Commonsense Reasoning on HellaSwag (val)
95.3Accuracy
GPT-4
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2023.03 | 95.3 | - | - | |
2026.02 | 91 | - | - | |
2026.02 | 90.2 | - | - | |
2026.02 | 90 | - | - | |
2023.03 | 85.6 | - | - | |
2023.03 | 85.5 | - | - | |
2023.03 | 84.2 | - | - | |
2026.02 | 82.4 | - | - | |
2026.02 | 81.8 | - | - | |
2026.02 | 77.6 | - | - | |
2026.06 | 68.4 | - | - | |
2026.05 | 66 | - | - | |
2026.05 | 65 | - | - | |
2026.05 | 64.5 | - | - | |
2026.05 | 63.5 | - | - | |
2026.05 | 63.5 | - | - | |
2026.05 | 62 | - | - | |
2026.05 | 62 | - | - | |
2026.05 | 61.5 | - | - | |
2026.05 | 61.5 | - | - | |
2026.05 | 60.5 | - | - | |
2026.05 | 60.5 | - | - | |
2026.05 | 60 | - | - | |
2026.05 | 59 | - | - | |
2026.05 | 59 | - | - | |
2026.05 | 59 | - | - | |
2026.05 | 59 | - | - | |
2026.05 | 58.5 | - | - | |
2026.06 | 58.1 | 1.1078 | 97.77 | |
2026.06 | 57.4 | - | - | |
2026.06 | 56.6 | - | - | |
2026.06 | 56.5 | 1.1254 | 99.989 | |
2026.06 | 56.2 | - | - | |
2026.06 | 55.8 | - | - | |
2024.01 | 54.8 | - | - | |
2026.06 | 53.6 | 1.1708 | 99.06 | |
2026.05 | 53 | - | - | |
2026.05 | 52.5 | - | - | |
2026.05 | 52.5 | - | - | |
2026.06 | 52.1 | 1.1848 | 96.8 | |
2026.06 | 51.6 | - | - | |
2026.05 | 51 | - | - | |
2026.05 | 51 | - | - | |
2026.06 | 50.9 | - | - | |
2024.07 | 50.7 | - | - | |
2024.01 | 50.5 | - | - | |
2026.06 | 49.8 | - | - | |
2024.01 | 49.1 | - | - | |
2024.07 | 46.8 | - | - | |
2024.01 | 46.2 | - | - | |
2024.07 | 46 | - | - | |
2024.07 | 45 | - | - | |
2024.01 | 38.8 | - | - | |
| 38.8 | - | - | ||
2026.05 | 37.46 | - | - | |
2026.06 | 35.9 | - | - | |
2026.06 | 34.8 | - | - | |
2024.07 | 33.8 | - | - | |
2026.05 | 33.79 | - | - | |
2024.07 | 33.4 | - | - | |
2024.07 | 33.3 | - | - | |
2024.07 | 33.2 | - | - | |
2026.05 | 31.82 | - | - | |
2026.05 | 31.58 | - | - | |
| 31.3 | - | - | ||
2026.05 | 30.96 | - | - | |
2026.05 | 30.2 | - | - | |
2026.05 | 30.08 | - | - |