BC-Bench - Bug Fixing: leaderboard

Metric: Mean resolution rate (%; mean over five runs; bug fixing: a task is resolved when the patch builds and every evaluation test passes; 101 manually curated Business Central (AL) tasks from two Microsoft production repositories; five independent runs per task, 30-minute timeout, agents see the AL code as plain text without the development environment; benchmark version as recorded per configuration (0.1.0 to 0.2.2)). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.668.5
2Claude Opus 4.557.4

Interactive version: theaggregate.ai/benchmark?slug=bc-bench-bug-fixing · How It Works · Data refreshed daily, snapshot 2026-09-29.