Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
53GenAcc
5
May 20, 2026
69TempAcc
5
May 20, 2026
58.8AUROC
5
May 20, 2026
0.636AUROC (MMLU QA)
5
May 20, 2026
84.63Accuracy
5
May 19, 2026
85.06Accuracy
5
May 19, 2026
86.92Accuracy
5
May 19, 2026
48.27ARC-c
5
May 19, 2026
0.724Cosine Similarity
5
May 19, 2026
63.46Accuracy
5
May 14, 2026
73.41Accuracy
5
May 14, 2026
78.2KU Score
5
May 12, 2026
15.65LLMcritic Calls
5
May 11, 2026
26.7CR (%)
5
May 8, 2026
74.5CR (%)
5
May 8, 2026
71.9Accuracy
5
May 8, 2026
34.7Accuracy
5
May 8, 2026
25.39BLEU
5
May 8, 2026
94Accuracy
5
May 1, 2026
97Accuracy
5
May 1, 2026
47.2F1 Score
5
Apr 30, 2026
10Exact Match (EM)
5
Apr 30, 2026
26.8EM
5
Apr 30, 2026
47.8EM
5
Apr 30, 2026
28Accuracy
5
Apr 29, 2026