Z.ai's GLM 5.3 Flash scored 81.0% on the HTB-Challenger Benchmark, solving 15 of 16 Hack The Box challenges, second only to OpenAI's GPT-5.6 Sol at 87.2%. Despite requiring more steps (median 24.5 vs.…
New three-year benchmark data from Hack The Box (HTB) shows that 68% of the top 25 cybersecurity teams included an AI agent, despite AI agents accounting for just 2.7% of all participants. The 2026 Gl…
In the 2026 Global Cyber Skills Benchmark, human teams still outperformed AI-augmented teams on completeness, with the top human team solving all 36 challenges in the NeuroGrid CTF versus the best AI …
A case study combining OpenAI's GPT-5.6 Luna and GPT-5.6 Sol models achieved near-Sol performance at a fraction of the cost on the HTB-Challenger Benchmark, which tests LLMs on Hack The Box security c…
Z.ai's GLM 5.3, a retrained version of GLM 5.2, scored 47.2% on the HTB-Challenger Benchmark, solving 10 of 16 Hack The Box challenges with a median cost of $0.49 per challenge, placing it near Muse S…
The HTB-Challenger Benchmark evaluates large language models' ability to find and exploit security vulnerabilities using selected Hack The Box challenges of varying difficulty, according to the benchm…
Tencent's Hy3 scored 34.8% on the HTB-Challenger Benchmark, the third-lowest among all tested models, and got stuck on 9 of 16 Hack The Box challenges, generating a median of 101,509 output tokens per…
OpenAI's GPT-5.6 Terra and Sol models initially rejected security-related prompts from a researcher, but joining the Trusted Access for Cyber program resolved the issue, allowing testing of the full G…
OpenAI's GPT-5.6 Terra achieved a 64.6% benchmark score on the HTB-Challenger Benchmark, solving 12 of 16 Hack The Box challenges with a median cost of $0.24 per challenge and a total cost of $10.38. …
OpenAI's GPT-5.6 Sol achieved an 87.2% benchmark score on the HTB-Challenger Benchmark, solving 15 of 16 Hack The Box challenges with a median cost of $0.29 per challenge and a total cost of $11.82. T…
GPT-5.6 Terra Pro solved 14 of 16 Hack The Box challenges, achieving a benchmark score of 75.1% with a median cost of $0.91 per challenge, according to the HTB-Challenger Benchmark. The model solved a…
XAI's Grok 4.6 achieved an 80% benchmark score on the HTB-Challenger Benchmark, solving 14 of 16 Hack The Box challenges with zero false positives, surpassing all previously tested models in both spee…
DeepSeek V4 Pro solved 8 of 16 Hack The Box challenges in the HTB-Challenger Benchmark, scoring 36.2% with no false positives, but its median cost per challenge was $0.35, comparable to GPT-5.6 Luna d…
DeepSeek V4 Flash 0731 solved only 2 of 16 Hack The Box challenges, scoring 8.2% on the HTB-Challenger Benchmark, and reported incorrect flags in 9 challenges, a false-positive rate unmatched by any o…
Qwen3.8 Max, released by Alibaba Cloud, solved 10 of 16 Hack The Box challenges with a benchmark score of 54.8%, but its median cost per challenge was $2.00, making it the most expensive model tested …
OpenAI's GPT-5.6 Luna Pro solved 11 of 16 Hack The Box challenges, scoring 55.0% on the HTB-Challenger Benchmark, compared with GPT-5.6 Luna which solved only one Medium and no Hard challenges. The mo…
Hack The Box's new HTB-Challenger benchmark evaluates LLM models on offensive security challenges, addressing the high cost and comparability issues of existing methods. The benchmark, created by an a…
Hack The Box announced new capabilities for its cyber readiness platform, including crisis simulations, SOC training, and AI-augmented learning assistance, to help organizations identify skills gaps, …
A developer spent two semesters building A.E.G.I.S., an AI agent designed to automate penetration testing by proposing and executing security assessment commands on isolated virtual machines. After up…