Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88.5Accuracy
7
Jul 8, 2026
89.8Accuracy
7
Jul 8, 2026
89.3Accuracy
7
Jul 8, 2026
75.22Avg@8
7
Jul 3, 2026
70.4EM
7
Jun 30, 2026
54.8EM (Exact Match)
7
Jun 30, 2026
55.5LVBench Score
7
Jun 29, 2026
0.21RL Score
7
Jun 29, 2026
0.27RL
7
Jun 29, 2026
0.18RL
7
Jun 29, 2026
0.23RL
7
Jun 29, 2026
40.32EM
7
Jun 26, 2026
19.53Exact Match (EM)
7
Jun 26, 2026
36.82EM
7
Jun 26, 2026
40.34EM
7
Jun 26, 2026
59.63Exact Match (EM)
7
Jun 26, 2026
39.2EM
7
Jun 26, 2026
90.11Accuracy
7
Jun 26, 2026
88.53Accuracy
7
Jun 26, 2026
8Accuracy
7
Jun 23, 2026
31.8Accuracy (WebQuestions)
7
Jun 23, 2026
52.74R-Fact Score
7
Jun 23, 2026
32Accuracy
7
Jun 18, 2026
0.462Judgment Score (Jdg)
7
Jun 18, 2026
45.06Accuracy/F1
7
Jun 16, 2026