Autonomous Agentic Data Engineering Code
4MATSDeepSeek-R1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-R1Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 4 | 19.1 | |
| DeepSeek-R1Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 3.63 | 11.92 | |
| Qwen3-MaxAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.58 | 20.56 | |
| Claude-4-SonnetAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.24 | 69.33 | |
| DeepSeek-V3.1Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 2.17 | 24.1 | |
| GPT-5.2Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.07 | 49.24 | |
| DeepSeek-R1Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2 | 4.75 | |
| DeepSeek-V3.1Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2 | -4.58 | |
| Claude-4-SonnetAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2 | 15.53 | |
| Qwen3-MaxAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 2 | 32.77 | |
| DeepSeek-R1Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 2 | 0.45 | |
| Qwen3-MaxAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.83 | 34.16 | |
| GPT-5.2Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.75 | 50.68 | |
| Claude-4-SonnetAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.74 | 22.71 | |
| Gemini-2.5-ProAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.71 | 16.24 | |
| Gemini-2.5-ProAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.55 | 37.77 | |
| GPT-5.2Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1.5 | 34.89 | |
| Qwen3-MaxAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1.5 | 32.03 | |
| GPT-5.2Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.5 | 52.12 | |
| DeepSeek-V3.1Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.24 | 29.15 | |
| Gemini-2.5-ProAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1 | 22 | |
| DeepSeek-V3.1Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1 | 19.83 | |
| Gemini-2.5-ProAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1 | 20.56 | |
| Claude-4-SonnetAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1 | 14.07 |