| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Finance D2 | SFT | Match Ratio (Mean)47.6 | 11 | 13d ago | |
| Dolly D2 | SFT | Mean Match Ratio49.2 | 11 | 13d ago | |
| The Pile (test) | GPT-Neo 1.3B | Fractional Extraction Rate63.4 | 10 | 1mo ago | |
| GPT-2 (train) | AttenMIA | Pearson r0.48 | 8 | 1mo ago | |
| MATH (test) | SFT | Mean Match Ratio40.9 | 4 | 13d ago | |
| Epidemiological Literature Outbreaks | AgentSLR | Precision85 | 3 | 24d ago | |
| Epidemiological Literature Models | AgentSLR | Precision90 | 3 | 24d ago | |
| Epidemiological Literature Parameters | AgentSLR | Precision83 | 3 | 24d ago | |
| Digital health research papers 150 data points (first 10 papers in a random subset of 50) | OpenExtract | Precision84.6 | 3 | 1mo ago |
