PulseAugur
EN
LIVE 20:27:16

New SCDBench benchmark reveals LLM struggles with smart contract decompilation

By PulseAugur Editorial · [1 sources] ·

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]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New SCDBench benchmark reveals LLM struggles with smart contract decompilation

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
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]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
120 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Kaihua Qin, Dawn Song, Arthur Gervais ·

    SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers

    arXiv:2605.29059v1 Announce Type: cross Abstract: Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studies use narrow datasets, inconsistent metrics, and limited semantic consistency c…

RELATED ENTITIES

RELATED TOPICS