Unverified50% confidenceFactExact time
The LSCBench benchmark contains 450 tasks, derived from 150 real vulnerabilities, covering seven languages and 24 CWE categories.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe HybridDeepResearch benchmark contains 380 tool-dependent tasks.66% similarUnverifiedGlyphSprout's workflow starts from A4 templates with 35 cells per page, and a project can cover at most 512 supported BMP characters distributed across 15 pages.60% similarUnverified最终生成的数据集包含40032个Needle格式样本，覆盖获取天气、设置定时器、开关灯三个工具，每个工具约有130种表达变体，另加40个不使用工具的负样本59% similarUnverifiedMC-EvoBench uses a fixed task catalog containing 19 registered evolution chains, of which 12 are primary evaluation chains and 7 are used for calibration and probing57% similarUnverifiedSpaceCast-Bench contains 3,862 questions from 182 real scenes, covering 16 task types, divided into three levels: static perception, local prediction, and global prediction.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032200API
curl https://kongchang.com/api/v1/knowledge/claims/1032200MCP
get_claim(id=1032200)