Machine Learning Engineering on MLE-Dojo (Score)
31.1ScoreEvoDS-evo-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| EvoDS-evo-8BBackbone=Qwen3-8B2026.06 | 31.1 | |
| ReActBackbone=o4-mini2026.06 | 30.8 | |
| EvoDS-8BBackbone=Qwen3-8B2026.06 | 30.2 | |
| ML-Master2Backbone=DeepSeek-V3.12026.06 | 29.9 | |
| ML-Master2Backbone=o4-mini2026.06 | 29.8 | |
| ML-Master2Backbone=GPT-4o2026.06 | 27.3 | |
| LAMBDABackbone=GPT-4o2026.06 | 26.8 | |
| LAMBDABackbone=DeepSeek-V3.12026.06 | 26.5 | |
| LAMBDABackbone=o4-mini2026.06 | 25.4 | |
| ReActBackbone=GPT-4o2026.06 | 22.8 | |
| ReActBackbone=DeepSeek-V3.12026.06 | 19.9 | |
| Code InterpreterBackbone=GPT-4o2026.06 | 18.1 | |
| LATMBackbone=o4-mini2026.06 | 17.3 | |
| AutoGenBackbone=o4-mini2026.06 | 16.5 | |
| Data InterpreterBackbone=o4-mini2026.06 | 15.2 | |
| LATMBackbone=DeepSeek-V3.12026.06 | 14 | |
| AutoGenBackbone=DeepSeek-V3.12026.06 | 13.7 | |
| DataMind-14BBackbone=Qwen2.5-Coder 14B2026.06 | 13.6 | |
| LATMBackbone=GPT-4o2026.06 | 13.2 | |
| Data InterpreterBackbone=DeepSeek-V3.12026.06 | 12.6 | |
| AutoGenBackbone=GPT-4o2026.06 | 10.8 | |
| Data InterpreterBackbone=GPT-4o2026.06 | 10.2 | |
| DeepAnalyze-8BBackbone=DeepSeek-R1-0528-Qwen3-8B2026.06 | 4.4 | |
| DataMind-7BBackbone=Qwen2.5-Coder 7B2026.06 | 1 |