Question Answering On Convfinqa
Metriken
Execution Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Execution Accuracy |
|---|---|
| are-chatgpt-and-gpt-4-general-purpose-solvers | 46.90 |
| convfinqa-exploring-the-chain-of-numerical | 68.9 |
| are-chatgpt-and-gpt-4-general-purpose-solvers | 76.48 |