluation
We evaluated the model on the following benchmarks:
- Japanese Benchmark: JMTEB
- Japanese Retrieval Tasks: JQaRA, JaCWIR, MLDR Japanese Subset
- English Benchmark: MTEB(eng, v2).
The scores in the table are all calculated by us unless otherwise noted.
Japanese Benchmark: JMTEB
Note that the Mean (TaskType) in the following leaderboard is the same as the Avg. in the original JMTEB leaderboard.
The files used for evaluation are stored in the jmteb directory.
| Model | # Parameters | Mean (TaskType) | Mean (Task) | Retrieval | STS | Classification | Reranking | Clustering | PairClassification |
|---|---|---|---|---|---|---|---|---|---|
| base models | < 300M | ||||||||
| cl-nagoya/ruri-base | 111M | 72.60 | 71.56 | 69.53 | 82.87 | 75.49 | 92.91 | 52.40 | 62.38 |
| AMBER-base | 130M | 72.12 | 72.12 | 73.40 | 77.81 | 76.14 | 93.27 | 48.05 | 64.03 |
| pkshatech/GLuCoSE-base-ja-v2 | 133M | 72.89 | 72.47 | 73.03 | 82.96 | 74.02 | 93.01 | 51.96 | 62.37 |
| pkshatech/RoSEtta-base-ja | 190M | 72.49 | 72.05 | 73.14 | 81.39 | 72.37 | 92.69 | 53.60 | 61.74 |
| intfloat/multilingual-e5-base | 278M | 71.11 | 69.72 | 69.45 | 80.45 | 69.86 | 92.90 | 51.62 | 62.35 |
| large models | 300M < | ||||||||
| AMBER-large (this model) |
315M | 72.52 | 73.22 | 75.40 | 79.32 | 77.14 | 93.54 | 48.73 | 60.97 |
| cl-nagoya/ruri-large | 337M | 73.20 | 73.06 | 72.86 | 83.14 | 77.15 | 93.00 | 50.78 | 62.29 |
| intfloat/multilingual-e5-large | 560M | 72.06 | 71.29 | 71.71 | 80.87 | 72.45 | 93.29 | 51.59 | 62.42 |
Japanese Retrieval Tasks: JQaRA, JaCWIR, MLDR Japanese Subset
The files used for MLDR are stored in the mldr directory.
The prompts used in JQaRA and JaCWIR are Retrieval-query and Retrieval-passage described in config_sentence_transformers.json.
| Model | # Parameters | JQaRA (nDCG@10) | JaCWIR (MAP@10) | MLDR Japanese Subset (nDCG@10) |
|---|---|---|---|---|
| base models | < 300M | |||
| cl-nagoya/ruri-base | 111M | 58.4 | 83.3 | 32.77 |
| AMBER-base | 130M | 57.1 | 81.6 | 35.69 |
| pkshatech/GLuCoSE-base-ja-v2 | 133M | 60.6 | 85.3 | 33.99 |
| intfloat/multilingual-e5-base | 278M | 47.1 | 85.3 | 25.46 |
| large models | 300M < | |||
| AMBER-large (this model) |
315M | 62.5 | 82.4 | 34.57 |
| cl-nagoya/ruri-large | 337M | 62.8 | 82.5 | 34.78 |
| intfloat/multilingual-e5-large | 560M | 55.4 | 87.3 | 29.95 |
English Benchmark: MTEB(eng, v2)
The files used for evaluation are stored in the mteb directory.
| Model | # Parameters | Mean (TaskType) | Mean (Task) | Retrieval | STS | Classification | Reranking | Clustering | PairClassification | Summarization |
|---|---|---|---|---|---|---|---|---|---|---|
| base models | < 300M | |||||||||
| AMBER-base | 130M | 54.75 | 58.20 | 40.11 | 81.29 | 70.39 | 42.98 | 42.27 | 80.12 | 26.08 |
| intfloat/multilingual-e5-base | 278M | 56.21 | 59.75 | 43.22 | 80.50 | 73.84 | 43.87 | 42.19 | 83.74 | 26.10 |
| large models | 300M < | |||||||||
| AMBER-large (this model) |
315M | 56.08 | 59.13 | 41.04 | 81.52 | 72.23 | 43.83 | 42.71 | 81.00 | 30.21 |
| intfloat/multilingual-e5-large | 560M | 57.06 | 60.84 | 46.17 | 81.11 | 74.88 | 44.31 | 41.91 | 84.33 | 26.67 |
More Information
TBA
Model Card Authors
Satoru Katsumata, Daisuke Kimura, Jiro Nishitoba
Model Card Contact
pr[at]retrieva.jp