Knowledge-intensive Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
42.3Truthfulness
36
Jun 11, 2026
69.19GPQA Score
16
Jun 11, 2026
53.8Pass@1
16
May 22, 2026
48.5Accuracy
14
May 13, 2026
3.11Speedup
12
Feb 26, 2026
39.8Truthfulness
8
Jun 11, 2026
71.7Pass@1 Accuracy
8
Jun 8, 2026
63.6Truthfulness
6
Jun 11, 2026
59.8Accuracy
6
Apr 10, 2026
36.8Truthfulness
4
Jun 11, 2026
2.9Truthfulness
4
Jun 11, 2026
0.46Training Cost (USD)
4
Feb 26, 2026
-0.9Truthfulness Score (T)
2
Jun 11, 2026