Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-hop Question Answering on HotpotQA fullwiki (val)

58.3Exact Match (EM)

SDP

29.169636.732344.29551.8577May 12, 2026May 21, 2026May 30, 2026Jun 9, 2026Jun 18, 2026Jun 27, 2026Jul 7, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.05
58.367.2-
2026.05
54.267-
2026.05
49.360.7-
2026.07
49.2262.181,588.5
2026.07
47.3259.982,373.1
2026.07
44.9860.951,766
2026.07
44.9661.082,569.7
2026.07
44.8560.831,545.7
2026.07
44.2557.12,807.3
2026.07
44.0659.511,355.4
2026.07
44.0460.233,432.1
2026.07
43.3956.171,723.5
2026.07
42.8255.732,814.3
2026.07
41.8154.451,720.1
2026.07
41.757.811,745.1
2026.07
40.4352.733,302
2026.07
39.5851.771,892.3
2026.05
39.240.5-
2026.07
39.1855.022,776
2026.07
38.6250.421,596.4
2026.07
37.7949.523,053.6
2026.07
37.4248.761,868.6
2026.07
35.6447.7968.8
2026.07
35.1747.612,843
2026.05
34.735-
2026.05
34.635.3-
2026.07
34.1947.831,120.4
2026.05
3434.4-
2026.07
32.8444.992,576.3
2026.07
32.5244.661,657.1
2026.07
32.1543.951,197.2
2026.07
32.1143.543,525.1
2026.07
31.5643.213,035.5
2026.07
30.2943.111,799.4