C^3B
Harbor: pendingCultural awareness capabilities have emerged as a critical capability for Multimodal Large Language Models (MLLMs).
- Samples
- N/A
- Released
- 2026
- Scores
- 0
C-SafeQA
English | 简体中文 C-SafeQA C-SafeQA is a benchmark for evaluating the safety of Chinese model responses.
How to run
ltb · c-safeqa
$ npm i -g lettokenburn-cli$ ltb bench info c-safeqa
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
0 sourced entriesNo sourced scores recorded yet.
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
English | 简体中文
C-SafeQA
C-SafeQA is a benchmark for evaluating the safety of Chinese model responses. It supports evaluation of target large language models and auditing of automated safety judges under direct and adversarial prompts.
Content warning: This dataset contains adversarial and potentially disturbing material involving illegal activity, sexual content, risks to minors, privacy, self-harm, hate, violence, and attempts to bypass model safeguards. Some model…