BC-Bench - Bug Fixing: leaderboard
BC-Bench (Microsoft, 2026) evaluates coding agents on 101 real tasks in AL, the language of Dynamics 365 Business Central, following the SWE-bench method. Bug fixing counts a task resolved when the patch builds and all evaluation tests pass; mean resolution rate over five runs in percent, higher is better.
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 February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 68.5 | #102 |
| 2 | Claude Opus 4.5 | 57.4 | #156 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=bc-bench-bug-fixing · How It Works · Data refreshed daily, snapshot 2026-11-13.