Credit scoring is critical to mortgage lending. It helps lenders decide who qualifies for a mortgage and on what terms. For decades, the government-sponsored enterprises (GSEs) have relied on Classic FICO scores. In October 2022, to modernize credit scoring and to promote competition, the Federal Housing Finance Agency (FHFA) announced the validation and approval of two new credit score models for use by the GSEs Fannie Mae and Freddie Mac: (1) FICO 10T, an updated version of Classic FICO, and (2) VantageScore 4.0, a model developed by VantageScore Solutions. Implementation has been phased in; loans can now be delivered to the GSEs using either Classic FICO or VantageScore 4.0. Data were recently released on FICO 10T, allowing market participants to compare FICO 10T with Classic FICO and VantageScore 4.0. In this brief, we show the results of this comparison.

Key Takeaways

• FICO 10T and VantageScore 4.0 have similar score distributions and average score levels within this sample. Both average about 13 points above Classic FICO, and they are within roughly 1 point of each other.
• Both FICO 10T and VantageScore 4.0 place more borrowers in the top score band. About 31 percent of loans score 800 or above under FICO 10T or VantageScore 4.0, versus 14 percent of loans under Classic FICO.
• All three models rank-order default risk well. FICO 10T captures the largest share of defaults in the riskiest decile, followed by VantageScore 4.0 and then Classic FICO.
• Within each model, using the average of the borrower’s scores performs better than using the lower of the borrower’s scores.
• We retested the results using different definitions of default risk, and the rank ordering was consistent. Our base definition of default is ever being 90 days or more delinquent. We retested using two alternative definitions of default: 90 or more days delinquent in the first two years and 90 or more days delinquent in the first three years.
• We retested these results in a stress environment (2020–21) and found that these rank orderings hold in stress periods as well as in normal periods.

How We Did It

We use the Fannie Mae Single-Family Loan Performance database December 2025 refresh, merged by loan identifier with FHFA and Fannie Mae historical score files for FICO 10T and VantageScore 4.0. Those files provide the two new scores for loans originated from 2013 through the third quarter of 2025. The Classic FICO score is taken from the loan file. The analysis sample is about 27.5 million loans on both new scores with a Classic FICO score present, with performance observed through December 2025.
 

This brief was supported by the Housing Finance Innovation Forum (HFIF), a group of organizations and individuals that support high-quality independent research that informs evidence-based policy development. We are grateful to them and to all our funders, who make it possible for Urban to advance its mission.

The views expressed are those of the authors and should not be attributed to the Urban Institute, its trustees, or its funders. Funders do not determine research findings or the insights and recommendations of Urban experts. Further information on the Urban Institute’s funding principles is available at urban.org/fundingprinciples.

Before publication, this analysis was shared for review and feedback with VantageScore Solutions, which is not an HFIF member, and FICO, which is an HFIF member. Urban retained full editorial independence and final discretion over the publication’s content, findings, and conclusions.