Benchmark RadarAI BENCHMARK PROFILE
BehaviorBench
Evaluates foundation models on four behavioral science capabilities: behavior prediction and simulation, strategic decision-making, subject-trait inference, and behavioral knowledge application, assessing both individual-level and distributional alignment.
- Released
- 2026-06-23
- Readiness
- Inspectable
- Primary field
- General AI
Why it matters
Addresses the lack of systematic evaluation of foundation models in behavioral science, providing a standardized benchmark that captures population-level validity, helping researchers and practitioners choose models for behavioral simulation and analysis.
Motivation
Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.