Command Palette
Search for a command to run...
Timedial On Big Bench
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
| Paper Title | ||
|---|---|---|
| Chinchilla-70B (few-shot, k=5) | 68.8 | Training Compute-Optimal Large Language Models |
| Gopher-280B (few-shot, k=5) | 50.9 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
0 of 2 row(s) selected.