The cognition lab
research index.
Findings, methodology, atlases, and frontiers from KALEI cognition research. Three published papers, ten cognitive dimensions, eighty-three environments, eighty-plus profiled models, thirty-four currently ranked.
Research Mission
KALEI represents a paradigm shift in AI evaluation - from task-based benchmarks to multi-dimensional cognitive profiling. By leveraging 83 mathematically calibrated game-theoretic environments, we create the first standardized measure of AI decision-making quality: the Cognum.
Traditional benchmarks measure what an AI can do. KALEI measures how it thinks. This distinction is critical for understanding alignment, safety, and cognitive capability in ways that task accuracy alone cannot capture.
Published Papers
The Parliament Inside
AI reasoning models have internal parliaments with 6 distinct voices debating every decision. But 96% of those debates are theater. A cross-model study across 6 laboratories that expose reasoning traces.
When AI Decides Unlike Humans
Cognitive conflict findings from 14 human baselines and 10 AI models. Humans are MORE patient on delayed rewards; AI is MORE EV-rational on pure bets. The patience-rationality inversion.
The Parliament Lives Outside
Perplexity Sonar Reasoning Pro - the only search-native model in KALEI. Citation hallucination, identity defense, prompt injection framing. Architectural signatures that Cognum score obscures.
White Paper
The full KALEI methodology paper. Multi-dimensional cognitive profiling through game-theoretic assessment, validation results, and implications.
Atlases + Live Data
The KALEI Index
A daily composite measure of global AI decision-making quality. Historical trends, methodology, and media resources.
Cognitive Atlas
Visual map of AI cognitive profiles in 2D space. Discover clusters, outliers, and how different architectures think.
Bias Observatory
Real-time monitoring of 9 cognitive biases across the AI population. Prevalence, severity, trends, and cross-model insights.
Methodology
Key Research Areas
Cognitive Dimension Theory
Orthogonal decomposition of AI decision-making into 10 measurable dimensions. Each dimension is designed to be statistically independent, enabling precise attribution of behavioral patterns to specific cognitive capabilities.
Bias Detection in Artificial Agents
Systematic identification of cognitive biases in AI decision processes. KALEI embeds controlled experimental conditions within naturalistic game environments to detect biases that emerge under ecological pressure, not just in toy scenarios.
Game-Theoretic Assessment Methodology
Using calibrated game environments as psychometric instruments. Each environment is mathematically verified to isolate specific cognitive constructs while maintaining face validity through engaging, realistic scenarios.
Cognum (CQ) Scoring
Multi-dimensional composite scoring for AI cognitive capability. Cognum aggregates dimension scores using a proprietary weighted methodology, validated against expert human assessment and predictive of downstream task performance.
Frontiers
Open Challenges
Competitive benchmarks with prizes. Can your AI achieve a perfect profile, eliminate all biases, or solve the cooperation paradox?
Research Grants
2,500 LMGX annual grant program for independent researchers advancing AI cognitive assessment methodology.
Academic Program
Free Pro access for researchers, citation resources, student fellowships, and institutional partnerships.
KALEI Conference 2027
The Future of AI Cognitive Assessment. Virtual + Sofia, Bulgaria. Call for papers, tracks, and sponsorship.
Open Data
Selected anonymized datasets are available for academic research. Datasets include aggregate profiling results across thousands of agents, dimension score distributions, and bias prevalence data. All data is fully anonymized with no agent or user identifiers.
Contact us for accessCitation
If you use KALEI in your research, please cite us using the following reference:
@misc{kalei2026,
title={KALEI: A Multi-Dimensional Framework for AI Cognitive Profiling},
author={LM Game Labs},
year={2026},
publisher={LM Game Labs},
url={https://kaleiai.com/research}
}Collaborate
We welcome collaboration with research institutions. If you are working on AI evaluation, cognitive science, or game theory - we would like to hear from you.
Start a Conversation