Language Modeling
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
17.08Score
8
Apr 15, 2026
28.44Score
8
Apr 15, 2026
11.42Perplexity (val)
8
Apr 15, 2026
43.511Perplexity (PPL)
8
Apr 2, 2026
33.008Perplexity (PPL)
8
Apr 2, 2026
29.339Perplexity (PPL)
8
Apr 2, 2026
15.77Perplexity (PPL)
8
Apr 1, 2026
94.09LM Score
8
Mar 9, 2026
2.25Perplexity
8
Mar 6, 2026
2.33Perplexity
8
Mar 6, 2026
3.24Perplexity
8
Mar 6, 2026
3.26Perplexity
8
Mar 6, 2026
7.96Perplexity
8
May 21, 2026
8.01Perplexity
8
Mar 6, 2026
8.68Perplexity
8
Mar 6, 2026
0.1Delta PPL (%)
8
May 27, 2026
1.96NLL
8
Feb 26, 2026
6.88PPL
8
Feb 26, 2026
3.167LCE
8
Feb 26, 2026
51.23PPL (Val)
8
Feb 26, 2026
28.32Perplexity (Before Attack)
8
Feb 26, 2026
0.559BPB
8
Feb 26, 2026
64.14ROUGE Score
8
Feb 26, 2026
3.25Finance Score
8
Feb 26, 2026
2.28Perplexity
8
Feb 26, 2026