Language Modeling on LAMBADA zero-shot (test)
69.12Accuracy (zero-shot)
GPTQ
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 69.12 | - | |
2021.08 | 63.24 | - | |
2026.01 | 62.97 | - | |
2021.08 | 61.73 | - | |
2021.08 | 58.47 | - | |
2021.08 | 58.2 | - | |
2021.08 | 57.89 | - | |
2021.08 | 57.38 | - | |
2021.08 | 57.29 | - | |
2021.08 | 57.23 | - | |
2026.01 | 56.45 | - | |
2021.08 | 56.36 | - | |
2021.08 | 55.06 | - | |
2021.08 | 45.99 | - | |
2021.08 | 45.18 | - | |
2026.01 | 38.75 | - | |
2026.01 | 38.36 | - | |
2026.01 | 38.36 | - | |
2026.01 | 38.01 | - | |
2026.01 | 36.77 | - | |
2026.01 | 36.67 | - | |
2026.01 | 35.52 | - | |
2021.08 | 34.78 | - | |
2021.08 | 34.58 | - | |
2021.08 | 34.41 | - | |
2021.08 | 34.16 | - | |
2021.08 | 33.4 | - | |
2021.08 | 33.24 | - | |
2021.08 | 33.19 | - | |
2021.08 | 32.99 | - | |
2026.01 | 32.56 | - | |
2021.08 | 32.54 | - | |
2026.01 | 32 | - | |
2026.01 | 31.59 | - | |
2023.12 | 30.2 | - | |
2023.12 | 29.4 | - | |
2026.01 | 29.2 | - | |
2026.01 | 29.05 | - | |
2023.12 | 28.6 | - | |
2023.12 | 28.2 | - | |
2023.12 | 23.5 | - | |
2023.12 | 20.4 | - | |
2023.12 | 20.4 | - | |
2023.12 | 20 | - | |
2024.06 | - | 51.28 | |
2024.06 | - | 49.86 | |
2024.06 | - | 47.52 | |
2026.01 | - | 45.04 | |
2026.01 | - | 93.47 | |
2026.01 | - | 57.28 | |
2026.01 | - | 65.4 | |
2026.01 | - | 50.92 | |
2026.01 | - | 51.7 | |
2026.01 | - | 44.66 | |
2026.01 | - | 45.35 | |
2026.01 | - | 35.66 | |
2026.01 | - | 42.77 | |
2026.01 | - | 44.1 | |
2026.01 | - | 40.62 | |
2026.01 | - | 39.08 |