Companies
5 synchronized stories carry this tag.
The updated benchmark contains 2,967 question-context-answer triplets from 495 international annual reports and expands testing from 11 to 20 models; retrieval caused 48.9% of reported failures.
Why it matters: The results suggest that finding the correct evidence remains a larger weakness than interpreting it, even as open-weight models approach proprietary systems on the bounded task.
CryptanalysisBench packages 191 tasks across six cryptographic primitive families and three difficulty tiers. Five frontier models solved 65–86% of known-break tasks and reportedly found previously unknown issues in SpoC and KINDI.
Why it matters: Cryptanalysis is a rare reasoning domain where candidate outputs can often be checked mechanically, making it useful for measuring both capability and emerging security risk.
Zhipu released GLM-5.2 weights and technical material focused on sustained coding, research and tool-use workloads with longer execution horizons.
Why it matters: Open long-horizon models give teams another controllable backend for testing whether persistence comes from weights, context management or harness design.
The MOSAIC-Bench preprint introduces 199 three-stage attack chains with deterministic exploit checks across 10 web applications, 31 weakness classes and five languages. Its authors report 53%-86% end-to-end attack success across nine coding agents and say reviewer agents approved 25.8% of confirmed-vulnerable cumulative changes.
Why it matters: Per-prompt safety can fail when individually normal requests combine into a malicious final state; review must consider the cumulative diff and intended system behavior.
Zhipu AI released GLM-5 as an open model focused on coding and long-running agent tasks, with a 744-billion-parameter mixture-of-experts design and 40 billion active parameters described in its later technical report. Reuters reported that the model was adapted for inference on several Chinese chip platforms, including Huawei Ascend, amid tighter access to advanced United States chips.
Why it matters: GLM-5 offered developers an inspectable frontier-scale agent model and demonstrated that serious long-horizon systems were being co-designed for non-NVIDIA hardware ecosystems.