Mythos Firefox 147 Exploit Benchmark
- Entity ID:
ent-20260419-b2c3d4e5f6a7 - Type:
dataset - Scope:
shared - Status:
active - Aliases: firefox-147-rerun, js-shell-exploit-benchmark
Description
Internal Anthropic benchmark re-running Opus 4.6's Firefox 147 JavaScript-engine vulnerability set against Mythos Preview. Opus 4.6 produced 2 working exploits out of several hundred attempts; Mythos produced 181 working exploits plus 29 additional register-control achievements on the same vulnerability set. Converted from discovery benchmark into a reusable capability regression test.
Key claims
- Mythos produced 181 working Firefox 147 exploits vs Opus 4.6's 2
Relations
- Mythos Firefox 147 Exploit Benchmark --[contains]--> Two-Version Output Efficiency Directive
- Mythos Firefox 147 Exploit Benchmark --[related_to]--> Repository Triage Benchmark (5-Tier)