Benchmark RadarAI BENCHMARK PROFILE
BehaviorBench
BehaviorBench evaluates personalized decision modeling from real-world behavioral traces, with belief and trade prediction tasks from prediction-market and on-chain records across 2,000 wallets.
- Released
- 2026-06-01
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Provides a real-world alternative to simulated user benchmarks, testing whether personalization methods can use observed behavioral evidence effectively in decision-support settings.
Motivation
Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.