Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TemporalWiki

Benchmarks

Task NameDataset NameSOTA ResultTrend
Temporal Knowledge ProbingTemporalWiki TWiki-Probes-1112
Accuracy (Unchanged)9.736
11
Temporal Knowledge ProbingTemporalWiki TWiki-Probes-1011
Accuracy (Unchanged)9.554
11
Temporal Knowledge ProbingTemporalWiki TWiki-Probes-0910
Score (Unchanged)9.999
11
Showing 3 of 3 rows