Multiple Choice Question Answering Mcqa On 2
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Gopher (few-shot, k=5) | 35.7 | Galactica: A Large Language Model for Science | |
| GAL 120B (zero-shot) | 32.5 | Galactica: A Large Language Model for Science | |
| BLOOM (few-shot, k=5) | 26.2 | Galactica: A Large Language Model for Science | |
| OPT (few-shot, k=5) | 29.4 | Galactica: A Large Language Model for Science | |
| Chinchilla (few-shot, k=5) | 33.3 | Galactica: A Large Language Model for Science |
0 of 5 row(s) selected.