Data Analysis on DABStep 2025 (hard-level)
45.24AccuracyDS-STAR
Evaluation Results
| Method | Links | |
|---|---|---|
| DS-STARFramework=DS-STAR, Model=Gemini-2.5-Pro2025.09 | 45.24 | |
| Amity DA AgentFramework=Amity DA Agent, Model=Gemini-2.5-Pro2025.09 | 41.01 | |
| DeepAnalyze-8BFramework=Model-only, Model=DeepAnalyze-8B2025.09 | 32.8 | |
| I2I-AgentFramework=I2I-Agent, Model=Claude-3.5-Sonnet2025.09 | 28.04 | |
| DA-AgentFramework=DA-Agent, Model=Gemini-2.5-Pro2025.09 | 22.49 | |
| ReActFramework=ReAct, Model=Claude-4-Sonnet2025.09 | 19.84 | |
| Open Data ScientistFramework=Open Data Scientist, Model=DeepSeek-V32025.09 | 16.4 | |
| o4-miniFramework=Model-only, Model=o4-mini2025.09 | 14.55 | |
| Gemini-2.5-ProFramework=Model-only, Model=Gemini-2.5-Pro2025.09 | 12.7 | |
| AutoGenFramework=AutoGen, Model=Gemini-2.5-Pro2025.09 | 10.32 | |
| ReActFramework=ReAct, Model=Gemini-2.5-Pro2025.09 | 10.05 | |
| Data InterpreterFramework=Data Interpreter, Model=Gemini-2.5-Pro2025.09 | 3.44 |