Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
17.1ES-ora Score
5
Jun 19, 2026
38.9ROUGE-L
5
Jun 18, 2026
70.81F1 Score
5
Jun 18, 2026
79.36F1 Score
5
Jun 18, 2026
1.36Inference Time (s)
5
Jun 15, 2026
4,582Solved Count
5
Jun 12, 2026
10.4Accuracy
5
Jun 11, 2026
55.96BBH MCQ Accuracy
5
Jun 11, 2026
3.78Standing Q_t^bg
5
Jun 11, 2026
3.9LLM-as-judge Score (1-5)
5
Jun 11, 2026
3.97LLM Judge Score (1-5)
5
Jun 11, 2026
3.87Score (1-5)
5
Jun 11, 2026
33.93Accuracy
5
Jun 9, 2026
82.34Accuracy
5
Jun 8, 2026
0Build Cost (tokens)
5
Jun 4, 2026
0Build Cost (Tokens)
5
Jun 4, 2026
0Build Cost
5
Jun 4, 2026
62.2Exact Match (EM)
5
Jun 4, 2026
75.2Exact Match (EM)
5
Jun 4, 2026
24Ours Win Count
5
Jun 1, 2026
71Accuracy
5
May 28, 2026
82Accuracy
5
May 28, 2026
2.3ECE
5
May 25, 2026
4.1ECE
5
May 25, 2026
89.97Accuracy (RGB)
5
May 22, 2026