Lambada On Big Bench
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Gopher-280B (zero-shot) | 74.5 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | |
| Chinchilla-70B (zero-shot) | 77.4 | Training Compute-Optimal Large Language Models |
0 of 2 row(s) selected.