| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Scaling Law Discovery lr&bsz | Ours | R2 Score (Target Region)0.22 | 19 | 2mo ago | |
| DSBench | VeriGraph-8B | Score66.43 | 18 | 1mo ago | |
| DA-Code (test) | DA-Agent | Data Wrangling Score34.8 | 9 | 4mo ago | |
| DS-1000 | EvoRoute | Performance Score56.5 | 8 | 4mo ago | |
| DS-1000 | Qwen2.5-7B-Ins + ADR | Pass@142.44 | 3 | 1mo ago | |
| Scaling Law Discovery u_shape | SIMPLETES | R2 Score-0.008 | 2 | 3mo ago | |
| Scaling Law Discovery domain_mix | SIMPLETES | R2 Score99.1 | 2 | 3mo ago | |
| Scaling Law Discovery parallel | SLDAgent | R2 Score1 | 2 | 3mo ago |