BugSourceBench
Explore score history ↗The work introduces BugSourceBench, a code repair benchmark with bugs from human-written, LM-generated, and human-edited LM-generated code. The benchmark evaluates the fix rate of language models on these bug sources. No scoring contract, dataset, or public access path is provided.
- Released
- 2026-07-03
- Evaluates
- Code & Software, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
BugSourceBench paper
No reported scores are on record for this benchmark yet.