Open-ended Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.05Judge Score
7
Apr 16, 2026
71.6LVM Evaluation Score
6
May 20, 2026
36BLEU-1
6
Apr 21, 2026
0.722Accuracy
6
Feb 26, 2026
67.4Open-ended Success Rate
5
May 20, 2026
50.8Accuracy
5
May 12, 2026
20.5Accuracy
5
May 12, 2026
60.9Accuracy
5
May 12, 2026
83Judge Score
5
Apr 16, 2026
81.81Judge Score
5
Apr 16, 2026
96.4Judge Score
5
Apr 16, 2026
54.2F1 Score
5
Mar 17, 2026
71Base Coverage
4
May 8, 2026
8.53GPT-4o Score
4
Apr 15, 2026
43BLEU-4
4
Mar 19, 2026
63.94Benign F1
2
Apr 28, 2026