ViREx-Bench is an open-source benchmarking framework for evaluating inference-time scaling of large language models on Vietnamese logical reasoning tasks. It provides tools for researchers to assess and compare model performance in this domain.
ViREx-Bench is a LLM eval & observability project. It focuses on evaluating and benchmarking LLM inference-time scaling on Vietnamese logical reasoning tasks. It is built as an open-source project for AI researchers. The project is open source (GPL-3.0). ViREx-Bench is available on the command line.
Behind ViREx-Bench is minhnguyent546, and it first shipped in 2026. The project is developed in the open on GitHub with 210 commits in the last 90 days. Among its 5 catalogued features are benchmarking framework, inference-time scaling, and vietnamese reasoning tasks.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match