Unverified50% confidenceFactExact time
The National University of Singapore and Alibaba (including the Qwen team) jointly submitted the LSCBench benchmark, containing 150 real vulnerabilities covering 7 languages and 24 CWE categories.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedStandard AI benchmarks include MMLU (a comprehensive knowledge test covering 57 subjects), GPQA (graduate-level professional question answering), SWE-bench (real-world software engineering tasks), HumanEval and MBPP (programming ability), and MATH and GSM8K (mathematical reasoning)61% similarUnverifiedThe benchmark was designed with 40 requests across 6 categories, covering faithfulness, unit conversion, multilingual (Bengali, Hindi), injection attacks, out-of-scope, and ambiguous input.60% similarUnverifiedCommonly used benchmarks for evaluating large language model capabilities include MMLU, HumanEval, MATH, and GPQA.60% similarUnverified在沙盒物理模拟测试中，Qwen3 27B主动编写测试脚本进行26项断言检查，反复验证直到10/10全部通过60% similarUnverifiedThe benchmark tested 18 models from six labs in a single run, covering Anthropic, OpenAI, Google, DeepSeek, Qwen, and GLM.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047280API
curl https://kongchang.com/api/v1/knowledge/claims/1047280MCP
get_claim(id=1047280)