Language Generation on Language Modeling Evaluation Set
7Generative Perplexity (Llama2)
Data
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.06 | 7 | 9.4 | 14.7 | 7.7 | |
2026.06 | 13.1 | 18.9 | 18.9 | 7.2 | |
2026.06 | 13.4 | 19.2 | 19.2 | 7.2 | |
2026.06 | 19 | 28.8 | 25.5 | 7.2 | |
2026.06 | 19.6 | 28.8 | 25.5 | 7.3 | |
2026.06 | 21.8 | 33 | 26.9 | 7.5 | |
2026.06 | 22.2 | 40.9 | 38.7 | 7.5 | |
2026.06 | 22.8 | 37.5 | 37.5 | 7.5 | |
2026.06 | 22.9 | 40.3 | 35.7 | 8.1 | |
2026.06 | 23.2 | 37.6 | 37.6 | 7.5 | |
2026.06 | 25.4 | 43.7 | 36.6 | 7.6 | |
2026.06 | 26.3 | 44.1 | 42.5 | 7.6 | |
2026.06 | 26.7 | 45 | 40.8 | 7.1 | |
2026.06 | 26.8 | 44.4 | 42 | 7.6 | |
2026.06 | 27.3 | 43.7 | 41.5 | 7.6 | |
2026.06 | 27.6 | 44.6 | 42.6 | 7.6 | |
2026.06 | 28.5 | 48.4 | 47.3 | 7.6 | |
2026.06 | 29.5 | 51.9 | 48.6 | 7.6 | |
2026.06 | 29.6 | 42.8 | 44.6 | 7.7 | |
2026.06 | 30.6 | 52.6 | 52.4 | 7.8 | |
2026.06 | 31.1 | 54.1 | 51.8 | 7.3 | |
2026.06 | 32.2 | 57.3 | 54.3 | 7.9 | |
2026.06 | 32.4 | 56.5 | 55.5 | 7.9 | |
2026.06 | 32.5 | 54.3 | 52.2 | 7.7 | |
2026.06 | 34.7 | 62.2 | 62.1 | 7.9 | |
2026.06 | 35.4 | 64 | 64.1 | 7.7 | |
2026.06 | 35.6 | 65.4 | 63.2 | 7.7 | |
2026.06 | 35.7 | 62.9 | 61.7 | 7.9 | |
2026.06 | 36.1 | 65 | 64.8 | 7.8 | |
2026.06 | 36.6 | 64.1 | 63.5 | 7.6 | |
2026.06 | 37.2 | 66.9 | 66.8 | 7.9 | |
2026.06 | 37.9 | 69.6 | 66.7 | 7.5 | |
2026.06 | 40.4 | 79.9 | 68.2 | 8.1 | |
2026.06 | 40.6 | 80 | 69.4 | 8.1 | |
2026.06 | 43.2 | 83.2 | 71.3 | 8 | |
2026.06 | 43.2 | 83.5 | 71.7 | 8 | |
2026.06 | 43.8 | 82.4 | 74.3 | 7.9 | |
2026.06 | 45.8 | 85.3 | 74.1 | 7.9 | |
2026.06 | 46.3 | 86.6 | 78.5 | 8.1 | |
2026.06 | 47.1 | 89.8 | 83.9 | 7.7 | |
2026.06 | 47.2 | 86.4 | 76.4 | 8.1 | |
2026.06 | 48.5 | 86.7 | 78.8 | 8.1 |