Benchmark RadarSDR-Bench
SDR-Bench evaluates LLM personalization in a two-party framework. It includes 6,279 customer success stories across 22 industries and ~200 enterprises, with a temporally constrained simulation to prevent data leakage. Scoring compares model-generated outreach against human outcomes.
- Released
- 2026-05-23
- Readiness
- Paper only
- Primary field
- Transport & Logistics
Why it matters
SDR-Bench addresses the gap in evaluating LLM personalization as a two-party problem, where generated messages must induce action in a third party. It provides a reproducible public benchmark for comparing model performance on this task, with validation against field deployment.
Motivation
Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradition in psychology and marketing as a two-party problem in which sender and receiver have independent objectives.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.