Natural Language Inference on RTE (0-shot and 32-shot settings)
84.8Accuracy (0-shot)
OPT-IML 175B
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2022.12 | 84.8 | 83.8 | |
2022.12 | 83.8 | 73.3 | |
2022.12 | 66.8 | 48.7 | |
2025.10 | 65.34 | - | |
2025.10 | 64.26 | - | |
2025.10 | 63.18 | - | |
2025.10 | 62.82 | - | |
2025.10 | 60.65 | - | |
2025.10 | 60.65 | - | |
2022.12 | 60.3 | 71 | |
2025.10 | 60.29 | - | |
2025.10 | 59.93 | - | |
2025.10 | 59.57 | - | |
2022.12 | 58.1 | 61.7 | |
2025.10 | 57.76 | - | |
2025.10 | 57.4 | - | |
2025.10 | 55.96 | - | |
2025.10 | 55.6 | - | |
2022.12 | 54.2 | 47.3 | |
2025.10 | 53.79 | - | |
2025.10 | 53.43 | - | |
2025.10 | 53.43 | - | |
2025.10 | 53.07 | - | |
2025.10 | 53.07 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.71 | - | |
2025.10 | 52.35 | - | |
2025.10 | 46.57 | - |