← Back to the wire

Anthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploits

AchievementBenchmarkSep 30, 2026

On ExploitBench, Zhipu AI's open-weight GLM-5.3 built working exploits in 50 of 410 attempts, close to Anthropic's Claude Mythos Preview at 56, according to an Anthropic analysis. Anthropic says GLM-5.3's safeguards can be bypassed, with refusal rates dropping to 2–12 percent after abliteration. CAISI calls it the most cyber-capable open-weight model to date, about four months behind leading US models. OpenAI is restricting access to its comparable model, Daybreak, while GLM-5.3 is freely downloadable.

Receipt № 21541 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

OpenAICompanyAnthropicCompanyZhipu AICompanyClaude Mythos PreviewModelDaybreakModelGLM-5.3Model
Canonical: https://the-decoder.com/anthropic-says-zhipus-open-weight-glm-5-3-nearly-matches-claude-mythos-preview-at-building-exploits/