Retrieval
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.869Recall@10
12
Feb 26, 2026
0.932Recall@10
12
Feb 26, 2026
0.924Recall@10
12
Feb 26, 2026
91.2Recall@10
12
Feb 26, 2026
0.931Recall@10
12
Feb 26, 2026
89.85Recall@10
12
Jun 2, 2026
91.17nDCG@10
12
Feb 26, 2026
94.24nDCG@10
12
Feb 26, 2026
93.56nDCG@10
12
Feb 26, 2026
24.04NDCG@10
12
Feb 26, 2026
0.184NDCG@10
12
Feb 26, 2026
0.219NDCG@10
12
Feb 26, 2026
66.71Accuracy
12
Feb 26, 2026
0.85NDCG@5
12
Feb 26, 2026
73.2NDCG@5
12
Feb 26, 2026
61.6NDCG@5
12
Feb 26, 2026
67.1NDCG@5
12
Feb 26, 2026
49.29Avg R
12
Feb 26, 2026
65.47Recall@500
11
Apr 29, 2026
44.9Recall@1
11
Apr 8, 2026
100HumanEval Score
11
Mar 24, 2026
78.82Long Task Score
11
Feb 26, 2026
70.77RTEB
11
Feb 26, 2026
60Top-1 Recall
11
Feb 26, 2026
77.01Top-20 Accuracy
11
Feb 26, 2026