General Instruction Following
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
22.1Score
46
Mar 4, 2026
85.9Score
38
Jul 7, 2026
84.1Accuracy
30
May 12, 2026
92.6Score
19
Feb 26, 2026
23Success Rate
3
May 22, 2026
51.06Accuracy
3
Feb 26, 2026