Benchmarks · agentic
ExploitBench v0.1
Agentic memory-corruption exploitation on real V8 CVEs; mean share of the 16-flag capability ladder (coverage → arbitrary read/write → code execution) across seeds.
4 models · 4 results · data as of 2026-10-29 · exploitbench.ai ↗
Leaderboard
Mythos Preview
All results
4 rows| # | Model | Effort | ExploitBench v0.1 |
|---|---|---|---|
| 1 | Mythos Preview | 78.0% | |
| 2 | GPT-5.5 Codex | xhigh | 72.0% |
| 3 | GPT-5.5 | xhigh | 47.0% |
| 4 | Opus 4.7 | max | 28.0% |