Unverified50% confidenceFactExact time
Evidence Core 的副标题为「Build live analytics with coding agents」
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/28/2026
First Seen
Valid until: 11/26/2026
Sources
Related Entities
Related Claims
UnverifiedLive Code Bench uses the latest competition problems with real-time updates to evaluate programming ability, in order to prevent data contamination69% similarVerifiedThe training data sources for specialized programming models include open-source code from GitHub, competitive programming solutions, technical documentation, and code review records, and the models are optimized for benchmarks such as HumanEval, MBPP, and SWE-bench.67% similarVerifiedMainstream benchmarks for evaluating programming large models include HumanEval, MBPP, SWE-bench, and LiveCodeBench64% similarVerifiedLiveCodeBench introduces a timestamp filtering strategy that selects problems published after a model's training cutoff date to ensure that the evaluation data is entirely new to the model being tested.61% similarUnverified2023年发表的论文如Extracting Training Data from ChatGPT证明，通过精心构造的查询序列，攻击者可以从模型中提取训练数据的逐字片段61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810775API
curl https://kongchang.com/api/v1/knowledge/claims/810775MCP
get_claim(id=810775)