AI BENCHMARK PROFILE
LiveK12Bench
Dynamic benchmark for multimodal reasoning on high school exam questions in math, physics, chemistry, and biology, with a mock exam evaluation scheme.
- Released
- 2026-05-26
- Readiness
- Paper only
- Primary field
- Science & Research
Why it matters
Static benchmarks are prone to contamination and fail to reflect real exam constraints. LiveK12Bench provides a growing, realistic evaluation for educational readiness.
Motivation
Advanced Large Multimodal Models (LMMs) have demonstrated impressive performance in K-12 reasoning tasks, exhibiting great promise as intelligent tutors.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.