Reasoning Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
76.9Precision@1
28
May 22, 2026
80Accuracy
26
Apr 23, 2026
94.62Accuracy
21
Apr 8, 2026
1,158Latency (NoKV, ms)
5
Jun 11, 2026
74.55Accuracy
3
May 7, 2026
26.8p@1
3
Apr 29, 2026
53.5P@1
3
Apr 29, 2026