Data Analysis Code Generation on DA-Code
0.399Overall ScoreReAct
Evaluation Results
| Method | Links | |
|---|---|---|
| ReActBackbone=o4-mini2026.06 | 0.399 | |
| ReActBackbone=DeepSeek-V3.12026.06 | 0.367 | |
| EvoDS-evo-8BBackbone=Qwen3-8B2026.06 | 0.355 | |
| EvoDS-8BBackbone=Qwen3-8B2026.06 | 0.337 | |
| ML-Master2Backbone=o4-mini2026.06 | 0.335 | |
| ReActBackbone=GPT-4o2026.06 | 0.303 | |
| DataMind-14BBackbone=Qwen2.5-Coder 14B2026.06 | 0.292 | |
| ML-Master2Backbone=DeepSeek-V3.12026.06 | 0.276 | |
| AutoGenBackbone=o4-mini2026.06 | 0.274 | |
| AutoGenBackbone=DeepSeek-V3.12026.06 | 0.26 | |
| Data InterpreterBackbone=GPT-4o2026.06 | 0.244 | |
| Data InterpreterBackbone=DeepSeek-V3.12026.06 | 0.234 | |
| Data InterpreterBackbone=o4-mini2026.06 | 0.227 | |
| LAMBDABackbone=o4-mini2026.06 | 0.221 | |
| DeepAnalyze-8BBackbone=DeepSeek-R1-0528-Qwen3-8B2026.06 | 0.217 | |
| LAMBDABackbone=DeepSeek-V3.12026.06 | 0.215 | |
| LATMBackbone=o4-mini2026.06 | 0.215 | |
| DataMind-7BBackbone=Qwen2.5-Coder 7B2026.06 | 0.211 | |
| LATMBackbone=DeepSeek-V3.12026.06 | 0.208 | |
| LAMBDABackbone=GPT-4o2026.06 | 0.2 | |
| ML-Master2Backbone=GPT-4o2026.06 | 0.195 | |
| AutoGenBackbone=GPT-4o2026.06 | 0.192 | |
| Code InterpreterBackbone=GPT-4o2026.06 | 0.171 | |
| LATMBackbone=GPT-4o2026.06 | 0.146 |