Benchmark
DEPBENCH
What is DEPBENCH?
Evaluates coding agents on 203 real-world dependency-upgrade tasks requiring source adaptation, scored by task completion rate.
- Released
- 2026-08-31
- Evaluates
- Code & Software, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2608.30300
DEPBENCH paper
No reported scores are on record for this benchmark yet.