| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CVEBench One-Day | Seed Agent | Pass@126.1 | 4 | 8d ago | |
| CVEBench Zero-Day | Seed Agent | pass@118.3 | 4 | 8d ago | |
| D2 (s1) | EVOPOC | Exploitation Count50 | 3 | 1mo ago | |
| D2 (s2) | EVOPOC | Exploited29 | 2 | 1mo ago | |
| XBOW (full) | AWE | Total Cost7.73 | 2 | 3mo ago | |
| CVE-GENIE 603 CVEs (test) | FORGE | Total CVEs Attempted603 | 1 | 4h ago | |
| VirtualBox real-world vulnerabilities | - | - | 0 | 3mo ago | |
| QEMU real-world vulnerabilities | - | - | 0 | 3mo ago |