Autonomous Agentic Data Engineering on Autonomous Agentic Data Engineering Finance
3.59MATSClaude-4-Sonnet
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude-4-SonnetAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 3.59 | 68.36 | |
| Qwen3-MaxAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 3.5 | 30 | |
| DeepSeek-V3.1Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 3 | 24.03 | |
| DeepSeek-V3.1Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 2.5 | 59.25 | |
| Claude-4-SonnetAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 2.35 | 39.69 | |
| Gemini-2.5-ProAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 2.16 | 64.11 | |
| DeepSeek-R1Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2 | -6.72 | |
| Gemini-2.5-ProAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 2 | 11.34 | |
| DeepSeek-R1Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 2 | 53.72 | |
| Claude-4-SonnetAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 2 | 61.34 | |
| DeepSeek-V3.1Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.8 | 40.28 | |
| DeepSeek-R1Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.65 | 54.92 | |
| DeepSeek-R1Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.56 | 26.56 | |
| GPT-5.2Agent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1.5 | 51.63 | |
| Claude-4-SonnetAgent Mode=One-Shot, Data Initialization Setting=From Scratch2026.05 | 1.5 | 17.46 | |
| GPT-5.2Agent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.5 | 13.72 | |
| Qwen3-MaxAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1.5 | 59.39 | |
| Qwen3-MaxAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.41 | 39.84 | |
| GPT-5.2Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.36 | 36.56 | |
| DeepSeek-V3.1Agent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.31 | 65.66 | |
| GPT-5.2Agent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.25 | 50.6 | |
| Qwen3-MaxAgent Mode=Iterative Agent, Data Initialization Setting=With Seed2026.05 | 1.23 | 61.33 | |
| Gemini-2.5-ProAgent Mode=Iterative Agent, Data Initialization Setting=From Scratch2026.05 | 1.13 | 35.06 | |
| Gemini-2.5-ProAgent Mode=One-Shot, Data Initialization Setting=With Seed2026.05 | 1 | 66.35 |