| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| IPI-3k | AdapTools | ASR69.3 | 90 | 1mo ago | |
| CFH-Hard Computer Use | Attack Success Rate (IA)69 | 8 | 1mo ago | ||
| CFH-Hard Coding | Attack Success Rate (IA)7 | 8 | 1mo ago | ||
| payloads Original | Attack Success Rate (IA)10 | 8 | 1mo ago | ||
| RTE | Attack Success Rate93 | 2 | 1mo ago | ||
| SST2 | ASR98 | 2 | 1mo ago | ||
| Jfleg | ASR99.5 | 2 | 1mo ago | ||
| MRPC | ASR98.5 | 2 | 1mo ago | ||
| FIPI | ASR98.5 | 2 | 1mo ago |