In-context retrieval
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
50.1SQuAD Accuracy
30
May 8, 2026
23.23FDA Accuracy
23
Apr 24, 2026
88.6Accuracy
16
Apr 13, 2026
100S-NIAH-1 (1K)
13
Jun 26, 2026
41.96SWDE Score
13
May 22, 2026
62.5Accuracy
13
Mar 17, 2026
74.5Accuracy
13
Mar 17, 2026
56.7Accuracy
13
Mar 17, 2026
41.3Accuracy
13
Mar 17, 2026
100S-N Score
10
Jul 7, 2026
100S-N
10
Jul 7, 2026
100S1 Score
8
Apr 10, 2026
100S-N Score
7
Jul 7, 2026
80.3Fuzzy ICR
6
Jun 30, 2026
99.55MQ Score
4
Apr 10, 2026
99S-N Score
3
Jul 7, 2026
99S-N Score
3
Jul 7, 2026
96S-N Score
1
Jul 7, 2026
97S-N
1
Jul 7, 2026
100S-N Score
1
Jul 7, 2026