Mythos漏洞复现基准测试：GPT-5.5仅5/18成功
Benchmarking Mythos-Linked Bug Rediscovery
这个实验戳破了AI漏洞发现能力的泡沫——即使给定了目标文件，顶级模型复现已知漏洞的成功率也极低。做AI安全评估或漏洞研究的团队，看完会重新审视benchmark的可靠性。
Anthropic在2026年4月发布的Mythos材料中声称其模型能发现真实漏洞，但本文通过控制实验复现了这些漏洞发现任务。
实验让GPT-5.5、Claude Opus 4.
7和Kimi K2在给定目标文件、只读源码和手动匹配规则下，尝试复现6个已知漏洞。结果显示，GPT-5.
5在54次尝试中仅成功5次（覆盖2/6任务），Claude Opus 4.7成功1次，Kimi K2为0次。
主要失败原因是模型过早锁定看似合理的候选错误，而忽略了补丁证据中的具体不变性。该结果不否定Anthropic未公开的工作流程，但表明在有利的靶标文件框架下，系统特定提示仅产生少量匹配。
Benchmarking Mythos-Linked Bug Rediscovery
Anthropic's April 2026 Mythos materials combine benchmark claims with concrete bug-finding stories across OpenBSD, FreeBSD, Linux, FFmpeg, and browsers. This paper reports a controlled target-file rediscovery experiment on six public or high-confidence Mythos-linked systems tasks. Each model receives the same target file or files, read-only source tools, three repeats per task, and one manual target-matching rubric; prompts omit CVE identifiers, patch hashes, advisory text, author names, disclosure dates, and answer key root cause language. The experiment contains 54 counted model-task attempts: three models, six tasks, and three repeats, giving 18 attempts per model. GPT-5.5 xhigh achieves 5/18 target rediscoveries, covering 2/6 tasks; counting one wrong-target mpegts.c finding separately gives 3/6 distinct core bugs. Claude Opus 4.7 achieves 1/18 target rediscoveries, covering 1/6 tasks. Kimi K2 records 0/18 target rediscoveries. The dominant failure mode is early commitment to plausible alternate candidates within the assigned file: models often submit source-grounded hypotheses while missing the specific invariant corrected by public Mythos patch evidence. These results do not refute Anthropic's undisclosed workflow, but show that under this favorable target-file scaffold, systems-specific prompting yields only six target matches across 54 counted attempts.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include 漏洞发现, 基准测试, GPT-5.5, Claude Opus 4.7.
Primary source verification: published directly by arXiv: Anthropic with first-party authority. Cross-source corroboration: 11 independent sources have covered this development (including berryxia, TestingCatalog, IT之家), confirming industry-wide signal strength.
