Long Context
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.7Score
25
Jun 1, 2026
67.59Accuracy
14
Apr 28, 2026
100Accuracy
6
Jul 7, 2026
99.8Accuracy
6
Feb 26, 2026
56.6Score
5
Jul 7, 2026
96.7RULER Accuracy (256k Context)
5
Jul 7, 2026
57.3Accuracy
4
Jul 7, 2026
88.26Accuracy
3
Apr 15, 2026
83.4Score
2
Jul 7, 2026
42.8Score
2
May 26, 2026
95Score
2
May 26, 2026
55.7Accuracy
2
Mar 11, 2026
71Accuracy
1
Apr 15, 2026
82.49Accuracy
1
Apr 15, 2026