Language Modeling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
39.872Perplexity
2
May 12, 2026
36.674Perplexity
2
May 12, 2026
0.889Perplexity
2
Apr 10, 2026
423.81Perplexity
2
Apr 10, 2026
131.95Perplexity
2
Apr 10, 2026
556.73Perplexity
2
Apr 10, 2026
145.55Perplexity
2
Apr 10, 2026
24.7Perplexity
2
Apr 6, 2026
2.708Cross-Entropy Loss
2
Mar 31, 2026
7.25PPL
2
Mar 20, 2026
18.008Perplexity (PPL)
2
Mar 20, 2026
18.294Perplexity (PPL)
2
Mar 20, 2026
20.656Perplexity (PPL)
2
Mar 20, 2026
19.461Perplexity (PPL)
2
Mar 20, 2026
17.731Perplexity (PPL)
2
Mar 20, 2026
22.002Perplexity (PPL)
2
Mar 20, 2026
17.783Perplexity (PPL)
2
Mar 20, 2026
15.405Perplexity (PPL)
2
Mar 20, 2026
14.96Perplexity (PPL)
2
Mar 20, 2026
15.972Perplexity (PPL)
2
Mar 20, 2026
15.097Perplexity (PPL)
2
Mar 20, 2026
19.55Perplexity (PPL)
2
Mar 20, 2026
18.414Perplexity (PPL)
2
Mar 20, 2026
16.903Perplexity (PPL)
2
Mar 20, 2026
18.354Perplexity (PPL)
2
Mar 20, 2026