Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
45.96EM
23
Feb 26, 2026
48.96Accuracy
23
Mar 27, 2026
43.5EM
23
Jun 15, 2026
56.8EM
23
Mar 12, 2026
64.9EM
23
Mar 12, 2026
35.51EM
23
Mar 12, 2026
46.3EM
23
Mar 12, 2026
88.2EM (Total)
23
Feb 26, 2026
95Accuracy
22
Jun 2, 2026
61.2Accuracy (Acc)
22
May 20, 2026
85.2Accuracy
22
May 20, 2026
39.75Accuracy
22
May 13, 2026
59Accuracy
22
May 8, 2026
73.67Accuracy
22
May 8, 2026
68.8Exact Match (EM)
22
Jun 17, 2026
53.5PRR
22
Apr 29, 2026
66.5PRR
22
Apr 29, 2026
0.5PRR
22
Apr 29, 2026
36.5MC1 Score
22
Apr 28, 2026
37.3ARC-Challenge Score
22
May 11, 2026
84.1Accuracy
22
Mar 10, 2026
36.6Accuracy
22
Feb 26, 2026
86.8Accuracy
22
Jun 4, 2026
58.4Accuracy
22
May 22, 2026
44.1Accuracy
22
Mar 12, 2026