Checked fact 2991 Oct 2026Research

Anthropic reports GLM-5.3 develops end-to-end exploits in 50 of 410 attempts on ExploitBench, and Claude Mythos Preview did so in 56 of 410 attempts.

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 find that GLM-5.3 develops end-to-end exploits in 50 of 410 attempts. Claude Mythos Preview did so at a similar rate—in 56 of 410 attempts.

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.

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 GLM-5.3 develops end-to-end exploits in 50 of 410 attempts on ExploitBench, and Claude Mythos Preview did so in 56 of 410 attempts.” ai notis, checked 1 Oct 2026. Source: GLM-5.3 and the spread of advanced cyber capabilities (Anthropic). https://ainotis.com/c/299

As a reference (APA style)

ai notis. (2026, October 1). Anthropic reports GLM-5.3 develops end-to-end exploits in 50 of 410 attempts on ExploitBench, and Claude Mythos Preview did so in 56 of 410 attempts [Checked claim 299]. ai notis. https://ainotis.com/c/299

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