LoopArena Benchmark
Explore score history ↗Evaluates a controller model guiding a fixed coding agent through long-running tasks, scored via contract accuracy, strict success rate, and cost metrics across three complementary settings.
- Released
- 2026-08-28
- Institutions
- Alibaba Group (China) · Commonwealth Scientific and Industrial Research Organisation · Beijing University of Posts and Telecommunications
- Evaluates
- Agents, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
LoopArena paper and code
No reported scores are on record for this benchmark yet.