Instruction Induction
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
85.08Accuracy
80
May 21, 2026
91.3Accuracy
80
May 21, 2026
38.7Avg Execution Score
17
Feb 26, 2026
100Active to Passive
10
Feb 26, 2026
100Active to Passive
9
Feb 26, 2026
60.14BBII Text Classification Score
6
Feb 26, 2026
0.852Antonyms
6
Feb 26, 2026