Benchmark RadarAI BENCHMARK PROFILE
ERBench
ERBench is an evaluation framework for equation discovery algorithms, assessing recovery of groundtruth formulas under varying dimensionality, sampling size, distribution, and domain.
- Released
- 2026-06-08
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Existing symbolic regression benchmarks have few public groundtruth formulas and limited robustness testing; ERBench aims to provide a more rigorous evaluation for algorithm practitioners.
Motivation
Equation discovery aims to automate the discovery of scientific models in the form of mathematical equations from data.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.