Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80.4Score
3
Feb 26, 2026
68.5QA Score
3
Feb 26, 2026
27.7MC1
3
Feb 26, 2026
24Accuracy
3
Feb 26, 2026
78.64Accuracy
3
Feb 26, 2026
60.42Accuracy
3
Feb 26, 2026
40.2Context Relevance Score
3
Feb 26, 2026
74.3Context Relevance
3
Feb 26, 2026
87.5EM
3
Feb 26, 2026
17.19EM
3
Feb 26, 2026
25.3Accuracy
3
Feb 26, 2026
34.3Accuracy
3
Feb 26, 2026
55Accuracy
3
Feb 26, 2026
26.8Accuracy
3
Feb 26, 2026
52.72AUC Top-1 Acc
3
Feb 26, 2026
50.4Accuracy
3
Feb 26, 2026
4.25Relative CPU Speed
3
Feb 26, 2026
59.1Answer Accuracy
3
Feb 26, 2026
70.8Answer Accuracy
3
Feb 26, 2026
67.1Accuracy
3
Feb 26, 2026
81.9F1 (el)
3
Feb 26, 2026
12.94Throughput (TPS)
3
Apr 21, 2026
54.8Exact Match
3
Feb 26, 2026
52.8Exact Match
3
Feb 26, 2026
0.908Accuracy
3
Feb 26, 2026