- Status
- partly answered As of 2026-10-01
- Addressee
- AI labsevaluators (Addressees taken from the question text, determined with Clef (Cloudflare) on 22 Oct 2026)
- Model
- DeepSeek V4.1 Flash
- Lab
- DeepSeek
- Occasion
- article by Chen Yixin
- Date
- 13–17 Sept
- Topic
- Cyber
What the sources say
On 3 September 2026, OpenAI named four public cyber benchmarks—ExploitBench, ExploitGym, SEC-Bench Pro and SRE-Bench—and two internal evaluations, Sandbox Bench and ExploitBench - Internal Port (June – August 2026), which refreshes ExploitBench with more recently disclosed vulnerabilities; the full methods, failure rates and tested model version needed for reproduction remain open.[1]
- OpenAI: GPT-6 Astra System Card ↗2026-09-03
Summarised by Sol 6.1, checked by Claude Opus 5.5
Touched in Liz's Atlas:
- Capabilities are Difficult to Estimate and Understand ↗Threat: Open problem · Trend: → steady · Evidence: contested
Checked
Status: Claude Sonnet 5 (research, effort high), Claude Opus 5.5 (check, effort high)
Scores: JEV (TypeSafe), estimate of 25 Sept 2026
Cite and take away
Cite and reuse
Own texts, questions and classifications: CC BY 4.0. Give attribution, link the license and indicate changes. Third-party source reports retain their own rights. CC BY 4.0
AMANi DUNiA. cyber-08 · What cyber-capability evidence should a lab publish before release — methods, task familie. Snapshot: . https://research.amanidunia.berlin/en/fragen/cyber-08/
Version: cyber-08
BibTeX
@misc{research__en_fragen_cyber_08_,
author = {{AMANi DUNiA}},
title = {cyber-08 · What cyber-capability evidence should a lab publish before release — methods, task familie},
year = {2026},
url = {https://research.amanidunia.berlin/en/fragen/cyber-08/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {cyber-08}
}Language and review status
Main text: EN. Review notes apply only to the content they name.
Existing review notes appear with the respective content.
See language coverage and data snapshot →