History
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
History
89Accuracy
83
History
83.58Macro F1
28
History factoid QA (test)
94.9Accuracy
25
History 10-shot (test)
78.81Average Accuracy
19
History
91.76AUC
19
History
84.7Anomaly F1
18
History
71.83Accuracy
15
History (test)
64.5Accuracy
15
History LLM-embedded (test)
75.86Accuracy
10
History
5Explanation Utility
3
History
18Pre-training Time
2
History (test)
—Primary metric
0