Spoken Instruction Following
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.6Consistency
7
May 21, 2026
60.3LC Win Rate
7
May 21, 2026
65.4LC Win Rate
7
May 21, 2026
0.689Win Rate (LC)
7
May 21, 2026
71.2LC Win Rate
7
May 21, 2026
77LC Win Rate
7
May 21, 2026