The following link may contain information concerning investments, products or other information. Intelligent Alpha LLC is not responsible for the accuracy or completeness of information on non-affiliated websites and does not make any representation regarding the advisability of investing in any investment fund or other investment product or vehicle. Importantly, Intelligent Alpha LLC is not compensated for linking you to any non-affiliated website and instead is only compensated with an asset-based fee in the limited capacities as either a licensor of intellectual property or a sub-adviser to an investment adviser. The material available on non-affiliated websites has been produced by entities that are not affiliated with Intelligent Alpha LLC. Descriptions of, references to, or links to products or publications within any non-affiliated linked website does not imply endorsement or recommendation of that product or publication by Intelligent Alpha LLC. Any opinions or recommendations from non-affiliated websites are solely those of the independent providers and are not the opinions or recommendations of Intelligent Alpha LLC which is not responsible for any inaccuracies or errors.
THIS INFORMATION IS NOT AN OFFER TO BUY OR A SOLICITATION TO SELL ANY SECURITY OR INVESTMENT PRODUCT. SUCH AN OFFER OR SOLICITATION IS MADE ONLY BY THE SECURITIES' OR INVESTMENT PRODUCTS' ISSUER OR SPONSOR THROUGH A PROSPECTUS OR OTHER OFFERING
We test the world's most powerful AI models on the hardest question in equity research: predicting where forward earnings expectations will be revised before the market reprices. Same data. Same task. Frontier models only. Measured against reality.
Frontier models only, ranked by combined direction accuracy (revenue + EPS). Click any model for detailed predictions and search behavior analysis. Direction and magnitude accuracy will update late in the current quarter.
"The ability to predict the future is the best measure of intelligence."
— Elon Musk
Thank you for subscribing! You'll hear from us soon.
Something went wrong. Please try again.
METHODOLOGY
How the Benchmark Works
The IEB tests whether frontier AI models can predict where the market's forward earnings expectations are too high or too low. Each model receives identical company data and is asked to predict the direction and magnitude of forward estimate revisions over the following 8–10 weeks.
Data Provided
8 quarters of income statements and balance sheets, 12 quarters of earnings surprise history, the most recent earnings call transcript, current consensus estimates, and 8 quarters of historical consensus revision data.
Tools Available
All models share access to historical financial data, Exa web search with a query limit, FRED economic data and a calculation tool. All models also receive the same directions and base rate details.
What Models Predict
Revenue and EPS revision direction (up, down, flat), magnitude (small, medium, large), an implied revision percentage, confidence score, key signals, and overall rationale.
Scoring
Predictions are scored against realized consensus changes measured 8–10 weeks after the prediction deadline. Direction accuracy measures whether the model called the right direction. Magnitude accuracy measures whether it sized the move correctly.
Universe
All US-listed domestic common equities with market cap above $10B, excluding ADRs, SPACs, and ETFs. Approximately ~700 stocks in Q2 2026. Universe is frozen at each quarterly prediction deadline and re-screened quarterly.
Auditability
Every run is logged for the entire universe with the prompt submitted, data packets, and search history. Model version strings and tool call logs are preserved. Scoring can be verified on stored predictions against updated consensus data after the scoring period.
Disclaimer: The Intelligent Earnings Benchmark (IEB) is an experimental, AI-generated financial benchmark developed by Intelligent Alpha for educational and informational purposes only. The IEB is not a financial product, investment vehicle, index fund, or investable strategy. It does not represent a recommendation to buy, sell, or hold any security. No assets are managed according to the IEB, and it should not be used as the sole basis for any investment decision.
The benchmark reflects hypothetical, backtested, and/or forward-looking results generated by AI models. These results are based on model predictions of revenue and earnings direction and magnitude for companies in the S&P 500. The IEB does not reflect actual portfolio performance, real-world trading, transaction costs, slippage, taxes, or other factors that would affect returns in practice. Hypothetical results have inherent limitations and should not be interpreted as indicative of future performance.
AI-generated predictions are inherently uncertain and may be inaccurate. Past performance, whether actual or simulated, is not indicative of future results. The models used to generate the IEB may change over time without notice, and Intelligent Alpha makes no representation or warranty regarding the accuracy, reliability, or completeness of any information provided.
Nothing on this page constitutes investment advice, tax advice, legal advice, or a solicitation to invest. Intelligent Alpha is not a registered investment adviser, broker-dealer, or financial planner. Users should consult a qualified financial professional before making investment decisions. By accessing this content, you acknowledge that you understand these limitations and agree not to rely on the IEB for investment purposes.
INSTITUTIONAL ACCESS
Full Dataset Available for Licensing
Access predictions for all 715 stocks across every model, including rationales, confidence scores, magnitude scores, and historical accuracy data. Available for research, asset management, and integration into investment workflows. Contact us.
Thank you for subscribing! You'll hear from us soon.
.svg)
