Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.6Score
36
Feb 26, 2026
79.9Accuracy (ACC)
36
Feb 26, 2026
99.75Accuracy
36
Feb 26, 2026
92.12Accuracy
36
Feb 26, 2026
100Accuracy
36
Feb 27, 2026
50.4Attack Success Rate
35
May 25, 2026
763Correlation Score
35
May 20, 2026
2,075Correlation (alpha=0.17)
35
May 20, 2026
20ACE
35
Apr 10, 2026
0.32ACE
35
Apr 10, 2026
45EM
35
Apr 8, 2026
72.28EM
35
Apr 8, 2026
85.59Exact Match (EM)
35
Apr 8, 2026
84.3Accuracy
35
May 15, 2026
89.3Score
35
May 6, 2026
72.7Avg Accuracy
35
Feb 26, 2026
80.1EM
35
Feb 26, 2026
76.2F1 Score
35
Feb 26, 2026
88Accuracy
34
Jun 24, 2026
73.1Accuracy
34
Jun 24, 2026
90.6Accuracy
34
Apr 29, 2026
53.5EM
34
Mar 10, 2026
74.1LLM Accuracy
34
Mar 4, 2026
89.7EM
34
Feb 26, 2026
82.2Answer F1
34
Jun 12, 2026