Instruction Following
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81Strict Accuracy
24
Jun 4, 2026
60.3SBERT Similarity
24
Feb 26, 2026
60.2SBERT Similarity
24
Feb 26, 2026
73.6SBERT Similarity
24
Feb 26, 2026
71.4SBERT Similarity
24
Feb 26, 2026
82.5Accuracy
24
Feb 26, 2026
38.5Overall Score
23
Apr 15, 2026
66.9CSR
23
Apr 15, 2026
52.4Average Score
23
Apr 15, 2026
7.9Average Score
23
Apr 15, 2026
79.8Overall Score
23
Apr 15, 2026
70.4HSR
23
Apr 15, 2026
68ISR
23
Apr 15, 2026
0.871Precision (L)
23
Apr 15, 2026
79.79IFBench Score
23
Jun 16, 2026
34.39ROUGE-L
23
Mar 5, 2026
64.2ISR
23
Feb 26, 2026
0.76ISR
23
Feb 26, 2026
82.2ISR
23
Feb 26, 2026
88.7ISR
23
Feb 26, 2026
0.982ISR
23
Feb 26, 2026
70.2SSR
22
Jul 7, 2026
85.4Score (%)
22
Jun 26, 2026
2.78Average Length
22
Mar 16, 2026
32.64ROUGE-L
22
May 21, 2026