Logical Args 벤치마크
Logical Args on BIG-bench
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | Gopher-280B (few-shot, k=5) | 59.1 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | allenai/dolma · rvlopes/gloria · bramiozo/PubScience | 2021 |
| 2 | Chinchilla-70B (few-shot, k=5) | 56.2 | Training Compute-Optimal Large Language Models | karpathy/llama2.c · nkluge-correa/teenytinyllama | 2022 |