Graduate-level Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.9Accuracy
224
Jun 19, 2026
40Score
33
May 29, 2026
37.4Accuracy
16
Feb 26, 2026
65.7Accuracy
11
Mar 9, 2026
2Acceptance Length
6
May 12, 2026
34.15Score
4
Jun 4, 2026