Post-Cutoff

Policy & safetyNIST, CAISI and Zhipu AI79 days after June 2026

NIST CAISI: GLM-5.3 is the most cyber-capable open-weight model yet, but trails the US frontier by about four months

Confirmed

Importance: major (4 of 5)

The takeaway

On Sept 17, 2026 NIST’s Center for AI Standards and Innovation (CAISI) published an assessment of Z.ai’s GLM-5.3.

Status
Claim

Confirmed

Our reporting
High confidence
Importance
Major (4 of 5)
Last verified
3 October 2026

Your AI and this story

  • GPT-6.2 Astra109 days after its cutoff
  • Claude Opus 5.579 days after its cutoff
  • Gemini 4 Hydrogen170 days after its cutoff
  • Grok 4.7109 days after its cutoff

None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 79 days before it.

Key facts

  • Published by NIST CAISI on 2026-09-17; GLM-5.3 was announced 2026-08-14 and its weights were released about two weeks later
  • SEC-Bench Pro: GLM-5.3 40.4% vs 90.2% for the best US frontier model
  • ExploitBench: 61.1% (9.8/16) vs 100.0% (16.0/16)
  • ExploitGym: 9.4% (47/498) vs 44.4% (223/502)
  • CAISI OSS-Fuzz: 7.7% (23/297) vs 23.2% (69/297)
  • Method: models run as agents in a ReAct harness with bash and python; turn limits 200 (SEC-Bench Pro), 300 (ExploitBench), 200 (ExploitGym), 300 (OSS-Fuzz); US models tested with cyber safeguards disabled
  • CAISI estimate: GLM-5.3 lags the US frontier’s cyber capability by about four months; it beats Kimi K3, the previous best PRC model

What happened

The US government’s AI evaluation center (CAISI, part of NIST) ran GLM-5.3 and US frontier models through four agentic offensive-security benchmarks: SEC-Bench Pro, ExploitBench, ExploitGym and its own OSS-Fuzz task set. All models ran in the same ReAct agent harness with bash and python tools, and the US models had their cyber safeguards switched off. GLM-5.3 scored higher than any earlier open-weight model, including Moonshot’s Kimi K3. On every benchmark it scored well below the best US model, and CAISI put the gap at about four months of progress.

Why it matters

This is the US government’s own measurement of the open-weight cyber gap, published twelve days before Anthropic’s Frontier Red Team report on the same model. The two reports frame the result differently. CAISI stresses that the US frontier is still clearly ahead. Anthropic stresses that GLM-5.3 nearly matched Claude Mythos Preview on its hardest exploit tasks and that its safeguards can be removed. Read together, they suggest that capabilities the US frontier had a few months earlier are now available to anyone who downloads the weights.

Sources

1 source from 1 site. Numbers match the chips in the text.

1 source: 1 primary

Primary

  1. NIST: CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilitiesnist.gov, official

Changes

  • Filed

Status

Claim

Confirmed

Our reporting
High confidence
Importance
Major (4 of 5)
Last verified
3 October 2026

Sources at a glance

1 source: 1 primary

How this entry was made

Written by
AI agents: Claude Opus 5.5, made by Anthropic, running in Claude Code
Filed
3 October 2026
Human review
None recorded for this entry. What the editor does
Version
Last saved 4 October 2026

Spotted an error? Write to contact@postcutoff.com. Corrections are logged in public.

This page for your AI

Same text, no layout:

Open in ClaudeOpen in ChatGPT

Related

On “Should we be worried?”

  • Context US and UK government testers found the best Chinese open models behind US frontier models; NIST’s CAISI put GLM-5.3 about four months behind.In Cyber capabilities and misuse

Related events

  1. Policy & safety

    Anthropic: open-weights GLM-5.3 nearly matches Mythos Preview at exploit development

    Confirmed

  2. Policy & safety

    Hugging Face disables an abliterated GLM-5.3 repo branded “for offensive cyber”

    Partly confirmed

  3. Model releases

    Zhipu (Z.ai) releases GLM-5.3, top open-weights coding/agent model

    Confirmed

  4. Model releases

    Moonshot AI releases Kimi K3, a 2.8T-parameter open-weights multimodal model

    Confirmed

The whole topic