Unverified50% confidenceBenchmarkExact time
The developer used Thingi10K dataset samples as well as specially constructed adversarial malformed inputs to conduct robustness testing on Sutura.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/29/2026
First Seen
Valid until: 11/27/2026
Sources
Related Entities
Related Claims
UnverifiedThe benchmark was built by the developer of SERPdive, whose product accounts for 3 of the 13 configurations in this test.71% similarUnverifiedSWE-bench Verified is one of the authoritative industry leaderboards for AI programming ability, with human annotators filtering out samples with ambiguous descriptions or unstable tests.64% similarUnverifiedMutation Testing checks whether test cases are truly effective by deliberately introducing defects into the code.64% similarUnverifiedBenchLocal的测试维度包括工具调用、命令行操作、Bug识别修复、指令遵循、Hermes Agent、结构化输出、数学推理、数据提取共8大类63% similarUnverified该实验的核心方法是冻结Prompt、Model config、Tool schema、Trace四个关键要素以实现可复现的回归检测61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/820894API
curl https://kongchang.com/api/v1/knowledge/claims/820894MCP
get_claim(id=820894)