Measure How AI Thinks
KahneBench evaluates Large Language Models for cognitive biases using Kahneman-Tversky dual-process theory. Understand if your AI thinks like System 1 (fast, intuitive) or System 2 (slow, deliberate).
Comprehensive Coverage
KahneBench provides the most exhaustive evaluation of cognitive biases in LLMs, grounded in Nobel Prize-winning research.
Explore KahneBench
Everything you need to understand, evaluate, and improve LLM rationality.
6 Advanced Metrics
Beyond simple accuracy, KahneBench provides deep insights into how LLMs make decisions.
How strongly the model exhibits a bias
Cross-domain consistency of the bias
System 2 override capacity with debiasing prompts
How closely model biases match human patterns
Trial-to-trial variance (noise vs systematic bias)
Metacognitive accuracy (confidence vs actual performance)
Ready to evaluate your models?
Get started with KahneBench and discover the cognitive patterns in your LLMs. Understand their biases, measure their rationality, and build more trustworthy AI.