MOSAIC-Bench demonstrates that nine production coding agents achieve 53-86% end-to-end attack success rates on staged innocuous tickets across 10 web substrates and 31 CWE classes, far higher than the 0-20.4% rates seen with direct prompts.
Baxbench: Can llms generate correct and secure backends?arXiv preprint arXiv:2502.11844
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RubberDuckBench shows top AI models score around 68% on real GitHub coding questions, rarely answer completely correctly, and hallucinate in 58% of responses on average.
citing papers explorer
-
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
MOSAIC-Bench demonstrates that nine production coding agents achieve 53-86% end-to-end attack success rates on staged innocuous tickets across 10 web substrates and 31 CWE classes, far higher than the 0-20.4% rates seen with direct prompts.
-
RubberDuckBench: A Benchmark for AI Coding Assistants
RubberDuckBench shows top AI models score around 68% on real GitHub coding questions, rarely answer completely correctly, and hallucinate in 58% of responses on average.