Frontier Red Team internal binary exploitation tasks
Reported model scores on Frontier Red Team internal binary exploitation tasks, best parseable score first. Each row keeps its verbatim score, test conditions and provenance, and links to the source coverage it was extracted from. Benchmark profile →
| Model | Score | Conditions | Provenance | Measured | Source |
|---|---|---|---|---|---|
| Anthropic Claude Mythos Preview | 6% | — | independent | — | coverage → |
| Z.ai GLM-5.3 | 4% of trials | — | independent | — | coverage → |
Scores are only comparable within one benchmark under matching conditions — results under different test setups, and scores from other benchmarks, are not directly comparable.