Command Palette
Search for a command to run...
Triviaqa On Big Bench
Metrics
Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | Repository | ||
|---|---|---|---|
| Gopher-280B (few-shot, k=64) | 57.1 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
0 of 1 row(s) selected.