diff --git "a/README.md" "b/README.md" --- "a/README.md" +++ "b/README.md" @@ -19,11 +19,11 @@ model-index: revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy - value: 88.01492537313432 + value: 91.31343283582089 - type: ap - value: 59.096217055359276 + value: 67.64251402604096 - type: f1 - value: 83.2699173062069 + value: 87.53372530755692 - task: type: Classification dataset: @@ -34,11 +34,11 @@ model-index: revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy - value: 97.29805 + value: 97.497825 - type: ap - value: 95.97973142381882 + value: 96.30329547047529 - type: f1 - value: 97.29773206176378 + value: 97.49769793778039 - task: type: Classification dataset: @@ -49,9 +49,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 62.798 + value: 62.564 - type: f1 - value: 61.33195375425034 + value: 60.975777935041066 - task: type: Retrieval dataset: @@ -62,65 +62,65 @@ model-index: revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: map_at_1 - value: 36.629 + value: 36.486000000000004 - type: map_at_10 - value: 54.982 + value: 54.842 - type: map_at_100 - value: 55.355 + value: 55.206999999999994 - type: map_at_1000 - value: 55.355 + value: 55.206999999999994 - type: map_at_3 - value: 50.036 + value: 49.893 - type: map_at_5 - value: 53.25 + value: 53.105000000000004 - type: mrr_at_1 - value: 37.624 + value: 37.34 - type: mrr_at_10 - value: 55.376000000000005 + value: 55.143 - type: mrr_at_100 - value: 55.749 + value: 55.509 - type: mrr_at_1000 - value: 55.749 + value: 55.509 - type: mrr_at_3 - value: 50.461999999999996 + value: 50.212999999999994 - type: mrr_at_5 - value: 53.644999999999996 + value: 53.432 - type: ndcg_at_1 - value: 36.629 + value: 36.486000000000004 - type: ndcg_at_10 - value: 64.35499999999999 + value: 64.273 - type: ndcg_at_100 - value: 65.778 + value: 65.66199999999999 - type: ndcg_at_1000 - value: 65.778 + value: 65.66199999999999 - type: ndcg_at_3 - value: 54.478 + value: 54.352999999999994 - type: ndcg_at_5 - value: 60.260000000000005 + value: 60.131 - type: precision_at_1 - value: 36.629 + value: 36.486000000000004 - type: precision_at_10 - value: 9.381 + value: 9.395000000000001 - type: precision_at_100 value: 0.996 - type: precision_at_1000 value: 0.1 - type: precision_at_3 - value: 22.451 + value: 22.428 - type: precision_at_5 - value: 16.273 + value: 16.259 - type: recall_at_1 - value: 36.629 + value: 36.486000000000004 - type: recall_at_10 - value: 93.812 + value: 93.95400000000001 - type: recall_at_100 value: 99.644 - type: recall_at_1000 value: 99.644 - type: recall_at_3 - value: 67.354 + value: 67.283 - type: recall_at_5 - value: 81.366 + value: 81.294 - task: type: Clustering dataset: @@ -131,7 +131,7 @@ model-index: revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure - value: 56.30960182540703 + value: 56.461169803700564 - task: type: Clustering dataset: @@ -142,7 +142,7 @@ model-index: revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure - value: 51.858431775176975 + value: 51.73600434466286 - task: type: Reranking dataset: @@ -153,9 +153,9 @@ model-index: revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map - value: 67.5678414928039 + value: 67.57827065898053 - type: mrr - value: 79.56305236776153 + value: 79.08136569493911 - task: type: STS dataset: @@ -166,17 +166,17 @@ model-index: revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson - value: 82.32511136457549 + value: 83.53324575999243 - type: cos_sim_spearman - value: 79.34518142776068 + value: 81.37173362822374 - type: euclidean_pearson - value: 81.09762569927126 + value: 82.19243335103444 - type: euclidean_spearman - value: 79.33554265391781 + value: 81.33679307304334 - type: manhattan_pearson - value: 81.33942162521643 + value: 82.38752665975699 - type: manhattan_spearman - value: 79.91206181439438 + value: 81.31510583189689 - task: type: Classification dataset: @@ -187,9 +187,9 @@ model-index: revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy - value: 85.99675324675324 + value: 87.56818181818181 - type: f1 - value: 85.5564660877528 + value: 87.25826722019875 - task: type: Clustering dataset: @@ -200,7 +200,7 @@ model-index: revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure - value: 50.413005916654384 + value: 50.09239610327673 - task: type: Clustering dataset: @@ -211,7 +211,7 @@ model-index: revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure - value: 46.58170679922341 + value: 46.64733054606282 - task: type: Retrieval dataset: @@ -222,65 +222,65 @@ model-index: revision: f46a197baaae43b4f621051089b82a364682dfeb metrics: - type: map_at_1 - value: 34.588 + value: 33.997 - type: map_at_10 - value: 47.851 + value: 48.176 - type: map_at_100 - value: 49.484 + value: 49.82 - type: map_at_1000 - value: 49.6 + value: 49.924 - type: map_at_3 - value: 43.34 + value: 43.626 - type: map_at_5 - value: 45.734 + value: 46.275 - type: mrr_at_1 - value: 42.203 + value: 42.059999999999995 - type: mrr_at_10 - value: 53.315999999999995 + value: 53.726 - type: mrr_at_100 - value: 53.977 + value: 54.398 - type: mrr_at_1000 - value: 54.001 + value: 54.416 - type: mrr_at_3 - value: 50.381 + value: 50.714999999999996 - type: mrr_at_5 - value: 52.198 + value: 52.639 - type: ndcg_at_1 - value: 42.203 + value: 42.059999999999995 - type: ndcg_at_10 - value: 55.143 + value: 55.574999999999996 - type: ndcg_at_100 - value: 60.278 + value: 60.744 - type: ndcg_at_1000 - value: 61.497 + value: 61.85699999999999 - type: ndcg_at_3 - value: 48.9 + value: 49.363 - type: ndcg_at_5 - value: 51.712 + value: 52.44 - type: precision_at_1 - value: 42.203 + value: 42.059999999999995 - type: precision_at_10 - value: 11.016 + value: 11.101999999999999 - type: precision_at_100 - value: 1.718 + value: 1.73 - type: precision_at_1000 - value: 0.219 + value: 0.218 - type: precision_at_3 - value: 24.224999999999998 + value: 24.464 - type: precision_at_5 - value: 17.711 + value: 18.026 - type: recall_at_1 - value: 34.588 + value: 33.997 - type: recall_at_10 - value: 69.91000000000001 + value: 70.35900000000001 - type: recall_at_100 - value: 91.01700000000001 + value: 91.642 - type: recall_at_1000 - value: 98.02199999999999 + value: 97.977 - type: recall_at_3 - value: 51.9 + value: 52.76 - type: recall_at_5 - value: 59.604 + value: 61.148 - task: type: Retrieval dataset: @@ -291,65 +291,65 @@ model-index: revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 metrics: - type: map_at_1 - value: 35.649 + value: 35.884 - type: map_at_10 - value: 47.713 + value: 48.14 - type: map_at_100 - value: 49.043 + value: 49.5 - type: map_at_1000 - value: 49.178 + value: 49.63 - type: map_at_3 - value: 44.355 + value: 44.646 - type: map_at_5 - value: 46.152 + value: 46.617999999999995 - type: mrr_at_1 - value: 44.268 + value: 44.458999999999996 - type: mrr_at_10 - value: 53.403999999999996 + value: 53.751000000000005 - type: mrr_at_100 - value: 54.035999999999994 + value: 54.37800000000001 - type: mrr_at_1000 - value: 54.078 + value: 54.415 - type: mrr_at_3 - value: 51.507000000000005 + value: 51.815 - type: mrr_at_5 - value: 52.583999999999996 + value: 52.882 - type: ndcg_at_1 - value: 44.268 + value: 44.458999999999996 - type: ndcg_at_10 - value: 53.679 + value: 54.157 - type: ndcg_at_100 - value: 57.794000000000004 + value: 58.362 - type: ndcg_at_1000 - value: 59.74 + value: 60.178 - type: ndcg_at_3 - value: 49.348 + value: 49.661 - type: ndcg_at_5 - value: 51.266999999999996 + value: 51.74999999999999 - type: precision_at_1 - value: 44.268 + value: 44.458999999999996 - type: precision_at_10 - value: 10.120999999999999 + value: 10.248 - type: precision_at_100 - value: 1.566 + value: 1.5890000000000002 - type: precision_at_1000 - value: 0.20600000000000002 + value: 0.207 - type: precision_at_3 - value: 23.864 + value: 23.928 - type: precision_at_5 - value: 16.650000000000002 + value: 16.878999999999998 - type: recall_at_1 - value: 35.649 + value: 35.884 - type: recall_at_10 - value: 64.152 + value: 64.798 - type: recall_at_100 - value: 81.096 + value: 82.345 - type: recall_at_1000 - value: 92.957 + value: 93.267 - type: recall_at_3 - value: 51.498 + value: 51.847 - type: recall_at_5 - value: 56.977 + value: 57.601 - task: type: Retrieval dataset: @@ -360,65 +360,65 @@ model-index: revision: 4885aa143210c98657558c04aaf3dc47cfb54340 metrics: - type: map_at_1 - value: 38.372 + value: 39.383 - type: map_at_10 - value: 52.693 + value: 53.714 - type: map_at_100 - value: 53.796 + value: 54.838 - type: map_at_1000 - value: 53.836 + value: 54.87800000000001 - type: map_at_3 - value: 48.818 + value: 50.114999999999995 - type: map_at_5 - value: 51.052 + value: 52.153000000000006 - type: mrr_at_1 - value: 44.013000000000005 + value: 45.016 - type: mrr_at_10 - value: 55.769999999999996 + value: 56.732000000000006 - type: mrr_at_100 - value: 56.415000000000006 + value: 57.411 - type: mrr_at_1000 - value: 56.435 + value: 57.431 - type: mrr_at_3 - value: 52.884 + value: 54.044000000000004 - type: mrr_at_5 - value: 54.552 + value: 55.639 - type: ndcg_at_1 - value: 44.013000000000005 + value: 45.016 - type: ndcg_at_10 - value: 59.45 + value: 60.228 - type: ndcg_at_100 - value: 63.422 + value: 64.277 - type: ndcg_at_1000 - value: 64.214 + value: 65.07 - type: ndcg_at_3 - value: 52.829 + value: 54.124 - type: ndcg_at_5 - value: 56.079 + value: 57.147000000000006 - type: precision_at_1 - value: 44.013000000000005 + value: 45.016 - type: precision_at_10 - value: 9.912 + value: 9.937 - type: precision_at_100 - value: 1.286 + value: 1.288 - type: precision_at_1000 value: 0.13899999999999998 - type: precision_at_3 - value: 23.992 + value: 24.471999999999998 - type: precision_at_5 - value: 16.803 + value: 16.991 - type: recall_at_1 - value: 38.372 + value: 39.383 - type: recall_at_10 - value: 76.279 + value: 76.175 - type: recall_at_100 - value: 92.842 + value: 93.02 - type: recall_at_1000 - value: 98.41 + value: 98.60900000000001 - type: recall_at_3 - value: 58.738 + value: 60.265 - type: recall_at_5 - value: 66.51899999999999 + value: 67.46600000000001 - task: type: Retrieval dataset: @@ -429,65 +429,65 @@ model-index: revision: 5003b3064772da1887988e05400cf3806fe491f2 metrics: - type: map_at_1 - value: 26.784999999999997 + value: 27.426000000000002 - type: map_at_10 - value: 37.152 + value: 37.397000000000006 - type: map_at_100 - value: 38.371 + value: 38.61 - type: map_at_1000 - value: 38.437 + value: 38.678000000000004 - type: map_at_3 - value: 34.211999999999996 + value: 34.150999999999996 - type: map_at_5 - value: 35.791000000000004 + value: 36.137 - type: mrr_at_1 - value: 29.153000000000002 + value: 29.944 - type: mrr_at_10 - value: 39.312999999999995 + value: 39.654 - type: mrr_at_100 - value: 40.32 + value: 40.638000000000005 - type: mrr_at_1000 - value: 40.367999999999995 + value: 40.691 - type: mrr_at_3 - value: 36.760999999999996 + value: 36.817 - type: mrr_at_5 - value: 38.083 + value: 38.524 - type: ndcg_at_1 - value: 29.153000000000002 + value: 29.944 - type: ndcg_at_10 - value: 42.785000000000004 + value: 43.094 - type: ndcg_at_100 - value: 48.613 + value: 48.789 - type: ndcg_at_1000 - value: 50.166 + value: 50.339999999999996 - type: ndcg_at_3 - value: 37.255 + value: 36.984 - type: ndcg_at_5 - value: 39.763999999999996 + value: 40.248 - type: precision_at_1 - value: 29.153000000000002 + value: 29.944 - type: precision_at_10 - value: 6.734 + value: 6.78 - type: precision_at_100 - value: 1.0250000000000001 + value: 1.024 - type: precision_at_1000 - value: 0.11900000000000001 + value: 0.11800000000000001 - type: precision_at_3 - value: 16.234 + value: 15.895000000000001 - type: precision_at_5 - value: 11.232000000000001 + value: 11.39 - type: recall_at_1 - value: 26.784999999999997 + value: 27.426000000000002 - type: recall_at_10 - value: 57.915000000000006 + value: 58.464000000000006 - type: recall_at_100 - value: 84.473 + value: 84.193 - type: recall_at_1000 - value: 96.011 + value: 95.52000000000001 - type: recall_at_3 - value: 43.105 + value: 42.172 - type: recall_at_5 - value: 49.15 + value: 50.101 - task: type: Retrieval dataset: @@ -498,65 +498,65 @@ model-index: revision: 90fceea13679c63fe563ded68f3b6f06e50061de metrics: - type: map_at_1 - value: 20.24 + value: 19.721 - type: map_at_10 - value: 31.493 + value: 31.604 - type: map_at_100 - value: 32.771 + value: 32.972 - type: map_at_1000 - value: 32.883 + value: 33.077 - type: map_at_3 - value: 27.062 + value: 27.218999999999998 - type: map_at_5 - value: 29.421999999999997 + value: 29.53 - type: mrr_at_1 - value: 25.622 + value: 25.0 - type: mrr_at_10 - value: 35.729 + value: 35.843 - type: mrr_at_100 - value: 36.613 + value: 36.785000000000004 - type: mrr_at_1000 - value: 36.665 + value: 36.842000000000006 - type: mrr_at_3 - value: 32.048 + value: 32.193 - type: mrr_at_5 - value: 34.169 + value: 34.264 - type: ndcg_at_1 - value: 25.622 + value: 25.0 - type: ndcg_at_10 - value: 38.463 + value: 38.606 - type: ndcg_at_100 - value: 43.909 + value: 44.272 - type: ndcg_at_1000 - value: 46.21 + value: 46.527 - type: ndcg_at_3 - value: 30.563000000000002 + value: 30.985000000000003 - type: ndcg_at_5 - value: 34.178999999999995 + value: 34.43 - type: precision_at_1 - value: 25.622 + value: 25.0 - type: precision_at_10 - value: 7.7490000000000006 + value: 7.811 - type: precision_at_100 - value: 1.1780000000000002 + value: 1.203 - type: precision_at_1000 - value: 0.149 + value: 0.15 - type: precision_at_3 - value: 15.049999999999999 + value: 15.423 - type: precision_at_5 - value: 11.616999999999999 + value: 11.791 - type: recall_at_1 - value: 20.24 + value: 19.721 - type: recall_at_10 - value: 55.657000000000004 + value: 55.625 - type: recall_at_100 - value: 78.803 + value: 79.34400000000001 - type: recall_at_1000 - value: 94.801 + value: 95.208 - type: recall_at_3 - value: 34.171 + value: 35.19 - type: recall_at_5 - value: 43.16 + value: 43.626 - task: type: Retrieval dataset: @@ -567,65 +567,65 @@ model-index: revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 metrics: - type: map_at_1 - value: 32.501000000000005 + value: 33.784 - type: map_at_10 - value: 46.286 + value: 47.522 - type: map_at_100 - value: 47.732 + value: 48.949999999999996 - type: map_at_1000 - value: 47.814 + value: 49.038 - type: map_at_3 - value: 41.957 + value: 43.284 - type: map_at_5 - value: 44.506 + value: 45.629 - type: mrr_at_1 - value: 39.75 + value: 41.482 - type: mrr_at_10 - value: 51.285000000000004 + value: 52.830999999999996 - type: mrr_at_100 - value: 52.051 + value: 53.559999999999995 - type: mrr_at_1000 - value: 52.075 + value: 53.588 - type: mrr_at_3 - value: 48.315999999999995 + value: 50.016000000000005 - type: mrr_at_5 - value: 50.125 + value: 51.614000000000004 - type: ndcg_at_1 - value: 39.75 + value: 41.482 - type: ndcg_at_10 - value: 53.361999999999995 + value: 54.569 - type: ndcg_at_100 - value: 58.703 + value: 59.675999999999995 - type: ndcg_at_1000 - value: 59.962 + value: 60.989000000000004 - type: ndcg_at_3 - value: 46.786 + value: 48.187000000000005 - type: ndcg_at_5 - value: 50.169 + value: 51.183 - type: precision_at_1 - value: 39.75 + value: 41.482 - type: precision_at_10 - value: 10.154 + value: 10.221 - type: precision_at_100 - value: 1.485 + value: 1.486 - type: precision_at_1000 - value: 0.17600000000000002 + value: 0.17500000000000002 - type: precision_at_3 - value: 23.003 + value: 23.548 - type: precision_at_5 - value: 16.766000000000002 + value: 16.805 - type: recall_at_1 - value: 32.501000000000005 + value: 33.784 - type: recall_at_10 - value: 68.901 + value: 69.798 - type: recall_at_100 - value: 90.527 + value: 90.098 - type: recall_at_1000 - value: 98.307 + value: 98.176 - type: recall_at_3 - value: 51.056000000000004 + value: 52.127 - type: recall_at_5 - value: 59.471 + value: 59.861 - task: type: Retrieval dataset: @@ -636,65 +636,65 @@ model-index: revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 metrics: - type: map_at_1 - value: 27.962999999999997 + value: 28.038999999999998 - type: map_at_10 - value: 41.434 + value: 41.904 - type: map_at_100 - value: 42.961 + value: 43.36 - type: map_at_1000 - value: 43.051 + value: 43.453 - type: map_at_3 - value: 37.579 + value: 37.785999999999994 - type: map_at_5 - value: 39.579 + value: 40.105000000000004 - type: mrr_at_1 - value: 34.932 + value: 35.046 - type: mrr_at_10 - value: 46.455999999999996 + value: 46.926 - type: mrr_at_100 - value: 47.362 + value: 47.815000000000005 - type: mrr_at_1000 - value: 47.398 + value: 47.849000000000004 - type: mrr_at_3 - value: 43.855 + value: 44.273 - type: mrr_at_5 - value: 45.322 + value: 45.774 - type: ndcg_at_1 - value: 34.932 + value: 35.046 - type: ndcg_at_10 - value: 48.323 + value: 48.937000000000005 - type: ndcg_at_100 - value: 54.173 + value: 54.544000000000004 - type: ndcg_at_1000 - value: 55.69 + value: 56.069 - type: ndcg_at_3 - value: 42.498000000000005 + value: 42.858000000000004 - type: ndcg_at_5 - value: 44.973 + value: 45.644 - type: precision_at_1 - value: 34.932 + value: 35.046 - type: precision_at_10 - value: 9.224 + value: 9.452 - type: precision_at_100 value: 1.429 - type: precision_at_1000 - value: 0.172 + value: 0.173 - type: precision_at_3 - value: 21.005 + value: 21.346999999999998 - type: precision_at_5 - value: 15.0 + value: 15.342 - type: recall_at_1 - value: 27.962999999999997 + value: 28.038999999999998 - type: recall_at_10 - value: 63.563 + value: 64.59700000000001 - type: recall_at_100 - value: 87.679 + value: 87.735 - type: recall_at_1000 - value: 97.381 + value: 97.41300000000001 - type: recall_at_3 - value: 47.205999999999996 + value: 47.368 - type: recall_at_5 - value: 53.784 + value: 54.93900000000001 - task: type: Retrieval dataset: @@ -705,65 +705,65 @@ model-index: revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 - value: 27.9895 + value: 28.17291666666667 - type: map_at_10 - value: 39.67808333333333 + value: 40.025749999999995 - type: map_at_100 - value: 41.05 + value: 41.39208333333333 - type: map_at_1000 - value: 41.15800000000001 + value: 41.499249999999996 - type: map_at_3 - value: 36.079499999999996 + value: 36.347 - type: map_at_5 - value: 38.056749999999994 + value: 38.41391666666667 - type: mrr_at_1 - value: 33.405583333333325 + value: 33.65925 - type: mrr_at_10 - value: 43.6965 + value: 44.085499999999996 - type: mrr_at_100 - value: 44.568000000000005 + value: 44.94116666666667 - type: mrr_at_1000 - value: 44.61208333333334 + value: 44.9855 - type: mrr_at_3 - value: 40.96574999999999 + value: 41.2815 - type: mrr_at_5 - value: 42.529833333333336 + value: 42.91491666666666 - type: ndcg_at_1 - value: 33.405583333333325 + value: 33.65925 - type: ndcg_at_10 - value: 46.016 + value: 46.430833333333325 - type: ndcg_at_100 - value: 51.39475 + value: 51.761 - type: ndcg_at_1000 - value: 53.17333333333334 + value: 53.50899999999999 - type: ndcg_at_3 - value: 40.166666666666664 + value: 40.45133333333333 - type: ndcg_at_5 - value: 42.899750000000004 + value: 43.31483333333334 - type: precision_at_1 - value: 33.405583333333325 + value: 33.65925 - type: precision_at_10 - value: 8.408999999999999 + value: 8.4995 - type: precision_at_100 - value: 1.3129166666666665 + value: 1.3210000000000004 - type: precision_at_1000 - value: 0.16583333333333336 + value: 0.16591666666666666 - type: precision_at_3 - value: 19.05825 + value: 19.165083333333335 - type: precision_at_5 - value: 13.6845 + value: 13.81816666666667 - type: recall_at_1 - value: 27.9895 + value: 28.17291666666667 - type: recall_at_10 - value: 60.572416666666676 + value: 61.12624999999999 - type: recall_at_100 - value: 83.63975 + value: 83.97266666666667 - type: recall_at_1000 - value: 95.58775 + value: 95.66550000000001 - type: recall_at_3 - value: 44.402750000000005 + value: 44.661249999999995 - type: recall_at_5 - value: 51.40116666666666 + value: 51.983333333333334 - task: type: Retrieval dataset: @@ -774,65 +774,65 @@ model-index: revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a metrics: - type: map_at_1 - value: 24.451 + value: 24.681 - type: map_at_10 - value: 34.526 + value: 34.892 - type: map_at_100 - value: 35.732 + value: 35.996 - type: map_at_1000 - value: 35.824 + value: 36.083 - type: map_at_3 - value: 31.503999999999998 + value: 31.491999999999997 - type: map_at_5 - value: 33.241 + value: 33.632 - type: mrr_at_1 - value: 28.221 + value: 28.528 - type: mrr_at_10 - value: 37.34 + value: 37.694 - type: mrr_at_100 - value: 38.389 + value: 38.613 - type: mrr_at_1000 - value: 38.443 + value: 38.668 - type: mrr_at_3 value: 34.714 - type: mrr_at_5 - value: 36.217 + value: 36.616 - type: ndcg_at_1 - value: 28.221 + value: 28.528 - type: ndcg_at_10 - value: 40.105000000000004 + value: 40.703 - type: ndcg_at_100 - value: 45.619 + value: 45.993 - type: ndcg_at_1000 - value: 47.597 + value: 47.847 - type: ndcg_at_3 - value: 34.711 + value: 34.622 - type: ndcg_at_5 - value: 37.38 + value: 38.035999999999994 - type: precision_at_1 - value: 28.221 + value: 28.528 - type: precision_at_10 - value: 6.7330000000000005 + value: 6.902 - type: precision_at_100 - value: 1.0170000000000001 + value: 1.0370000000000001 - type: precision_at_1000 value: 0.126 - type: precision_at_3 value: 15.798000000000002 - type: precision_at_5 - value: 11.227 + value: 11.655999999999999 - type: recall_at_1 - value: 24.451 + value: 24.681 - type: recall_at_10 - value: 54.332 + value: 55.81 - type: recall_at_100 - value: 78.842 + value: 79.785 - type: recall_at_1000 - value: 92.868 + value: 92.959 - type: recall_at_3 - value: 39.495999999999995 + value: 39.074 - type: recall_at_5 - value: 46.198 + value: 47.568 - task: type: Retrieval dataset: @@ -843,65 +843,65 @@ model-index: revision: 46989137a86843e03a6195de44b09deda022eec7 metrics: - type: map_at_1 - value: 18.989 + value: 18.627 - type: map_at_10 - value: 28.189999999999998 + value: 27.872000000000003 - type: map_at_100 - value: 29.575000000000003 + value: 29.237999999999996 - type: map_at_1000 - value: 29.705 + value: 29.363 - type: map_at_3 - value: 25.406000000000002 + value: 24.751 - type: map_at_5 - value: 26.851000000000003 + value: 26.521 - type: mrr_at_1 - value: 23.400000000000002 + value: 23.021 - type: mrr_at_10 - value: 32.231 + value: 31.924000000000003 - type: mrr_at_100 - value: 33.239000000000004 + value: 32.922000000000004 - type: mrr_at_1000 - value: 33.309 + value: 32.988 - type: mrr_at_3 - value: 29.869 + value: 29.192 - type: mrr_at_5 - value: 31.102999999999998 + value: 30.798 - type: ndcg_at_1 - value: 23.400000000000002 + value: 23.021 - type: ndcg_at_10 - value: 33.634 + value: 33.535 - type: ndcg_at_100 - value: 39.772999999999996 + value: 39.732 - type: ndcg_at_1000 - value: 42.385 + value: 42.201 - type: ndcg_at_3 - value: 28.938999999999997 + value: 28.153 - type: ndcg_at_5 - value: 30.913 + value: 30.746000000000002 - type: precision_at_1 - value: 23.400000000000002 + value: 23.021 - type: precision_at_10 - value: 6.366 + value: 6.459 - type: precision_at_100 - value: 1.1159999999999999 + value: 1.1320000000000001 - type: precision_at_1000 value: 0.153 - type: precision_at_3 - value: 14.212 + value: 13.719000000000001 - type: precision_at_5 - value: 10.151 + value: 10.193000000000001 - type: recall_at_1 - value: 18.989 + value: 18.627 - type: recall_at_10 - value: 45.837 + value: 46.463 - type: recall_at_100 - value: 73.04899999999999 + value: 74.226 - type: recall_at_1000 - value: 91.245 + value: 91.28500000000001 - type: recall_at_3 - value: 32.309 + value: 31.357000000000003 - type: recall_at_5 - value: 37.665 + value: 38.067 - task: type: Retrieval dataset: @@ -912,65 +912,65 @@ model-index: revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 metrics: - type: map_at_1 - value: 30.595 + value: 31.457 - type: map_at_10 - value: 42.286 + value: 42.888 - type: map_at_100 - value: 43.586999999999996 + value: 44.24 - type: map_at_1000 - value: 43.669000000000004 + value: 44.327 - type: map_at_3 - value: 38.888 + value: 39.588 - type: map_at_5 - value: 40.669 + value: 41.423 - type: mrr_at_1 - value: 36.287000000000006 + value: 37.126999999999995 - type: mrr_at_10 - value: 46.405 + value: 47.083000000000006 - type: mrr_at_100 - value: 47.282999999999994 + value: 47.997 - type: mrr_at_1000 - value: 47.327000000000005 + value: 48.044 - type: mrr_at_3 - value: 43.874 + value: 44.574000000000005 - type: mrr_at_5 - value: 45.414 + value: 46.202 - type: ndcg_at_1 - value: 36.287000000000006 + value: 37.126999999999995 - type: ndcg_at_10 - value: 48.407 + value: 48.833 - type: ndcg_at_100 - value: 53.824000000000005 + value: 54.327000000000005 - type: ndcg_at_1000 - value: 55.483000000000004 + value: 56.011 - type: ndcg_at_3 - value: 42.9 + value: 43.541999999999994 - type: ndcg_at_5 - value: 45.391999999999996 + value: 46.127 - type: precision_at_1 - value: 36.287000000000006 + value: 37.126999999999995 - type: precision_at_10 - value: 8.414000000000001 + value: 8.376999999999999 - type: precision_at_100 - value: 1.232 + value: 1.2309999999999999 - type: precision_at_1000 - value: 0.147 + value: 0.146 - type: precision_at_3 - value: 20.118 + value: 20.211000000000002 - type: precision_at_5 - value: 13.993 + value: 14.16 - type: recall_at_1 - value: 30.595 + value: 31.457 - type: recall_at_10 - value: 62.656 + value: 62.369 - type: recall_at_100 - value: 85.74199999999999 + value: 85.444 - type: recall_at_1000 - value: 96.854 + value: 96.65599999999999 - type: recall_at_3 - value: 47.413 + value: 47.961 - type: recall_at_5 - value: 54.04 + value: 54.676 - task: type: Retrieval dataset: @@ -981,65 +981,65 @@ model-index: revision: 160c094312a0e1facb97e55eeddb698c0abe3571 metrics: - type: map_at_1 - value: 28.236 + value: 27.139999999999997 - type: map_at_10 - value: 39.751 + value: 38.801 - type: map_at_100 - value: 41.435 + value: 40.549 - type: map_at_1000 - value: 41.677 + value: 40.802 - type: map_at_3 - value: 35.957 + value: 35.05 - type: map_at_5 - value: 38.112 + value: 36.884 - type: mrr_at_1 - value: 33.794000000000004 + value: 33.004 - type: mrr_at_10 - value: 44.449 + value: 43.864 - type: mrr_at_100 - value: 45.268 + value: 44.667 - type: mrr_at_1000 - value: 45.311 + value: 44.717 - type: mrr_at_3 - value: 41.502 + value: 40.777 - type: mrr_at_5 - value: 43.142 + value: 42.319 - type: ndcg_at_1 - value: 33.794000000000004 + value: 33.004 - type: ndcg_at_10 - value: 46.787 + value: 46.022 - type: ndcg_at_100 - value: 52.290000000000006 + value: 51.542 - type: ndcg_at_1000 - value: 54.336 + value: 53.742000000000004 - type: ndcg_at_3 - value: 40.78 + value: 39.795 - type: ndcg_at_5 - value: 43.669999999999995 + value: 42.272 - type: precision_at_1 - value: 33.794000000000004 + value: 33.004 - type: precision_at_10 - value: 9.051 + value: 9.012 - type: precision_at_100 - value: 1.7919999999999998 + value: 1.7770000000000001 - type: precision_at_1000 - value: 0.259 + value: 0.26 - type: precision_at_3 - value: 19.368 + value: 19.038 - type: precision_at_5 - value: 14.229 + value: 13.675999999999998 - type: recall_at_1 - value: 28.236 + value: 27.139999999999997 - type: recall_at_10 - value: 61.358000000000004 + value: 60.961 - type: recall_at_100 - value: 85.028 + value: 84.451 - type: recall_at_1000 - value: 97.813 + value: 98.113 - type: recall_at_3 - value: 44.207 + value: 43.001 - type: recall_at_5 - value: 51.885000000000005 + value: 49.896 - task: type: Retrieval dataset: @@ -1050,65 +1050,203 @@ model-index: revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 - value: 17.505000000000003 + value: 17.936 - type: map_at_10 - value: 26.762000000000004 + value: 27.399 - type: map_at_100 - value: 28.113 + value: 28.632 - type: map_at_1000 - value: 28.222 + value: 28.738000000000003 - type: map_at_3 - value: 23.876 + value: 24.456 - type: map_at_5 - value: 25.572 + value: 26.06 - type: mrr_at_1 value: 19.224 - type: mrr_at_10 - value: 28.660000000000004 + value: 28.998 - type: mrr_at_100 - value: 29.863 + value: 30.11 - type: mrr_at_1000 - value: 29.935000000000002 + value: 30.177 - type: mrr_at_3 - value: 25.878 + value: 26.247999999999998 - type: mrr_at_5 - value: 27.449 + value: 27.708 - type: ndcg_at_1 value: 19.224 - type: ndcg_at_10 - value: 32.054 + value: 32.911 - type: ndcg_at_100 - value: 38.339 + value: 38.873999999999995 - type: ndcg_at_1000 - value: 40.8 + value: 41.277 - type: ndcg_at_3 - value: 26.491 + value: 27.142 - type: ndcg_at_5 - value: 29.298999999999996 + value: 29.755 - type: precision_at_1 value: 19.224 - type: precision_at_10 - value: 5.434 + value: 5.6930000000000005 + - type: precision_at_100 + value: 0.9259999999999999 + - type: precision_at_1000 + value: 0.126 + - type: precision_at_3 + value: 12.138 + - type: precision_at_5 + value: 8.909 + - type: recall_at_1 + value: 17.936 + - type: recall_at_10 + value: 48.096 + - type: recall_at_100 + value: 75.389 + - type: recall_at_1000 + value: 92.803 + - type: recall_at_3 + value: 32.812999999999995 + - type: recall_at_5 + value: 38.851 + - task: + type: Retrieval + dataset: + type: mteb/climate-fever + name: MTEB ClimateFEVER + config: default + split: test + revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 + metrics: + - type: map_at_1 + value: 22.076999999999998 + - type: map_at_10 + value: 35.44 + - type: map_at_100 + value: 37.651 + - type: map_at_1000 + value: 37.824999999999996 + - type: map_at_3 + value: 30.764999999999997 + - type: map_at_5 + value: 33.26 + - type: mrr_at_1 + value: 50.163000000000004 + - type: mrr_at_10 + value: 61.207 + - type: mrr_at_100 + value: 61.675000000000004 + - type: mrr_at_1000 + value: 61.692 + - type: mrr_at_3 + value: 58.60999999999999 + - type: mrr_at_5 + value: 60.307 + - type: ndcg_at_1 + value: 50.163000000000004 + - type: ndcg_at_10 + value: 45.882 + - type: ndcg_at_100 + value: 53.239999999999995 + - type: ndcg_at_1000 + value: 55.852000000000004 + - type: ndcg_at_3 + value: 40.514 + - type: ndcg_at_5 + value: 42.038 + - type: precision_at_1 + value: 50.163000000000004 + - type: precision_at_10 + value: 13.466000000000001 + - type: precision_at_100 + value: 2.164 + - type: precision_at_1000 + value: 0.266 + - type: precision_at_3 + value: 29.707 + - type: precision_at_5 + value: 21.694 + - type: recall_at_1 + value: 22.076999999999998 + - type: recall_at_10 + value: 50.193 + - type: recall_at_100 + value: 74.993 + - type: recall_at_1000 + value: 89.131 + - type: recall_at_3 + value: 35.472 + - type: recall_at_5 + value: 41.814 + - task: + type: Retrieval + dataset: + type: mteb/dbpedia + name: MTEB DBPedia + config: default + split: test + revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 + metrics: + - type: map_at_1 + value: 9.953 + - type: map_at_10 + value: 24.515 + - type: map_at_100 + value: 36.173 + - type: map_at_1000 + value: 38.351 + - type: map_at_3 + value: 16.592000000000002 + - type: map_at_5 + value: 20.036 + - type: mrr_at_1 + value: 74.25 + - type: mrr_at_10 + value: 81.813 + - type: mrr_at_100 + value: 82.006 + - type: mrr_at_1000 + value: 82.011 + - type: mrr_at_3 + value: 80.875 + - type: mrr_at_5 + value: 81.362 + - type: ndcg_at_1 + value: 62.5 + - type: ndcg_at_10 + value: 52.42 + - type: ndcg_at_100 + value: 56.808 + - type: ndcg_at_1000 + value: 63.532999999999994 + - type: ndcg_at_3 + value: 56.654 + - type: ndcg_at_5 + value: 54.18300000000001 + - type: precision_at_1 + value: 74.25 + - type: precision_at_10 + value: 42.699999999999996 - type: precision_at_100 - value: 0.911 + value: 13.675 - type: precision_at_1000 - value: 0.125 + value: 2.664 - type: precision_at_3 - value: 11.83 + value: 60.5 - type: precision_at_5 - value: 8.834999999999999 + value: 52.800000000000004 - type: recall_at_1 - value: 17.505000000000003 + value: 9.953 - type: recall_at_10 - value: 46.309 + value: 30.253999999999998 - type: recall_at_100 - value: 74.579 + value: 62.516000000000005 - type: recall_at_1000 - value: 92.384 + value: 84.163 - type: recall_at_3 - value: 31.734 + value: 18.13 - type: recall_at_5 - value: 38.361000000000004 + value: 22.771 - task: type: Classification dataset: @@ -1119,9 +1257,78 @@ model-index: revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy - value: 67.085 + value: 79.455 - type: f1 - value: 61.019909873305686 + value: 74.16798697647569 + - task: + type: Retrieval + dataset: + type: mteb/fever + name: MTEB FEVER + config: default + split: test + revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 + metrics: + - type: map_at_1 + value: 87.531 + - type: map_at_10 + value: 93.16799999999999 + - type: map_at_100 + value: 93.341 + - type: map_at_1000 + value: 93.349 + - type: map_at_3 + value: 92.444 + - type: map_at_5 + value: 92.865 + - type: mrr_at_1 + value: 94.014 + - type: mrr_at_10 + value: 96.761 + - type: mrr_at_100 + value: 96.762 + - type: mrr_at_1000 + value: 96.762 + - type: mrr_at_3 + value: 96.672 + - type: mrr_at_5 + value: 96.736 + - type: ndcg_at_1 + value: 94.014 + - type: ndcg_at_10 + value: 95.112 + - type: ndcg_at_100 + value: 95.578 + - type: ndcg_at_1000 + value: 95.68900000000001 + - type: ndcg_at_3 + value: 94.392 + - type: ndcg_at_5 + value: 94.72500000000001 + - type: precision_at_1 + value: 94.014 + - type: precision_at_10 + value: 11.065 + - type: precision_at_100 + value: 1.157 + - type: precision_at_1000 + value: 0.11800000000000001 + - type: precision_at_3 + value: 35.259 + - type: precision_at_5 + value: 21.599 + - type: recall_at_1 + value: 87.531 + - type: recall_at_10 + value: 97.356 + - type: recall_at_100 + value: 98.965 + - type: recall_at_1000 + value: 99.607 + - type: recall_at_3 + value: 95.312 + - type: recall_at_5 + value: 96.295 - task: type: Retrieval dataset: @@ -1132,65 +1339,134 @@ model-index: revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: map_at_1 - value: 32.251999999999995 + value: 32.055 - type: map_at_10 - value: 53.98500000000001 + value: 53.114 - type: map_at_100 - value: 56.093 + value: 55.235 - type: map_at_1000 - value: 56.198 + value: 55.345 - type: map_at_3 - value: 46.765 + value: 45.854 - type: map_at_5 - value: 50.739999999999995 + value: 50.025 - type: mrr_at_1 - value: 60.956999999999994 + value: 60.34 - type: mrr_at_10 - value: 69.38600000000001 + value: 68.804 - type: mrr_at_100 - value: 69.877 + value: 69.309 - type: mrr_at_1000 - value: 69.884 + value: 69.32199999999999 - type: mrr_at_3 - value: 67.052 + value: 66.40899999999999 - type: mrr_at_5 - value: 68.356 + value: 67.976 - type: ndcg_at_1 - value: 60.956999999999994 + value: 60.34 - type: ndcg_at_10 - value: 62.78399999999999 + value: 62.031000000000006 - type: ndcg_at_100 - value: 68.743 + value: 68.00500000000001 - type: ndcg_at_1000 - value: 69.92399999999999 + value: 69.286 - type: ndcg_at_3 - value: 57.336 + value: 56.355999999999995 - type: ndcg_at_5 - value: 59.121 + value: 58.687 - type: precision_at_1 - value: 60.956999999999994 + value: 60.34 - type: precision_at_10 - value: 17.346 + value: 17.176 - type: precision_at_100 - value: 2.3689999999999998 + value: 2.36 - type: precision_at_1000 value: 0.259 - type: precision_at_3 - value: 37.912 + value: 37.14 + - type: precision_at_5 + value: 27.809 + - type: recall_at_1 + value: 32.055 + - type: recall_at_10 + value: 70.91 + - type: recall_at_100 + value: 91.83 + - type: recall_at_1000 + value: 98.871 + - type: recall_at_3 + value: 51.202999999999996 + - type: recall_at_5 + value: 60.563 + - task: + type: Retrieval + dataset: + type: mteb/hotpotqa + name: MTEB HotpotQA + config: default + split: test + revision: ab518f4d6fcca38d87c25209f94beba119d02014 + metrics: + - type: map_at_1 + value: 43.68 + - type: map_at_10 + value: 64.389 + - type: map_at_100 + value: 65.24 + - type: map_at_1000 + value: 65.303 + - type: map_at_3 + value: 61.309000000000005 + - type: map_at_5 + value: 63.275999999999996 + - type: mrr_at_1 + value: 87.36 + - type: mrr_at_10 + value: 91.12 + - type: mrr_at_100 + value: 91.227 + - type: mrr_at_1000 + value: 91.229 + - type: mrr_at_3 + value: 90.57600000000001 + - type: mrr_at_5 + value: 90.912 + - type: ndcg_at_1 + value: 87.36 + - type: ndcg_at_10 + value: 73.076 + - type: ndcg_at_100 + value: 75.895 + - type: ndcg_at_1000 + value: 77.049 + - type: ndcg_at_3 + value: 68.929 + - type: ndcg_at_5 + value: 71.28 + - type: precision_at_1 + value: 87.36 + - type: precision_at_10 + value: 14.741000000000001 + - type: precision_at_100 + value: 1.694 + - type: precision_at_1000 + value: 0.185 + - type: precision_at_3 + value: 43.043 - type: precision_at_5 - value: 27.900999999999996 + value: 27.681 - type: recall_at_1 - value: 32.251999999999995 + value: 43.68 - type: recall_at_10 - value: 71.616 + value: 73.707 - type: recall_at_100 - value: 92.685 + value: 84.7 - type: recall_at_1000 - value: 98.983 + value: 92.309 - type: recall_at_3 - value: 52.064 + value: 64.564 - type: recall_at_5 - value: 60.49099999999999 + value: 69.203 - task: type: Classification dataset: @@ -1201,11 +1477,80 @@ model-index: revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy - value: 96.4592 + value: 96.75399999999999 - type: ap - value: 94.57299077219179 + value: 95.29389839242187 - type: f1 - value: 96.45842059801627 + value: 96.75348377433475 + - task: + type: Retrieval + dataset: + type: mteb/msmarco + name: MTEB MSMARCO + config: default + split: dev + revision: c5a29a104738b98a9e76336939199e264163d4a0 + metrics: + - type: map_at_1 + value: 25.176 + - type: map_at_10 + value: 38.598 + - type: map_at_100 + value: 39.707 + - type: map_at_1000 + value: 39.744 + - type: map_at_3 + value: 34.566 + - type: map_at_5 + value: 36.863 + - type: mrr_at_1 + value: 25.874000000000002 + - type: mrr_at_10 + value: 39.214 + - type: mrr_at_100 + value: 40.251 + - type: mrr_at_1000 + value: 40.281 + - type: mrr_at_3 + value: 35.291 + - type: mrr_at_5 + value: 37.545 + - type: ndcg_at_1 + value: 25.874000000000002 + - type: ndcg_at_10 + value: 45.98 + - type: ndcg_at_100 + value: 51.197 + - type: ndcg_at_1000 + value: 52.073 + - type: ndcg_at_3 + value: 37.785999999999994 + - type: ndcg_at_5 + value: 41.870000000000005 + - type: precision_at_1 + value: 25.874000000000002 + - type: precision_at_10 + value: 7.181 + - type: precision_at_100 + value: 0.979 + - type: precision_at_1000 + value: 0.106 + - type: precision_at_3 + value: 16.051000000000002 + - type: precision_at_5 + value: 11.713 + - type: recall_at_1 + value: 25.176 + - type: recall_at_10 + value: 68.67699999999999 + - type: recall_at_100 + value: 92.55 + - type: recall_at_1000 + value: 99.164 + - type: recall_at_3 + value: 46.372 + - type: recall_at_5 + value: 56.16 - task: type: Classification dataset: @@ -1216,9 +1561,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 98.45873233014134 + value: 99.03784769721841 - type: f1 - value: 98.38426074551533 + value: 98.97791641821495 - task: type: Classification dataset: @@ -1229,9 +1574,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 90.01823985408116 + value: 91.88326493388054 - type: f1 - value: 70.71419843084274 + value: 73.74809928034335 - task: type: Classification dataset: @@ -1242,9 +1587,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 84.35104236718225 + value: 85.41358439811701 - type: f1 - value: 82.50884520186432 + value: 83.503679460639 - task: type: Classification dataset: @@ -1255,9 +1600,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 88.0665770006725 + value: 89.77135171486215 - type: f1 - value: 87.06928510969733 + value: 88.89843747468366 - task: type: Clustering dataset: @@ -1268,7 +1613,7 @@ model-index: revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure - value: 46.053400985420204 + value: 46.22695362087359 - task: type: Clustering dataset: @@ -1279,7 +1624,7 @@ model-index: revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure - value: 44.445957227318054 + value: 44.132372165849425 - task: type: Reranking dataset: @@ -1290,9 +1635,9 @@ model-index: revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map - value: 33.277065197675775 + value: 33.35680810650402 - type: mrr - value: 34.654704063060656 + value: 34.72625715637218 - task: type: Retrieval dataset: @@ -1303,65 +1648,134 @@ model-index: revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: map_at_1 - value: 6.728000000000001 + value: 7.165000000000001 - type: map_at_10 - value: 15.052999999999999 + value: 15.424 - type: map_at_100 - value: 19.901 + value: 20.28 - type: map_at_1000 - value: 21.72 + value: 22.065 - type: map_at_3 - value: 10.901 + value: 11.236 - type: map_at_5 - value: 12.651000000000002 + value: 13.025999999999998 - type: mrr_at_1 - value: 52.322 + value: 51.702999999999996 - type: mrr_at_10 - value: 60.614999999999995 + value: 59.965 - type: mrr_at_100 - value: 61.199000000000005 + value: 60.667 - type: mrr_at_1000 - value: 61.227 + value: 60.702999999999996 - type: mrr_at_3 - value: 58.977999999999994 + value: 58.772000000000006 - type: mrr_at_5 - value: 59.907 + value: 59.267 - type: ndcg_at_1 - value: 50.619 + value: 49.536 - type: ndcg_at_10 - value: 40.278000000000006 + value: 40.6 - type: ndcg_at_100 + value: 37.848 + - type: ndcg_at_1000 + value: 46.657 + - type: ndcg_at_3 + value: 46.117999999999995 + - type: ndcg_at_5 + value: 43.619 + - type: precision_at_1 + value: 51.393 + - type: precision_at_10 + value: 30.31 + - type: precision_at_100 + value: 9.972 + - type: precision_at_1000 + value: 2.329 + - type: precision_at_3 + value: 43.137 + - type: precision_at_5 value: 37.585 + - type: recall_at_1 + value: 7.165000000000001 + - type: recall_at_10 + value: 19.689999999999998 + - type: recall_at_100 + value: 39.237 + - type: recall_at_1000 + value: 71.417 + - type: recall_at_3 + value: 12.247 + - type: recall_at_5 + value: 14.902999999999999 + - task: + type: Retrieval + dataset: + type: mteb/nq + name: MTEB NQ + config: default + split: test + revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 + metrics: + - type: map_at_1 + value: 42.653999999999996 + - type: map_at_10 + value: 59.611999999999995 + - type: map_at_100 + value: 60.32300000000001 + - type: map_at_1000 + value: 60.336 + - type: map_at_3 + value: 55.584999999999994 + - type: map_at_5 + value: 58.19 + - type: mrr_at_1 + value: 47.683 + - type: mrr_at_10 + value: 62.06700000000001 + - type: mrr_at_100 + value: 62.537 + - type: mrr_at_1000 + value: 62.544999999999995 + - type: mrr_at_3 + value: 59.178 + - type: mrr_at_5 + value: 61.034 + - type: ndcg_at_1 + value: 47.654 + - type: ndcg_at_10 + value: 67.001 + - type: ndcg_at_100 + value: 69.73899999999999 - type: ndcg_at_1000 - value: 46.459 + value: 69.986 - type: ndcg_at_3 - value: 46.143 + value: 59.95700000000001 - type: ndcg_at_5 - value: 43.7 + value: 64.025 - type: precision_at_1 - value: 52.012 + value: 47.654 - type: precision_at_10 - value: 30.154999999999998 + value: 10.367999999999999 - type: precision_at_100 - value: 9.87 + value: 1.192 - type: precision_at_1000 - value: 2.343 + value: 0.121 - type: precision_at_3 - value: 42.931000000000004 + value: 26.651000000000003 - type: precision_at_5 - value: 37.771 + value: 18.459 - type: recall_at_1 - value: 6.728000000000001 + value: 42.653999999999996 - type: recall_at_10 - value: 19.372 + value: 86.619 - type: recall_at_100 - value: 39.044000000000004 + value: 98.04899999999999 - type: recall_at_1000 - value: 71.602 + value: 99.812 - type: recall_at_3 - value: 12.328 + value: 68.987 - type: recall_at_5 - value: 14.758 + value: 78.158 - task: type: Retrieval dataset: @@ -1372,65 +1786,65 @@ model-index: revision: None metrics: - type: map_at_1 - value: 72.421 + value: 72.538 - type: map_at_10 - value: 86.648 + value: 86.702 - type: map_at_100 - value: 87.258 + value: 87.31 - type: map_at_1000 - value: 87.26899999999999 + value: 87.323 - type: map_at_3 - value: 83.82 + value: 83.87 - type: map_at_5 - value: 85.629 + value: 85.682 - type: mrr_at_1 - value: 83.21 + value: 83.31 - type: mrr_at_10 - value: 89.198 + value: 89.225 - type: mrr_at_100 - value: 89.277 + value: 89.30399999999999 - type: mrr_at_1000 - value: 89.277 + value: 89.30399999999999 - type: mrr_at_3 - value: 88.428 + value: 88.44300000000001 - type: mrr_at_5 - value: 88.98 + value: 89.005 - type: ndcg_at_1 - value: 83.24000000000001 + value: 83.32000000000001 - type: ndcg_at_10 - value: 90.067 + value: 90.095 - type: ndcg_at_100 - value: 91.091 + value: 91.12 - type: ndcg_at_1000 - value: 91.146 + value: 91.179 - type: ndcg_at_3 - value: 87.6 + value: 87.606 - type: ndcg_at_5 - value: 89.004 + value: 89.031 - type: precision_at_1 - value: 83.24000000000001 + value: 83.32000000000001 - type: precision_at_10 - value: 13.644 + value: 13.641 - type: precision_at_100 - value: 1.542 + value: 1.541 - type: precision_at_1000 value: 0.157 - type: precision_at_3 - value: 38.437 + value: 38.377 - type: precision_at_5 - value: 25.194 + value: 25.162000000000003 - type: recall_at_1 - value: 72.421 + value: 72.538 - type: recall_at_10 - value: 96.49600000000001 + value: 96.47200000000001 - type: recall_at_100 - value: 99.802 + value: 99.785 - type: recall_at_1000 - value: 100.0 + value: 99.99900000000001 - type: recall_at_3 - value: 89.31400000000001 + value: 89.278 - type: recall_at_5 - value: 93.363 + value: 93.367 - task: type: Clustering dataset: @@ -1441,7 +1855,7 @@ model-index: revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure - value: 73.97491289906442 + value: 73.55219145406065 - task: type: Clustering dataset: @@ -1452,7 +1866,7 @@ model-index: revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure - value: 73.49590001712183 + value: 74.13437105242755 - task: type: Retrieval dataset: @@ -1463,65 +1877,65 @@ model-index: revision: None metrics: - type: map_at_1 - value: 6.978 + value: 6.873 - type: map_at_10 - value: 18.307000000000002 + value: 17.944 - type: map_at_100 - value: 21.605 + value: 21.171 - type: map_at_1000 - value: 21.965 + value: 21.528 - type: map_at_3 - value: 12.642000000000001 + value: 12.415 - type: map_at_5 - value: 15.453 + value: 15.187999999999999 - type: mrr_at_1 - value: 34.300000000000004 + value: 33.800000000000004 - type: mrr_at_10 - value: 46.886 + value: 46.455 - type: mrr_at_100 - value: 47.78 + value: 47.378 - type: mrr_at_1000 - value: 47.795 + value: 47.394999999999996 - type: mrr_at_3 - value: 42.467 + value: 42.367 - type: mrr_at_5 - value: 45.427 + value: 44.972 - type: ndcg_at_1 - value: 34.300000000000004 + value: 33.800000000000004 - type: ndcg_at_10 - value: 29.372999999999998 + value: 28.907 - type: ndcg_at_100 - value: 40.355000000000004 + value: 39.695 - type: ndcg_at_1000 - value: 45.221000000000004 + value: 44.582 - type: ndcg_at_3 - value: 27.230999999999998 + value: 26.949 - type: ndcg_at_5 - value: 24.352 + value: 23.988 - type: precision_at_1 - value: 34.300000000000004 + value: 33.800000000000004 - type: precision_at_10 - value: 15.36 + value: 15.079999999999998 - type: precision_at_100 - value: 3.116 + value: 3.056 - type: precision_at_1000 - value: 0.426 + value: 0.42100000000000004 - type: precision_at_3 - value: 25.367 + value: 25.167 - type: precision_at_5 - value: 21.62 + value: 21.26 - type: recall_at_1 - value: 6.978 + value: 6.873 - type: recall_at_10 - value: 31.142999999999997 + value: 30.568 - type: recall_at_100 - value: 63.27199999999999 + value: 62.062 - type: recall_at_1000 - value: 86.512 + value: 85.37700000000001 - type: recall_at_3 - value: 15.433 + value: 15.312999999999999 - type: recall_at_5 - value: 21.918000000000003 + value: 21.575 - task: type: STS dataset: @@ -1532,17 +1946,17 @@ model-index: revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson - value: 81.90996932803432 + value: 82.37009118256057 - type: cos_sim_spearman - value: 78.73848819688604 + value: 79.27986395671529 - type: euclidean_pearson - value: 78.82008134820491 + value: 79.18037715442115 - type: euclidean_spearman - value: 78.73797968799013 + value: 79.28004791561621 - type: manhattan_pearson - value: 78.98817729907871 + value: 79.34062972800541 - type: manhattan_spearman - value: 78.88989195290672 + value: 79.43106695543402 - task: type: STS dataset: @@ -1553,17 +1967,17 @@ model-index: revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson - value: 86.9169693104017 + value: 87.48474767383833 - type: cos_sim_spearman - value: 78.6067489618467 + value: 79.54505388752513 - type: euclidean_pearson - value: 83.04545335395649 + value: 83.43282704179565 - type: euclidean_spearman - value: 78.6070135484733 + value: 79.54579919925405 - type: manhattan_pearson - value: 83.49435095447187 + value: 83.77564492427952 - type: manhattan_spearman - value: 78.9690144080464 + value: 79.84558396989286 - task: type: STS dataset: @@ -1574,17 +1988,17 @@ model-index: revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson - value: 88.86389266236574 + value: 88.803698035802 - type: cos_sim_spearman - value: 88.88070867328447 + value: 88.83451367754881 - type: euclidean_pearson - value: 88.52907860408021 + value: 88.28939285711628 - type: euclidean_spearman - value: 88.88041097815055 + value: 88.83528996073112 - type: manhattan_pearson - value: 88.65795865729802 + value: 88.28017412671795 - type: manhattan_spearman - value: 89.09614539167227 + value: 88.9228828016344 - task: type: STS dataset: @@ -1595,17 +2009,17 @@ model-index: revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson - value: 85.90258145848692 + value: 85.27469288153428 - type: cos_sim_spearman - value: 84.16679932371741 + value: 83.87477064876288 - type: euclidean_pearson - value: 84.95294032883719 + value: 84.2601737035379 - type: euclidean_spearman - value: 84.16781112349103 + value: 83.87431082479074 - type: manhattan_pearson - value: 85.18004344325733 + value: 84.3621547772745 - type: manhattan_spearman - value: 84.52374692147366 + value: 84.12094375000423 - task: type: STS dataset: @@ -1616,17 +2030,17 @@ model-index: revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson - value: 87.89191454971963 + value: 88.12749863201587 - type: cos_sim_spearman - value: 88.44916193520294 + value: 88.54287568368565 - type: euclidean_pearson - value: 87.85883738567667 + value: 87.90429700607999 - type: euclidean_spearman - value: 88.44928880968476 + value: 88.5437689576261 - type: manhattan_pearson - value: 88.1871454451139 + value: 88.19276653356833 - type: manhattan_spearman - value: 88.94431200065807 + value: 88.99995393814679 - task: type: STS dataset: @@ -1637,17 +2051,17 @@ model-index: revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson - value: 85.36716703986853 + value: 85.68398747560902 - type: cos_sim_spearman - value: 86.16132844716138 + value: 86.48815303460574 - type: euclidean_pearson - value: 85.25811478217042 + value: 85.52356631237954 - type: euclidean_spearman - value: 86.16215262183867 + value: 86.486391949551 - type: manhattan_pearson - value: 85.43281209842574 + value: 85.67267981761788 - type: manhattan_spearman - value: 86.44640605346511 + value: 86.7073696332485 - task: type: STS dataset: @@ -1658,17 +2072,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 88.29794966742152 + value: 88.9057107443124 - type: cos_sim_spearman - value: 88.27359278171622 + value: 88.7312168757697 - type: euclidean_pearson - value: 88.06469525438956 + value: 88.72810439714794 - type: euclidean_spearman - value: 88.28670070410784 + value: 88.71976185854771 - type: manhattan_pearson - value: 87.89087342332212 + value: 88.50433745949111 - type: manhattan_spearman - value: 88.11041644578535 + value: 88.51726175544195 - task: type: STS dataset: @@ -1679,17 +2093,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 66.75199645389645 + value: 67.59391795109886 - type: cos_sim_spearman - value: 66.20137384486978 + value: 66.87613008631367 - type: euclidean_pearson - value: 68.622513186352 + value: 69.23198488262217 - type: euclidean_spearman - value: 66.23640152769464 + value: 66.85427723013692 - type: manhattan_pearson - value: 68.97988448341921 + value: 69.50730124841084 - type: manhattan_spearman - value: 66.39142269154794 + value: 67.10404669820792 - task: type: STS dataset: @@ -1700,17 +2114,17 @@ model-index: revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson - value: 86.48693548775047 + value: 87.0820605344619 - type: cos_sim_spearman - value: 86.08823308674964 + value: 86.8518089863434 - type: euclidean_pearson - value: 85.65692420470154 + value: 86.31087134689284 - type: euclidean_spearman - value: 86.08859480677167 + value: 86.8518520517941 - type: manhattan_pearson - value: 85.90164709250936 + value: 86.47203796160612 - type: manhattan_spearman - value: 86.40785365360473 + value: 87.1080149734421 - task: type: Reranking dataset: @@ -1721,9 +2135,9 @@ model-index: revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map - value: 88.80093449044475 + value: 89.09255369305481 - type: mrr - value: 97.02094655526028 + value: 97.10323445617563 - task: type: Retrieval dataset: @@ -1734,65 +2148,65 @@ model-index: revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: map_at_1 - value: 59.594 + value: 61.260999999999996 - type: map_at_10 - value: 72.649 + value: 74.043 - type: map_at_100 - value: 73.051 + value: 74.37700000000001 - type: map_at_1000 - value: 73.056 + value: 74.384 - type: map_at_3 - value: 69.667 + value: 71.222 - type: map_at_5 - value: 71.528 + value: 72.875 - type: mrr_at_1 - value: 62.666999999999994 + value: 64.333 - type: mrr_at_10 - value: 73.625 + value: 74.984 - type: mrr_at_100 - value: 73.956 + value: 75.247 - type: mrr_at_1000 - value: 73.962 + value: 75.25500000000001 - type: mrr_at_3 - value: 71.77799999999999 + value: 73.167 - type: mrr_at_5 - value: 72.994 + value: 74.35000000000001 - type: ndcg_at_1 - value: 62.666999999999994 + value: 64.333 - type: ndcg_at_10 - value: 77.981 + value: 79.06 - type: ndcg_at_100 - value: 79.474 + value: 80.416 - type: ndcg_at_1000 - value: 79.569 + value: 80.55600000000001 - type: ndcg_at_3 - value: 73.4 + value: 74.753 - type: ndcg_at_5 - value: 75.806 + value: 76.97500000000001 - type: precision_at_1 - value: 62.666999999999994 + value: 64.333 - type: precision_at_10 value: 10.567 - type: precision_at_100 - value: 1.123 + value: 1.1199999999999999 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 - value: 29.555999999999997 + value: 29.889 - type: precision_at_5 - value: 19.467000000000002 + value: 19.533 - type: recall_at_1 - value: 59.594 + value: 61.260999999999996 - type: recall_at_10 value: 93.167 - type: recall_at_100 - value: 99.333 + value: 99.0 - type: recall_at_1000 value: 100.0 - type: recall_at_3 - value: 80.72200000000001 + value: 81.667 - type: recall_at_5 - value: 86.79400000000001 + value: 87.394 - task: type: PairClassification dataset: @@ -1803,51 +2217,51 @@ model-index: revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy - value: 99.67920792079208 + value: 99.71980198019801 - type: cos_sim_ap - value: 91.12451155203843 + value: 92.81616007802704 - type: cos_sim_f1 - value: 82.7763496143959 + value: 85.17548454688318 - type: cos_sim_precision - value: 85.18518518518519 + value: 89.43894389438944 - type: cos_sim_recall - value: 80.5 + value: 81.3 - type: dot_accuracy - value: 99.68019801980198 + value: 99.71980198019801 - type: dot_ap - value: 91.12360077338997 + value: 92.81398760591358 - type: dot_f1 - value: 82.81893004115227 + value: 85.17548454688318 - type: dot_precision - value: 85.27542372881356 + value: 89.43894389438944 - type: dot_recall - value: 80.5 + value: 81.3 - type: euclidean_accuracy - value: 99.67920792079208 + value: 99.71980198019801 - type: euclidean_ap - value: 91.12526537243333 + value: 92.81560637245072 - type: euclidean_f1 - value: 82.7763496143959 + value: 85.17548454688318 - type: euclidean_precision - value: 85.18518518518519 + value: 89.43894389438944 - type: euclidean_recall - value: 80.5 + value: 81.3 - type: manhattan_accuracy - value: 99.68613861386139 + value: 99.73069306930694 - type: manhattan_ap - value: 91.52045550487428 + value: 93.14005487480794 - type: manhattan_f1 - value: 83.38461538461539 + value: 85.56263269639068 - type: manhattan_precision - value: 85.57894736842105 + value: 91.17647058823529 - type: manhattan_recall - value: 81.3 + value: 80.60000000000001 - type: max_accuracy - value: 99.68613861386139 + value: 99.73069306930694 - type: max_ap - value: 91.52045550487428 + value: 93.14005487480794 - type: max_f1 - value: 83.38461538461539 + value: 85.56263269639068 - task: type: Clustering dataset: @@ -1858,7 +2272,7 @@ model-index: revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure - value: 79.90649023801956 + value: 79.86443362395185 - task: type: Clustering dataset: @@ -1869,7 +2283,7 @@ model-index: revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure - value: 49.681864218959205 + value: 49.40897096662564 - task: type: Reranking dataset: @@ -1880,9 +2294,9 @@ model-index: revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map - value: 55.89272881949486 + value: 55.66040806627947 - type: mrr - value: 56.88128660555132 + value: 56.58670475766064 - task: type: Summarization dataset: @@ -1893,13 +2307,13 @@ model-index: revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson - value: 31.945233723225954 + value: 31.51015090598575 - type: cos_sim_spearman - value: 31.361651389713284 + value: 31.35016454939226 - type: dot_pearson - value: 31.96193321438737 + value: 31.5150068731 - type: dot_spearman - value: 31.37045148053791 + value: 31.34790869023487 - task: type: Retrieval dataset: @@ -1910,1263 +2324,283 @@ model-index: revision: None metrics: - type: map_at_1 - value: 0.244 + value: 0.254 - type: map_at_10 - value: 2.011 + value: 2.064 - type: map_at_100 - value: 12.555 + value: 12.909 - type: map_at_1000 - value: 30.386000000000003 + value: 31.761 - type: map_at_3 - value: 0.718 + value: 0.738 - type: map_at_5 - value: 1.118 + value: 1.155 - type: mrr_at_1 - value: 94.0 + value: 96.0 - type: mrr_at_10 - value: 97.0 + value: 98.0 - type: mrr_at_100 - value: 97.0 + value: 98.0 - type: mrr_at_1000 - value: 97.0 + value: 98.0 - type: mrr_at_3 - value: 97.0 + value: 98.0 - type: mrr_at_5 - value: 97.0 + value: 98.0 - type: ndcg_at_1 value: 93.0 - type: ndcg_at_10 - value: 81.612 + value: 82.258 - type: ndcg_at_100 - value: 63.468 + value: 64.34 - type: ndcg_at_1000 - value: 56.508 + value: 57.912 - type: ndcg_at_3 - value: 88.81599999999999 + value: 90.827 - type: ndcg_at_5 - value: 85.599 + value: 86.79 - type: precision_at_1 - value: 94.0 + value: 96.0 - type: precision_at_10 - value: 84.0 + value: 84.8 - type: precision_at_100 - value: 65.18 + value: 66.0 - type: precision_at_1000 - value: 24.758 + value: 25.356 - type: precision_at_3 - value: 93.333 + value: 94.667 - type: precision_at_5 - value: 89.2 + value: 90.4 - type: recall_at_1 - value: 0.244 + value: 0.254 - type: recall_at_10 - value: 2.161 + value: 2.1950000000000003 - type: recall_at_100 - value: 15.862000000000002 + value: 16.088 - type: recall_at_1000 - value: 53.146 + value: 54.559000000000005 - type: recall_at_3 - value: 0.738 + value: 0.75 - type: recall_at_5 - value: 1.167 - - task: - type: Classification - dataset: - type: mteb/toxic_conversations_50k - name: MTEB ToxicConversationsClassification - config: default - split: test - revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c - metrics: - - type: accuracy - value: 82.948 - - type: ap - value: 26.37282466987438 - - type: f1 - value: 66.9868680256644 + value: 1.191 - task: - type: Classification + type: Retrieval dataset: - type: mteb/tweet_sentiment_extraction - name: MTEB TweetSentimentExtractionClassification + type: mteb/touche2020 + name: MTEB Touche2020 config: default split: test - revision: d604517c81ca91fe16a244d1248fc021f9ecee7a - metrics: - - type: accuracy - value: 73.78607809847199 - - type: f1 - value: 74.1324659804999 - - task: - type: Clustering - dataset: - type: mteb/twentynewsgroups-clustering - name: MTEB TwentyNewsgroupsClustering - config: default - split: test - revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 - metrics: - - type: v_measure - value: 54.11838832136805 - - task: - type: PairClassification - dataset: - type: mteb/twittersemeval2015-pairclassification - name: MTEB TwitterSemEval2015 - config: default - split: test - revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 - metrics: - - type: cos_sim_accuracy - value: 87.64975859808071 - - type: cos_sim_ap - value: 79.0918389936708 - - type: cos_sim_f1 - value: 72.18518052585232 - - type: cos_sim_precision - value: 68.98292858860303 - - type: cos_sim_recall - value: 75.69920844327177 - - type: dot_accuracy - value: 87.64379805686356 - - type: dot_ap - value: 79.09373814934631 - - type: dot_f1 - value: 72.18216318785579 - - type: dot_precision - value: 69.33171324422844 - - type: dot_recall - value: 75.27704485488127 - - type: euclidean_accuracy - value: 87.64975859808071 - - type: euclidean_ap - value: 79.09199976607417 - - type: euclidean_f1 - value: 72.17610062893083 - - type: euclidean_precision - value: 68.96634615384616 - - type: euclidean_recall - value: 75.69920844327177 - - type: manhattan_accuracy - value: 87.61399535077786 - - type: manhattan_ap - value: 78.91167634954901 - - type: manhattan_f1 - value: 72.0995176440721 - - type: manhattan_precision - value: 69.47162426614481 - - type: manhattan_recall - value: 74.93403693931398 - - type: max_accuracy - value: 87.64975859808071 - - type: max_ap - value: 79.09373814934631 - - type: max_f1 - value: 72.18518052585232 - - task: - type: PairClassification - dataset: - type: mteb/twitterurlcorpus-pairclassification - name: MTEB TwitterURLCorpus - config: default - split: test - revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf - metrics: - - type: cos_sim_accuracy - value: 89.43415997205729 - - type: cos_sim_ap - value: 86.69200523144308 - - type: cos_sim_f1 - value: 79.16424418604652 - - type: cos_sim_precision - value: 74.95871180842279 - - type: cos_sim_recall - value: 83.86972590083154 - - type: dot_accuracy - value: 89.43415997205729 - - type: dot_ap - value: 86.69346224233253 - - type: dot_f1 - value: 79.15884340968833 - - type: dot_precision - value: 77.26139862190294 - - type: dot_recall - value: 81.15183246073299 - - type: euclidean_accuracy - value: 89.43221950556915 - - type: euclidean_ap - value: 86.69176407206174 - - type: euclidean_f1 - value: 79.16409231328366 - - type: euclidean_precision - value: 74.97074413161698 - - type: euclidean_recall - value: 83.85432707114259 - - type: manhattan_accuracy - value: 89.49237396670159 - - type: manhattan_ap - value: 86.72274876446832 - - type: manhattan_f1 - value: 79.18286510672633 - - type: manhattan_precision - value: 75.6058271466592 - - type: manhattan_recall - value: 83.1151832460733 - - type: max_accuracy - value: 89.49237396670159 - - type: max_ap - value: 86.72274876446832 - - type: max_f1 - value: 79.18286510672633 - - task: - type: STS - dataset: - type: C-MTEB/AFQMC - name: MTEB AFQMC - config: default - split: validation - revision: b44c3b011063adb25877c13823db83bb193913c4 - metrics: - - type: cos_sim_pearson - value: 65.7103214280117 - - type: cos_sim_spearman - value: 72.62249544256886 - - type: euclidean_pearson - value: 71.36812167041296 - - type: euclidean_spearman - value: 72.62325941111307 - - type: manhattan_pearson - value: 71.25613851615468 - - type: manhattan_spearman - value: 72.54244015155267 - - task: - type: STS - dataset: - type: C-MTEB/ATEC - name: MTEB ATEC - config: default - split: test - revision: 0f319b1142f28d00e055a6770f3f726ae9b7d865 - metrics: - - type: cos_sim_pearson - value: 59.903467713912974 - - type: cos_sim_spearman - value: 62.8205444560593 - - type: euclidean_pearson - value: 67.06329904158285 - - type: euclidean_spearman - value: 62.82051743557576 - - type: manhattan_pearson - value: 66.97943759454319 - - type: manhattan_spearman - value: 62.763028353169325 - - task: - type: Classification - dataset: - type: mteb/amazon_reviews_multi - name: MTEB AmazonReviewsClassification (zh) - config: zh - split: test - revision: 1399c76144fd37290681b995c656ef9b2e06e26d - metrics: - - type: accuracy - value: 53.57399999999999 - - type: f1 - value: 50.57496370390049 - - task: - type: STS - dataset: - type: C-MTEB/BQ - name: MTEB BQ - config: default - split: test - revision: e3dda5e115e487b39ec7e618c0c6a29137052a55 - metrics: - - type: cos_sim_pearson - value: 79.09488668095824 - - type: cos_sim_spearman - value: 81.34731850197655 - - type: euclidean_pearson - value: 82.19030116395511 - - type: euclidean_spearman - value: 81.34699287691117 - - type: manhattan_pearson - value: 82.19510202220734 - - type: manhattan_spearman - value: 81.35888167395795 - - task: - type: Clustering - dataset: - type: C-MTEB/CLSClusteringP2P - name: MTEB CLSClusteringP2P - config: default - split: test - revision: 4b6227591c6c1a73bc76b1055f3b7f3588e72476 - metrics: - - type: v_measure - value: 48.60079470735067 - - task: - type: Clustering - dataset: - type: C-MTEB/CLSClusteringS2S - name: MTEB CLSClusteringS2S - config: default - split: test - revision: e458b3f5414b62b7f9f83499ac1f5497ae2e869f - metrics: - - type: v_measure - value: 46.125672623152155 - - task: - type: Reranking - dataset: - type: C-MTEB/CMedQAv1-reranking - name: MTEB CMedQAv1 - config: default - split: test - revision: 8d7f1e942507dac42dc58017c1a001c3717da7df - metrics: - - type: map - value: 88.0714642862605 - - type: mrr - value: 90.17428571428572 - - task: - type: Reranking - dataset: - type: C-MTEB/CMedQAv2-reranking - name: MTEB CMedQAv2 - config: default - split: test - revision: 23d186750531a14a0357ca22cd92d712fd512ea0 - metrics: - - type: map - value: 88.51263170426526 - - type: mrr - value: 90.53325396825396 - - task: - type: Retrieval - dataset: - type: C-MTEB/CmedqaRetrieval - name: MTEB CmedqaRetrieval - config: default - split: dev - revision: cd540c506dae1cf9e9a59c3e06f42030d54e7301 - metrics: - - type: map_at_1 - value: 29.610999999999997 - - type: map_at_10 - value: 42.832 - - type: map_at_100 - value: 44.639 - - type: map_at_1000 - value: 44.738 - - type: map_at_3 - value: 38.549 - - type: map_at_5 - value: 40.905 - - type: mrr_at_1 - value: 44.461 - - type: mrr_at_10 - value: 52.274 - - type: mrr_at_100 - value: 53.179 - - type: mrr_at_1000 - value: 53.213 - - type: mrr_at_3 - value: 49.917 - - type: mrr_at_5 - value: 51.13799999999999 - - type: ndcg_at_1 - value: 44.461 - - type: ndcg_at_10 - value: 49.557 - - type: ndcg_at_100 - value: 56.432 - - type: ndcg_at_1000 - value: 58.050000000000004 - - type: ndcg_at_3 - value: 44.419 - - type: ndcg_at_5 - value: 46.386 - - type: precision_at_1 - value: 44.461 - - type: precision_at_10 - value: 10.673 - - type: precision_at_100 - value: 1.6310000000000002 - - type: precision_at_1000 - value: 0.184 - - type: precision_at_3 - value: 24.656 - - type: precision_at_5 - value: 17.619 - - type: recall_at_1 - value: 29.610999999999997 - - type: recall_at_10 - value: 60.112 - - type: recall_at_100 - value: 88.346 - - type: recall_at_1000 - value: 98.993 - - type: recall_at_3 - value: 44.243 - - type: recall_at_5 - value: 50.64300000000001 - - task: - type: PairClassification - dataset: - type: C-MTEB/CMNLI - name: MTEB Cmnli - config: default - split: validation - revision: 41bc36f332156f7adc9e38f53777c959b2ae9766 - metrics: - - type: cos_sim_accuracy - value: 82.17678893565845 - - type: cos_sim_ap - value: 89.77899888165327 - - type: cos_sim_f1 - value: 83.03306727480046 - - type: cos_sim_precision - value: 81.0371689294458 - - type: cos_sim_recall - value: 85.1297638531681 - - type: dot_accuracy - value: 82.1647624774504 - - type: dot_ap - value: 89.78074283382892 - - type: dot_f1 - value: 83.03306727480046 - - type: dot_precision - value: 81.0371689294458 - - type: dot_recall - value: 85.1297638531681 - - type: euclidean_accuracy - value: 82.1888153938665 - - type: euclidean_ap - value: 89.77917362529757 - - type: euclidean_f1 - value: 83.03306727480046 - - type: euclidean_precision - value: 81.0371689294458 - - type: euclidean_recall - value: 85.1297638531681 - - type: manhattan_accuracy - value: 81.82802164762477 - - type: manhattan_ap - value: 89.56708721584408 - - type: manhattan_f1 - value: 82.72179938657275 - - type: manhattan_precision - value: 80.44631020768891 - - type: manhattan_recall - value: 85.1297638531681 - - type: max_accuracy - value: 82.1888153938665 - - type: max_ap - value: 89.78074283382892 - - type: max_f1 - value: 83.03306727480046 - - task: - type: Retrieval - dataset: - type: C-MTEB/CovidRetrieval - name: MTEB CovidRetrieval - config: default - split: dev - revision: 1271c7809071a13532e05f25fb53511ffce77117 - metrics: - - type: map_at_1 - value: 66.807 - - type: map_at_10 - value: 75.47399999999999 - - type: map_at_100 - value: 75.837 - - type: map_at_1000 - value: 75.84 - - type: map_at_3 - value: 73.67399999999999 - - type: map_at_5 - value: 74.558 - - type: mrr_at_1 - value: 66.913 - - type: mrr_at_10 - value: 75.467 - - type: mrr_at_100 - value: 75.823 - - type: mrr_at_1000 - value: 75.82600000000001 - - type: mrr_at_3 - value: 73.67399999999999 - - type: mrr_at_5 - value: 74.586 - - type: ndcg_at_1 - value: 66.913 - - type: ndcg_at_10 - value: 79.591 - - type: ndcg_at_100 - value: 81.15 - - type: ndcg_at_1000 - value: 81.229 - - type: ndcg_at_3 - value: 75.83800000000001 - - type: ndcg_at_5 - value: 77.45 - - type: precision_at_1 - value: 66.913 - - type: precision_at_10 - value: 9.325999999999999 - - type: precision_at_100 - value: 1.0030000000000001 - - type: precision_at_1000 - value: 0.101 - - type: precision_at_3 - value: 27.432000000000002 - - type: precision_at_5 - value: 17.281 - - type: recall_at_1 - value: 66.807 - - type: recall_at_10 - value: 92.46600000000001 - - type: recall_at_100 - value: 99.262 - - type: recall_at_1000 - value: 99.895 - - type: recall_at_3 - value: 82.086 - - type: recall_at_5 - value: 85.985 - - task: - type: Retrieval - dataset: - type: C-MTEB/DuRetrieval - name: MTEB DuRetrieval - config: default - split: dev - revision: a1a333e290fe30b10f3f56498e3a0d911a693ced - metrics: - - type: map_at_1 - value: 26.599 - - type: map_at_10 - value: 81.577 - - type: map_at_100 - value: 84.368 - - type: map_at_1000 - value: 84.39999999999999 - - type: map_at_3 - value: 56.825 - - type: map_at_5 - value: 71.462 - - type: mrr_at_1 - value: 90.5 - - type: mrr_at_10 - value: 93.798 - - type: mrr_at_100 - value: 93.851 - - type: mrr_at_1000 - value: 93.853 - - type: mrr_at_3 - value: 93.5 - - type: mrr_at_5 - value: 93.672 - - type: ndcg_at_1 - value: 90.5 - - type: ndcg_at_10 - value: 88.633 - - type: ndcg_at_100 - value: 91.217 - - type: ndcg_at_1000 - value: 91.484 - - type: ndcg_at_3 - value: 87.29599999999999 - - type: ndcg_at_5 - value: 86.31299999999999 - - type: precision_at_1 - value: 90.5 - - type: precision_at_10 - value: 42.18 - - type: precision_at_100 - value: 4.839 - - type: precision_at_1000 - value: 0.49 - - type: precision_at_3 - value: 78.133 - - type: precision_at_5 - value: 65.82000000000001 - - type: recall_at_1 - value: 26.599 - - type: recall_at_10 - value: 90.137 - - type: recall_at_100 - value: 98.393 - - type: recall_at_1000 - value: 99.747 - - type: recall_at_3 - value: 59.199999999999996 - - type: recall_at_5 - value: 76.173 - - task: - type: Retrieval - dataset: - type: C-MTEB/EcomRetrieval - name: MTEB EcomRetrieval - config: default - split: dev - revision: 687de13dc7294d6fd9be10c6945f9e8fec8166b9 - metrics: - - type: map_at_1 - value: 55.2 - - type: map_at_10 - value: 64.925 - - type: map_at_100 - value: 65.446 - - type: map_at_1000 - value: 65.459 - - type: map_at_3 - value: 62.266999999999996 - - type: map_at_5 - value: 64.107 - - type: mrr_at_1 - value: 55.2 - - type: mrr_at_10 - value: 64.925 - - type: mrr_at_100 - value: 65.446 - - type: mrr_at_1000 - value: 65.459 - - type: mrr_at_3 - value: 62.266999999999996 - - type: mrr_at_5 - value: 64.107 - - type: ndcg_at_1 - value: 55.2 - - type: ndcg_at_10 - value: 69.85900000000001 - - type: ndcg_at_100 - value: 72.194 - - type: ndcg_at_1000 - value: 72.506 - - type: ndcg_at_3 - value: 64.538 - - type: ndcg_at_5 - value: 67.843 - - type: precision_at_1 - value: 55.2 - - type: precision_at_10 - value: 8.540000000000001 - - type: precision_at_100 - value: 0.959 - - type: precision_at_1000 - value: 0.098 - - type: precision_at_3 - value: 23.7 - - type: precision_at_5 - value: 15.82 - - type: recall_at_1 - value: 55.2 - - type: recall_at_10 - value: 85.39999999999999 - - type: recall_at_100 - value: 95.89999999999999 - - type: recall_at_1000 - value: 98.3 - - type: recall_at_3 - value: 71.1 - - type: recall_at_5 - value: 79.10000000000001 - - task: - type: Classification - dataset: - type: C-MTEB/IFlyTek-classification - name: MTEB IFlyTek - config: default - split: validation - revision: 421605374b29664c5fc098418fe20ada9bd55f8a - metrics: - - type: accuracy - value: 53.92843401308196 - - type: f1 - value: 40.44614048360205 - - task: - type: Classification - dataset: - type: C-MTEB/JDReview-classification - name: MTEB JDReview - config: default - split: test - revision: b7c64bd89eb87f8ded463478346f76731f07bf8b - metrics: - - type: accuracy - value: 86.22889305816133 - - type: ap - value: 55.542660925360835 - - type: f1 - value: 81.26964576055315 - - task: - type: STS - dataset: - type: C-MTEB/LCQMC - name: MTEB LCQMC - config: default - split: test - revision: 17f9b096f80380fce5ed12a9be8be7784b337daf - metrics: - - type: cos_sim_pearson - value: 68.50234587951512 - - type: cos_sim_spearman - value: 73.04229322574785 - - type: euclidean_pearson - value: 71.76475440799503 - - type: euclidean_spearman - value: 73.04203161533454 - - type: manhattan_pearson - value: 71.75530397681868 - - type: manhattan_spearman - value: 73.01054099221574 - - task: - type: Reranking - dataset: - type: C-MTEB/Mmarco-reranking - name: MTEB MMarcoReranking - config: default - split: dev - revision: None - metrics: - - type: map - value: 22.67056873798454 - - type: mrr - value: 21.63888888888889 - - task: - type: Retrieval - dataset: - type: C-MTEB/MMarcoRetrieval - name: MTEB MMarcoRetrieval - config: default - split: dev - revision: 539bbde593d947e2a124ba72651aafc09eb33fc2 + revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: map_at_1 - value: 67.65 + value: 2.976 - type: map_at_10 - value: 76.726 + value: 11.389000000000001 - type: map_at_100 - value: 77.03 + value: 18.429000000000002 - type: map_at_1000 - value: 77.042 + value: 20.113 - type: map_at_3 - value: 74.924 + value: 6.483 - type: map_at_5 - value: 76.08200000000001 + value: 8.770999999999999 - type: mrr_at_1 - value: 69.87100000000001 + value: 40.816 - type: mrr_at_10 - value: 77.238 + value: 58.118 - type: mrr_at_100 - value: 77.492 + value: 58.489999999999995 - type: mrr_at_1000 - value: 77.503 + value: 58.489999999999995 - type: mrr_at_3 - value: 75.633 + value: 53.061 - type: mrr_at_5 - value: 76.678 + value: 57.041 - type: ndcg_at_1 - value: 69.87100000000001 + value: 40.816 - type: ndcg_at_10 - value: 80.37100000000001 + value: 30.567 - type: ndcg_at_100 - value: 81.658 + value: 42.44 - type: ndcg_at_1000 - value: 81.94200000000001 + value: 53.480000000000004 - type: ndcg_at_3 - value: 76.94 + value: 36.016 - type: ndcg_at_5 - value: 78.926 + value: 34.257 - type: precision_at_1 - value: 69.87100000000001 + value: 42.857 - type: precision_at_10 - value: 9.681 + value: 25.714 - type: precision_at_100 - value: 1.032 + value: 8.429 - type: precision_at_1000 - value: 0.105 + value: 1.5939999999999999 - type: precision_at_3 - value: 28.906 + value: 36.735 - type: precision_at_5 - value: 18.404 + value: 33.878 - type: recall_at_1 - value: 67.65 + value: 2.976 - type: recall_at_10 - value: 91.078 + value: 17.854999999999997 - type: recall_at_100 - value: 96.767 + value: 51.833 - type: recall_at_1000 - value: 98.933 + value: 86.223 - type: recall_at_3 - value: 82.02000000000001 + value: 7.887 - type: recall_at_5 - value: 86.771 + value: 12.026 - task: type: Classification dataset: - type: mteb/amazon_massive_intent - name: MTEB MassiveIntentClassification (zh-CN) - config: zh-CN + type: mteb/toxic_conversations_50k + name: MTEB ToxicConversationsClassification + config: default split: test - revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 + revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy - value: 79.7848016139879 + value: 85.1174 + - type: ap + value: 30.169441069345748 - type: f1 - value: 76.99189501152489 + value: 69.79254701873245 - task: type: Classification dataset: - type: mteb/amazon_massive_scenario - name: MTEB MassiveScenarioClassification (zh-CN) - config: zh-CN + type: mteb/tweet_sentiment_extraction + name: MTEB TweetSentimentExtractionClassification + config: default split: test - revision: 7d571f92784cd94a019292a1f45445077d0ef634 + revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy - value: 83.64492266308001 + value: 72.58347481607245 - type: f1 - value: 82.84955852311293 - - task: - type: Retrieval - dataset: - type: C-MTEB/MedicalRetrieval - name: MTEB MedicalRetrieval - config: default - split: dev - revision: 2039188fb5800a9803ba5048df7b76e6fb151fc6 - metrics: - - type: map_at_1 - value: 54.400000000000006 - - type: map_at_10 - value: 60.529999999999994 - - type: map_at_100 - value: 61.114999999999995 - - type: map_at_1000 - value: 61.153999999999996 - - type: map_at_3 - value: 59.150000000000006 - - type: map_at_5 - value: 59.955000000000005 - - type: mrr_at_1 - value: 54.50000000000001 - - type: mrr_at_10 - value: 60.58 - - type: mrr_at_100 - value: 61.165000000000006 - - type: mrr_at_1000 - value: 61.204 - - type: mrr_at_3 - value: 59.199999999999996 - - type: mrr_at_5 - value: 60.004999999999995 - - type: ndcg_at_1 - value: 54.400000000000006 - - type: ndcg_at_10 - value: 63.522999999999996 - - type: ndcg_at_100 - value: 66.742 - - type: ndcg_at_1000 - value: 67.818 - - type: ndcg_at_3 - value: 60.702999999999996 - - type: ndcg_at_5 - value: 62.149 - - type: precision_at_1 - value: 54.400000000000006 - - type: precision_at_10 - value: 7.290000000000001 - - type: precision_at_100 - value: 0.8880000000000001 - - type: precision_at_1000 - value: 0.097 - - type: precision_at_3 - value: 21.733 - - type: precision_at_5 - value: 13.74 - - type: recall_at_1 - value: 54.400000000000006 - - type: recall_at_10 - value: 72.89999999999999 - - type: recall_at_100 - value: 88.8 - - type: recall_at_1000 - value: 97.39999999999999 - - type: recall_at_3 - value: 65.2 - - type: recall_at_5 - value: 68.7 + value: 72.74877295564937 - task: - type: Classification + type: Clustering dataset: - type: C-MTEB/MultilingualSentiment-classification - name: MTEB MultilingualSentiment + type: mteb/twentynewsgroups-clustering + name: MTEB TwentyNewsgroupsClustering config: default - split: validation - revision: 46958b007a63fdbf239b7672c25d0bea67b5ea1a + split: test + revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - - type: accuracy - value: 77.16000000000001 - - type: f1 - value: 76.97953105264186 + - type: v_measure + value: 53.90586138221305 - task: type: PairClassification dataset: - type: C-MTEB/OCNLI - name: MTEB Ocnli + type: mteb/twittersemeval2015-pairclassification + name: MTEB TwitterSemEval2015 config: default - split: validation - revision: 66e76a618a34d6d565d5538088562851e6daa7ec + split: test + revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy - value: 79.48023822414727 + value: 87.35769207844072 - type: cos_sim_ap - value: 84.483894203704 + value: 77.9645072410354 - type: cos_sim_f1 - value: 80.55130168453292 + value: 71.32352941176471 - type: cos_sim_precision - value: 77.96442687747036 + value: 66.5903890160183 - type: cos_sim_recall - value: 83.31573389651531 + value: 76.78100263852242 - type: dot_accuracy - value: 79.48023822414727 + value: 87.37557370209214 - type: dot_ap - value: 84.49261973641154 + value: 77.96250046429908 - type: dot_f1 - value: 80.55130168453292 + value: 71.28932757557064 - type: dot_precision - value: 77.96442687747036 + value: 66.95249130938586 - type: dot_recall - value: 83.31573389651531 + value: 76.22691292875989 - type: euclidean_accuracy - value: 79.48023822414727 + value: 87.35173153722357 - type: euclidean_ap - value: 84.48068994534293 + value: 77.96520460741593 - type: euclidean_f1 - value: 80.55130168453292 + value: 71.32470733210104 - type: euclidean_precision - value: 77.96442687747036 + value: 66.91329479768785 - type: euclidean_recall - value: 83.31573389651531 + value: 76.35883905013192 - type: manhattan_accuracy - value: 79.37195452084461 + value: 87.25636287774931 - type: manhattan_ap - value: 84.45931914984077 + value: 77.77752485611796 - type: manhattan_f1 - value: 80.53142565150742 + value: 71.18148599269183 - type: manhattan_precision - value: 78.01980198019803 + value: 66.10859728506787 - type: manhattan_recall - value: 83.21013727560718 + value: 77.0976253298153 - type: max_accuracy - value: 79.48023822414727 + value: 87.37557370209214 - type: max_ap - value: 84.49261973641154 + value: 77.96520460741593 - type: max_f1 - value: 80.55130168453292 - - task: - type: Classification - dataset: - type: C-MTEB/OnlineShopping-classification - name: MTEB OnlineShopping - config: default - split: test - revision: e610f2ebd179a8fda30ae534c3878750a96db120 - metrics: - - type: accuracy - value: 94.3 - - type: ap - value: 92.84324255663363 - - type: f1 - value: 94.29275233313747 - - task: - type: STS - dataset: - type: C-MTEB/PAWSX - name: MTEB PAWSX - config: default - split: test - revision: 9c6a90e430ac22b5779fb019a23e820b11a8b5e1 - metrics: - - type: cos_sim_pearson - value: 50.25954594958544 - - type: cos_sim_spearman - value: 55.1554675848278 - - type: euclidean_pearson - value: 53.71113201288935 - - type: euclidean_spearman - value: 55.1558156481826 - - type: manhattan_pearson - value: 53.816355416293646 - - type: manhattan_spearman - value: 55.14310001157623 - - task: - type: STS - dataset: - type: C-MTEB/QBQTC - name: MTEB QBQTC - config: default - split: test - revision: 790b0510dc52b1553e8c49f3d2afb48c0e5c48b7 - metrics: - - type: cos_sim_pearson - value: 29.187751074660845 - - type: cos_sim_spearman - value: 30.889291180505868 - - type: euclidean_pearson - value: 28.73210543314964 - - type: euclidean_spearman - value: 30.889662787316784 - - type: manhattan_pearson - value: 29.21703764852649 - - type: manhattan_spearman - value: 31.47317743982721 - - task: - type: STS - dataset: - type: mteb/sts22-crosslingual-sts - name: MTEB STS22 (zh) - config: zh - split: test - revision: eea2b4fe26a775864c896887d910b76a8098ad3f - metrics: - - type: cos_sim_pearson - value: 61.1898272680276 - - type: cos_sim_spearman - value: 64.93927648503598 - - type: euclidean_pearson - value: 61.11026474293018 - - type: euclidean_spearman - value: 64.94229072933243 - - type: manhattan_pearson - value: 62.19814132782434 - - type: manhattan_spearman - value: 65.2583560877569 - - task: - type: STS - dataset: - type: C-MTEB/STSB - name: MTEB STSB - config: default - split: test - revision: 0cde68302b3541bb8b3c340dc0644b0b745b3dc0 - metrics: - - type: cos_sim_pearson - value: 78.76122365246462 - - type: cos_sim_spearman - value: 78.68211802616669 - - type: euclidean_pearson - value: 77.17265704615994 - - type: euclidean_spearman - value: 78.68087191872655 - - type: manhattan_pearson - value: 77.61313585452194 - - type: manhattan_spearman - value: 79.22153641729726 - - task: - type: Reranking - dataset: - type: C-MTEB/T2Reranking - name: MTEB T2Reranking - config: default - split: dev - revision: 76631901a18387f85eaa53e5450019b87ad58ef9 - metrics: - - type: map - value: 67.80243119237458 - - type: mrr - value: 78.00406497512118 - - task: - type: Retrieval - dataset: - type: C-MTEB/T2Retrieval - name: MTEB T2Retrieval - config: default - split: dev - revision: 8731a845f1bf500a4f111cf1070785c793d10e64 - metrics: - - type: map_at_1 - value: 28.936 - - type: map_at_10 - value: 82.256 - - type: map_at_100 - value: 85.688 - - type: map_at_1000 - value: 85.727 - - type: map_at_3 - value: 57.655 - - type: map_at_5 - value: 71.05 - - type: mrr_at_1 - value: 92.548 - - type: mrr_at_10 - value: 94.586 - - type: mrr_at_100 - value: 94.64399999999999 - - type: mrr_at_1000 - value: 94.646 - - type: mrr_at_3 - value: 94.255 - - type: mrr_at_5 - value: 94.464 - - type: ndcg_at_1 - value: 92.548 - - type: ndcg_at_10 - value: 88.74600000000001 - - type: ndcg_at_100 - value: 91.58500000000001 - - type: ndcg_at_1000 - value: 91.953 - - type: ndcg_at_3 - value: 89.578 - - type: ndcg_at_5 - value: 88.584 - - type: precision_at_1 - value: 92.548 - - type: precision_at_10 - value: 43.954 - - type: precision_at_100 - value: 5.099 - - type: precision_at_1000 - value: 0.518 - - type: precision_at_3 - value: 78.213 - - type: precision_at_5 - value: 65.839 - - type: recall_at_1 - value: 28.936 - - type: recall_at_10 - value: 87.869 - - type: recall_at_100 - value: 97.286 - - type: recall_at_1000 - value: 99.173 - - type: recall_at_3 - value: 59.157000000000004 - - type: recall_at_5 - value: 74.02499999999999 - - task: - type: Classification - dataset: - type: C-MTEB/TNews-classification - name: MTEB TNews - config: default - split: validation - revision: 317f262bf1e6126357bbe89e875451e4b0938fe4 - metrics: - - type: accuracy - value: 53.269 - - type: f1 - value: 50.68236445411186 - - task: - type: Clustering - dataset: - type: C-MTEB/ThuNewsClusteringP2P - name: MTEB ThuNewsClusteringP2P - config: default - split: test - revision: 5798586b105c0434e4f0fe5e767abe619442cf93 - metrics: - - type: v_measure - value: 86.47994658950259 - - task: - type: Clustering - dataset: - type: C-MTEB/ThuNewsClusteringS2S - name: MTEB ThuNewsClusteringS2S - config: default - split: test - revision: 8a8b2caeda43f39e13c4bc5bea0f8a667896e10d - metrics: - - type: v_measure - value: 85.34791895793325 - - task: - type: Retrieval - dataset: - type: C-MTEB/VideoRetrieval - name: MTEB VideoRetrieval - config: default - split: dev - revision: 58c2597a5943a2ba48f4668c3b90d796283c5639 - metrics: - - type: map_at_1 - value: 65.5 - - type: map_at_10 - value: 74.134 - - type: map_at_100 - value: 74.49799999999999 - - type: map_at_1000 - value: 74.509 - - type: map_at_3 - value: 72.467 - - type: map_at_5 - value: 73.462 - - type: mrr_at_1 - value: 65.5 - - type: mrr_at_10 - value: 74.134 - - type: mrr_at_100 - value: 74.49799999999999 - - type: mrr_at_1000 - value: 74.509 - - type: mrr_at_3 - value: 72.467 - - type: mrr_at_5 - value: 73.462 - - type: ndcg_at_1 - value: 65.5 - - type: ndcg_at_10 - value: 78.144 - - type: ndcg_at_100 - value: 79.726 - - type: ndcg_at_1000 - value: 79.97800000000001 - - type: ndcg_at_3 - value: 74.735 - - type: ndcg_at_5 - value: 76.55999999999999 - - type: precision_at_1 - value: 65.5 - - type: precision_at_10 - value: 9.06 - - type: precision_at_100 - value: 0.976 - - type: precision_at_1000 - value: 0.1 - - type: precision_at_3 - value: 27.1 - - type: precision_at_5 - value: 17.16 - - type: recall_at_1 - value: 65.5 - - type: recall_at_10 - value: 90.60000000000001 - - type: recall_at_100 - value: 97.6 - - type: recall_at_1000 - value: 99.5 - - type: recall_at_3 - value: 81.3 - - type: recall_at_5 - value: 85.8 + value: 71.32470733210104 - task: - type: Classification + type: PairClassification dataset: - type: C-MTEB/waimai-classification - name: MTEB Waimai + type: mteb/twitterurlcorpus-pairclassification + name: MTEB TwitterURLCorpus config: default split: test - revision: 339287def212450dcaa9df8c22bf93e9980c7023 + revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - - type: accuracy - value: 89.43999999999998 - - type: ap - value: 75.53653890653014 - - type: f1 - value: 87.91597334503136 + - type: cos_sim_accuracy + value: 89.38176737687739 + - type: cos_sim_ap + value: 86.58811861657401 + - type: cos_sim_f1 + value: 79.09430644097604 + - type: cos_sim_precision + value: 75.45085977911366 + - type: cos_sim_recall + value: 83.10748383122882 + - type: dot_accuracy + value: 89.38370784336554 + - type: dot_ap + value: 86.58840606004333 + - type: dot_f1 + value: 79.10179860068133 + - type: dot_precision + value: 75.44546153308643 + - type: dot_recall + value: 83.13058207576223 + - type: euclidean_accuracy + value: 89.38564830985369 + - type: euclidean_ap + value: 86.58820721061164 + - type: euclidean_f1 + value: 79.09070942235888 + - type: euclidean_precision + value: 75.38729937194697 + - type: euclidean_recall + value: 83.17677856482906 + - type: manhattan_accuracy + value: 89.40699344122326 + - type: manhattan_ap + value: 86.60631843011362 + - type: manhattan_f1 + value: 79.14949970570925 + - type: manhattan_precision + value: 75.78191039729502 + - type: manhattan_recall + value: 82.83030489682784 + - type: max_accuracy + value: 89.40699344122326 + - type: max_ap + value: 86.60631843011362 + - type: max_f1 + value: 79.14949970570925 --- ## gte-Qwen2-7B-instruct