Language Modeling
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
0.74BPB
4
Feb 26, 2026
1Perplexity (PPL)
4
Feb 26, 2026
1PPL
4
Feb 26, 2026
31.92Perplexity
4
Feb 26, 2026
28Test Perplexity (10 epochs)
4
Feb 26, 2026
104.66Perplexity
3
Jul 7, 2026
7.48Anatomy Accuracy
3
Jun 30, 2026
9.72Score
3
Jun 19, 2026
2.491Perplexity
3
Jun 15, 2026
1.216Perplexity
3
Jun 12, 2026
1.275Perplexity
3
Jun 12, 2026
1.247Perplexity
3
Jun 12, 2026
1.148Perplexity
3
Jun 12, 2026
3.595BPB
3
Jun 5, 2026
53.29Accuracy
3
Jun 4, 2026
11.502Perplexity
3
Jun 1, 2026
0.021CF Score
3
May 27, 2026
0.072CF
3
May 27, 2026
44.36LAMBADA Accuracy
3
May 26, 2026
2.077Validation Cross-Entropy
3
May 26, 2026
63.4Accuracy (LAMBADA 5-shot)
3
May 25, 2026
9.75Perplexity (C4)
3
May 21, 2026
31.45Validation Perplexity
3
May 20, 2026
14.9Perplexity
3
May 12, 2026
15.03Final PPL
3
May 12, 2026