Knowledge
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.787Score
3
Feb 26, 2026
92.28Score
2
May 26, 2026
68.02Score
2
May 26, 2026
79.39Score
2
May 26, 2026
0.346Normalized Probability Mass
2
Mar 18, 2026
58.5Compression Accuracy
2
Mar 18, 2026
0.696Normalized Log Accuracy
2
Mar 18, 2026
49.3Normalized Log Accuracy
2
Mar 18, 2026
29.4Log Accuracy (0-shot)
2
Mar 18, 2026
65.2Normalized Log Accuracy
2
Mar 18, 2026
67.06Score
2
Feb 26, 2026
42.18Knowledge Score
2
Feb 26, 2026
41.41Score
2
Feb 26, 2026