Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
32.62EM
8
Jun 12, 2026
46.86EM
8
Jun 12, 2026
59.65EM
8
Jun 12, 2026
40Accuracy
8
Jun 12, 2026
1.236SimpleQA Score
8
Jun 11, 2026
54.2Backward Score
8
Jun 9, 2026
99.1Accuracy
8
Jun 9, 2026
93.18CF
8
Jun 5, 2026
94.27Correct First (CF)
8
Jun 5, 2026
45.1Accuracy
8
Jun 5, 2026
55.2Accuracy
8
Jun 5, 2026
75.8LLaaJ
8
Jun 4, 2026
77.8Correctness Rate (RC)
8
Jun 4, 2026
89.1RC
8
Jun 4, 2026
117.39Exact Match (EM)
8
Jun 4, 2026
50.8F1 Score
8
May 29, 2026
75.3F1 Score
8
May 29, 2026
47.1F1 Score
8
May 29, 2026
52.2F1 Score
8
May 29, 2026
91.1Accuracy
8
May 29, 2026
73.2Accuracy
8
May 29, 2026
86.5Accuracy
8
May 29, 2026
100Answer Score
8
May 28, 2026
67.83EM
8
May 28, 2026
65.2WR Score
8
May 27, 2026