Benchmark RadarAI BENCHMARK PROFILE
ELBench
ELBench is a benchmark for education-facing large language models, evaluating General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation under a common protocol with 2,939 items.
- Released
- 2026-08-10
- Readiness
- Inspectable
- Primary field
- General AI
Why it matters
It fills the gap of integrated evaluation for education-facing models, which require accuracy, safety, instructional usefulness, and pedagogical alignment simultaneously.
Motivation
Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.