A new benchmark called SCDBench has been introduced to evaluate Large Language Models (LLMs) used for smart contract decompilation. The benchmark includes a dataset of 600 real-world Solidity contracts with paired bytecode, ground-truth source code, and semantic checkpoints. Current frontier LLMs like Claude Opus 4.7 and GPT-5.3-Codex show promise in generating structured and compilable code, but struggle with semantic consistency, with the best model only perfectly decompiling 42 contracts. The research also found that incorporating compilation repair significantly improves performance. AI
IMPACT Highlights limitations in LLM's ability to ensure semantic consistency in generated smart contracts, indicating a need for further research in this area.
RANK_REASON The cluster contains an academic paper introducing a new benchmark for evaluating LLM capabilities in a specific domain. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
