Unverified50% confidenceFactExact time
LLST's capability test uses a fixed set of 102 prompt samples, covering five dimensions: knowledge reasoning, instruction following, advanced mathematics, Chinese language ability, and code generation.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLST (Local Large Model Standard Test) is an open-source standardized local large model testing tool consisting of two components: a capability benchmark and a gradient stress test.69% similarUnverified评估大语言模型推理可靠性的系统化基准测试包括GSM8K、MATH竞赛题集和BIG-Bench Hard64% similarUnverified对于需要审查完整轨迹的复杂Skill，可以引入LLM as a Judge配合评分标准（rubric）来判断通过或失败64% similarUnverifiedCommon implementation approaches for LLM semantic-level assertions include rule-based checkers, embedding vector cosine similarity thresholds (e.g., 0.85), LLM-as-judge scoring, and NLI model-based factual consistency verification.64% similarUnverifiedQoder CN scored 90 points in a programming capability test and answered all 5 questions correctly in a reasoning capability test.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930276API
curl https://kongchang.com/api/v1/knowledge/claims/930276MCP
get_claim(id=930276)