Checked fact 3001 Oct 2026Research

Anthropic reports that on its internal Binary Exploitation benchmark (100 randomly selected tasks) GLM-5.3 achieved full control-flow hijacks in 4% of trials and Claude Mythos Preview in 6%.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

We evaluate several models on 100 tasks from the benchmark (selected at random), and find that GLM-5.3 develops full control-flow hijacks in 4% of the trials; Claude Mythos Preview did so in 6%.

What the source said when we opened it, on 1 Oct 2026.

The source

GLM-5.3 and the spread of advanced cyber capabilities
Anthropic · 2026-09-29

Open the source archived copy

Checked

Checked by the notis newsroom on 1 Oct 2026, against the source above.

The number in it

4% · glm-5-3, benchmark score (Binary Exploitation (Anthropic internal, 100 tasks))
6% · claude-mythos-preview, benchmark score (Binary Exploitation (Anthropic internal, 100 tasks))

In the story

Anthropic says GLM-5.3 builds exploits close to Claude Mythos Preview 1 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic reports that on its internal Binary Exploitation benchmark (100 randomly selected tasks) GLM-5.3 achieved full control-flow hijacks in 4% of trials and Claude Mythos Preview in 6%.” ai notis, checked 1 Oct 2026. Source: GLM-5.3 and the spread of advanced cyber capabilities (Anthropic). https://ainotis.com/c/300

As a reference (APA style)

ai notis. (2026, October 1). Anthropic reports that on its internal Binary Exploitation benchmark (100 randomly selected tasks) GLM-5.3 achieved full control-flow hijacks in 4% of trials and Claude Mythos Preview in 6% [Checked claim 300]. ai notis. https://ainotis.com/c/300

Anyone may quote this address. It does not change; if we correct the story, this page says so.