SCDBench (Compilation Repair): leaderboard

Metric: Semantically consistent public functions (%; all replayed test cases match return data, revert status, logs and storage, of 14,553 functions in 600 contracts, after one same-model repair attempt from compiler errors). Source: arxiv.org. Saturation forecast: Around September 2028. 4 models tracked.

Top models

#ModelScore
1Claude Opus 4.7 (High)29.44
2GLM-5 (Thinking)20.72
3GLM-5 (Non-reasoning)17.66

Interactive version: theaggregate.ai/benchmark?slug=scdbench-compilation-repair · How It Works · Data refreshed daily, snapshot 2026-09-26.