Autonomous Agentic Data Engineering on Autonomous Agentic Data Engineering Average
3.7MATSDeepSeek-V3.1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-V3.1Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 3.7 | 36.76 | |
| DeepSeek-R1Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.8 | 54.59 | |
| Claude-4-SonnetAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.67 | 73.26 | |
| DeepSeek-V3.1Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2.5 | 12.5 | |
| DeepSeek-R1Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 2.44 | 25.16 | |
| Claude-4-SonnetAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 2.23 | 40.44 | |
| DeepSeek-R1Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2.17 | 15.32 | |
| Claude-4-SonnetAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2.17 | 21.05 | |
| GPT-5.2Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.14 | 56.01 | |
| Qwen3-MaxAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2 | 33.24 | |
| DeepSeek-V3.1Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 2 | 43.95 | |
| Qwen3-MaxAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.85 | 52.19 | |
| Qwen3-MaxAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.83 | 47.17 | |
| Claude-4-SonnetAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.83 | 51.63 | |
| Gemini-2.5-ProAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.78 | 49.5 | |
| GPT-5.2Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1.67 | 40.73 | |
| Gemini-2.5-ProAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1.67 | 22.99 | |
| DeepSeek-R1Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.67 | 45.92 | |
| Qwen3-MaxAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.61 | 44.08 | |
| GPT-5.2Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.51 | 57.29 | |
| Gemini-2.5-ProAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.48 | 31.03 | |
| DeepSeek-V3.1Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.34 | 57.65 | |
| GPT-5.2Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.33 | 41.36 | |
| Gemini-2.5-ProAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1 | 57.97 |