Multiple-choice Question Answering on CommonsenseQA (CSQA)
66.4Accuracy
Llama-2-13b-chat (OTTER)
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2024.04 | 66.4 | 1.8 | |
2024.04 | 64.5 | 3.1 | |
2024.04 | 64 | 9.8 | |
2024.04 | 63.4 | 12.9 | |
2024.04 | 60.4 | 3.5 | |
2024.04 | 58.1 | 2 | |
2024.04 | 57.6 | 1 | |
2024.04 | 57 | 10.2 | |
2024.04 | 56.9 | 8.3 | |
2024.04 | 56.5 | 15.2 | |
2024.04 | 42.7 | 3.8 | |
2026.02 | 37.3 | - | |
2026.02 | 36.9 | - | |
2026.02 | 36.2 | - | |
2026.02 | 36.1 | - | |
2026.02 | 35.9 | - | |
2026.02 | 33.3 | - | |
2026.02 | 33.2 | - | |
2024.04 | 31.9 | 28.4 | |
2026.02 | 29.6 | - | |
2026.02 | 29.3 | - |