Language Modeling
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
3.918Perplexity
2
Jul 8, 2026
3.925Perplexity
2
Jul 8, 2026
2.421Validation Loss
2
Jul 7, 2026
32Readable Cells Rate
2
Jun 30, 2026
1.876Loss
2
Jun 5, 2026
2.048Loss
2
Jun 5, 2026
2.182Loss
2
Jun 5, 2026
10.26Arxiv Perplexity
2
Jun 4, 2026
13.92Perplexity
2
May 26, 2026
11.96Perplexity
2
May 22, 2026
7.244Perplexity
2
May 21, 2026
9.043Perplexity
2
May 21, 2026
12.313Perplexity
2
May 21, 2026
10.98Perplexity (PPL)
2
May 14, 2026
17.23PPL
2
May 14, 2026
17.85Perplexity
2
May 14, 2026
22.07Perplexity
2
May 12, 2026
19.73Perplexity (PPL)
2
May 12, 2026
12.978Perplexity
2
May 12, 2026
21.803Perplexity
2
May 12, 2026
23.819Perplexity
2
May 12, 2026
30.008Perplexity
2
May 12, 2026
3.765Perplexity
2
May 12, 2026
43.802Perplexity
2
May 12, 2026
11.301Perplexity
2
May 12, 2026