# Vals finds Chinese open AI model nearly matches OpenAI’s hacking model in tests

Digest AI · Policy & Regulation · published 2026-11-06T18:43:43Z

Canonical: https://digestai.news/story/vals-finds-chinese-open-ai-model-nearly-matches-openais-hacking-model

## Summary

Vals, a company that benchmarks AI capabilities, tested how well different models could execute complex, multi-step network attacks on simulated corporate networks. The results suggest open-weight models—like DeepSeek—are closing the gap with proprietary ones, such as OpenAI’s Daybreak, which remains the most capable but costs significantly more to run.

In two scenarios, Daybreak completed 81% of tasks on average, while DeepSeek achieved 73%. Vals notes open models like DeepSeek cost $2–$3 in tokens per attack versus $17–$46 for Daybreak. The findings challenge assumptions that gated access to frontier models could delay the spread of advanced hacking tools. Experts debate whether AI fundamentally alters cybersecurity or accelerates existing threats, though attackers still favor older models for cost efficiency. Some warn unreleased closed models may surpass open-weight capabilities, creating an ongoing arms race.

## Key points

- Vals tested two simulated scenarios: a public-facing network and a multi-step compromise task
- OpenAI’s Daybreak model scored 81% task completion, DeepSeek 73%, with open models cheaper to run
- Experts warn closed labs may have unreleased models exceeding open-weight capabilities, prolonging the cat-and-mouse game

## Why it matters

Open models matching proprietary ones in hacking capability accelerates risks for defenders and raises questions about the sustainability of access controls.

## Sources

1. [Free Chinese AI Models Are Getting Scary Good at Hacking](https://wired.com/story/free-chinese-ai-models-are-getting-scary-good-at-hacking) (Wired AI, 2026-11-06)

Part of the developing story: [AI Model Surge Meets Security Crisis](https://digestai.news/thread/typesafe-ai-releases-jev-1-14-with-images-box-type-and-262k-token-context) (6 stories)

## Cite

Digest AI, "Vals finds Chinese open AI model nearly matches OpenAI’s hacking model in tests", 6 November 2026, https://digestai.news/story/vals-finds-chinese-open-ai-model-nearly-matches-openais-hacking-model

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/vals-finds-chinese-open-ai-model-nearly-matches-openais-hacking-model.json