Common Sense Reasoning On Rwsd
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| Modell 1 | 0.669 |
| Modell 2 | 0.571 |
| Modell 3 | 0.669 |
| russiansuperglue-a-russian-language | 0.662 |
| russiansuperglue-a-russian-language | 0.84 |
| Modell 6 | 0.636 |
| Modell 7 | 0.649 |
| Modell 8 | 0.545 |
| Modell 9 | 0.669 |
| Modell 10 | 0.675 |
| mt5-a-massively-multilingual-pre-trained-text | 0.669 |
| Modell 12 | 0.669 |
| unreasonable-effectiveness-of-rule-based | 0.669 |
| Modell 14 | 0.669 |
| unreasonable-effectiveness-of-rule-based | 0.597 |
| Modell 16 | 0.669 |
| Modell 17 | 0.662 |
| Modell 18 | 0.669 |
| Modell 19 | 0.669 |
| unreasonable-effectiveness-of-rule-based | 0.669 |
| Modell 21 | 0.669 |
| Modell 22 | 0.669 |