Data Analysis (Accuracy) on DABench
90.2AccuracyANN
Evaluation Results
| Method | Links | |
|---|---|---|
| ANNBackbone=GPT-42025.06 | 90.2 | |
| ANNBackbone=GPT-4o-mini2025.06 | 90.2 | |
| Captain AgentBackbone=GPT-42025.06 | 88.32 | |
| AutoGenBackbone=GPT-42025.06 | 82.88 | |
| ANNBackbone=GPT-3.5-turbo2025.06 | 76 | |
| AutoAgentsBackbone=GPT-42025.06 | 57.98 | |
| Meta-promptingBackbone=GPT-42025.06 | 39.69 | |
| Vanilla LLMBackbone=GPT-42025.06 | 6.61 |