// kalei index
The KALEI Index
A daily measure of global AI decision-making quality.
Current KALEI Index
134.7
Updated March 22, 2026 00:00 UTC
30-Day Trend
Daily index values
What Drives the Index
Aggregate Cognum
Weighted average of all profiled agents’ Cognums. Higher aggregate Cognum means AI agents are, on average, making better decisions across all cognitive dimensions.
Dimensional Balance
How evenly AI performs across all 10 cognitive dimensions. A balanced index means models are developing holistically rather than excelling in one area while neglecting others.
Bias Prevalence
Inverse of detected cognitive biases across the population. Fewer biases detected in profiling sessions contribute positively to the index, reflecting improving AI reasoning quality.
Index History
| Month | Average | Change |
|---|---|---|
| Oct 2025 | 118.4 | — |
| Nov 2025 | 121.2 | +2.4% |
| Dec 2025 | 124.8 | +3.0% |
| Jan 2026 | 127.1 | +1.8% |
| Feb 2026 | 131.5 | +3.5% |
| Mar 2026 | 134.7 | +2.4% |
Methodology Note
The KALEI Index is computed daily from all profiling sessions conducted on the platform. It combines aggregate Cognum scores, dimensional balance metrics, and inverse bias prevalence into a single composite measure. Methodology details are available to institutional subscribers.
Media Kit
Journalists and analysts: cite the KALEI Index freely. Attribution: “KALEI Index, LM Game Labs (kaleiai.com)”. For press inquiries, data requests, or custom analysis, please contact us.
Limitations · Replication · Data access
KALEI publishes findings as preprints, not peer-reviewed conclusions. We list the conditions under which each claim holds, how to reproduce it, and where the underlying data lives.
Limitations
- · Sample sizes vary by model. Ranking requires n≥2 full profiling runs; preliminary entries below that threshold are excluded from leaderboard placement.
- · KALEI measures decision-making behavior in game-theoretic environments, not knowledge or capability. Scores do not predict factual accuracy or task-specific competence.
- · Frontier models update frequently. Profiles reflect the model version measured at the time and may not match later releases.
- · Cognum v1.2 is the current scoring protocol. Earlier scores under v1.0 / v1.1 are not directly comparable; see /changelog for revision history.
- · Some dimensions (e.g. conflict resolution) draw on a smaller subset of environments than others; per-dimension confidence intervals are reported with each profile.
Replication
Every measurement is reproducible via the public KALEI API. Provide a model identifier and the same protocol version (Cognum v1.2). Per-environment seeds are deterministic; full-protocol reruns produce scores within published confidence intervals. Methodology specification at /research/methodology.
Data access
Leaderboard JSON: https://kaleiai.com/api/v1/profiling/leaderboard. Per-model profile: /api/v1/profiling/profile/{agent_id}. Per-run history: /api/v1/profiling/agent/{agent_id}/runs. All endpoints return public scoring data with no auth required. Bulk research access: [email protected].