Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.4EM
15
Feb 26, 2026
0Task 1: 1 Supporting Fact Error
15
Feb 26, 2026
73Accuracy
15
Feb 26, 2026
62.58HotpotQA EM
14
Jun 29, 2026
32RL
14
Jun 29, 2026
0.19RL Score
14
Jun 29, 2026
30RL Score
14
Jun 29, 2026
86.8Accuracy
14
Jun 23, 2026
46.7Exact Match (EM)
14
Jun 16, 2026
67.13LLM Accuracy
14
Jun 2, 2026
33.9Containment Accuracy
14
Jun 2, 2026
69.4Containment Accuracy
14
Jun 2, 2026
65.6Containment Accuracy
14
Jun 2, 2026
92.38Accuracy
14
Jun 2, 2026
74.79F1 Score
14
Jun 2, 2026
89.1Accuracy
14
May 29, 2026
40.3F1 Score
14
May 28, 2026
73.4F1 Score
14
May 28, 2026
62.1F1 Score
14
May 27, 2026
40.54EM
14
May 27, 2026
48.8Exact Match Accuracy
14
May 21, 2026
88.5Exact Match
14
May 21, 2026
21.5BLEU
14
May 20, 2026
9.3BLEU
14
May 20, 2026
13.2BLEU
14
May 20, 2026