Kaggle launches Human Behavior Bench for predicting human decisions
A 94.1% score above the human noise ceiling suggests behavioural-simulation systems like Engram 1.0 can outperform frontier LLMs at modelling subgroups, not just answer questions. Product and research teams building personalisation, market research or user modelling tools now have a public baseline to test against. The 601 private cases make leaderboard gaming harder, so results should hold up better than fully public benchmarks.
Kaggle and RunRehearsals launched Human Behavior Bench, a public benchmark testing whether AI models can predict real human preferences and everyday decisions. The benchmark is built on surveys of 1,244 US adults collected between June and September 2026, with cohorts ranging from traditional demographics like age, income and location to behavioural groups such as GLP-1 patients and recent car buyers. It contains 750 cases (149 public, 601 private) spanning finance, health, recreation, values and consumption, scored using 1-TVD. Against a human noise ceiling of about 93, Rehearsals' Engram 1.0 (AI Twins) leads at 94.1%, ahead of Gemini 4 Argon at 80.6%, Claude Opus 5 at 80.2% and GPT-5.6 Sol at 79.5%. The organisers note that LLM predictions tend to converge toward the mean while real human preference distributions vary widely.
Can frontier models actually predict how real people behave? 🕺
Today, in collaboration with @RunRehearsals, we are launching Human Behavior Bench, the first public benchmark that tests whether AI can understand human preference and everyday decision-making.
AI models have gotten increasingly good at coding, but knowing for whom to build is the next frontier of challenges for AI models to capture. Human Behavior Bench evaluates models on predicting real human behavior across health, entertainment, recreation, values, and consumption.
To build this baseline, we gathered ground truth data directly from real people and evaluated models across a wide range of everyday scenarios:
• Ground truth baseline: 1,244 US adults surveyed (June-Sept 2026) • Some cohorts are traditional demographic indicators such as age, income, and location • Other filters are behavioral e.g. GLP-1 patients and recent car buyers • 750 cases total (149 public / 601 private) across finance, health, recreation, values, and consumption • Scored using 1-TVD (total variation distance)
Base models still have a significant gap to close to accurately predict human behavior by cohort. LLMs’ predictions tend to converge towards the mean, while the true distribution of human preferences vary greatly.
Against a human noise ceiling of ~93, the current leaderboard scores are: Rehearsals’ Engram 1.0 (AI Twins) tops the leaderboard at 94.1%, followed by Gemini 4 Argon at 80.6% Claude Opus 5 at 80.2%, GPT-5.6 Sol at 79.5%.
