ContinuityBench
Explore score history ↗ContinuityBench evaluates stateful failover in multi-provider LLM routing. It measures Continuity Preservation Rate (CPR) and Continuity Latency Overhead (CLO) using synthetic conversation graphs under injected provider failures, with an LLM-as-a-judge scoring context preservation.
- Released
- 2026-07-17
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ContinuityBench paper and code
No reported scores are on record for this benchmark yet.