DeepSeek v4.1 Flash Is Now Our Best Hacking Model
DeepSeek V4.1 Flash achieves 11/11 code executions on Enclave's AI hacking benchmark for $4.65 across Grafana, Jenkins, and Nextcloud targets.
Enclave AI reports DeepSeek V4.1 Flash gained code execution on all 11 vulnerable targets while all four fixed controls held, costing $4.65 accepted ($5.14 total) with 268.3 million mostly cached input tokens. A path-level audit found six runs used the planned weaknesses, such as Jenkins credential-file abuse and a Nextcloud access-control confusion, while five runs exploited alternate routes in the Grafana and Jenkins test environments. The benchmark was hardened to check attack paths, not just outcomes, underscoring that hacking agents find the fastest exploitable route.
- Perfect 11/11 score at $4.65 using cached-token pricing
- Model exploited Grafana plugin loading, Jenkins credential exposure, upload race, and Nextcloud access control
- Median successful run took 4 minutes 38 seconds over 2,349 Bash commands
- Audit found five alternate attack paths the original scoring missed
- Benchmark updated with stricter path-level checks
- Organizations
- Enclave AI
- AI models
- DeepSeek V4.1 Flash
From the original article
4 min read at enclave.ai
DeepSeek V4. 1 Flash produced an extraordinary result in our AI hacking benchmark. It gained code execution on all 11 vulnerable targets, while all four fixed targets remained secure.
By talhof8 · enclave.ai
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.