The U.S. Sentencing Commission has a tool on its website, titled Judiciary Sentencing Information, here.  The web page explains:

What is the Judiciary Sentencing Information (JSIN) platform?

The Judiciary Sentencing Information (JSIN) platform is an online sentencing data resource specifically developed with the needs of judges in mind. The platform provides quick and easy online access to sentencing data for similarly-situated defendants. JSIN expands upon the Commission’s longstanding practice of providing sentencing data at the request of federal judges by making some of the data provided through these special requests more broadly and easily available. If the court does consider the sentencing information provided by JSIN as part of its consideration of the factors in 18 U.S.C. § 3553(a) when imposing sentence, it should do so only after considering the properly calculated guideline range and any applicable departures provided for in the Guidelines Manual.

The page offers a link to the tool, here, and “Frequently Asked Questions” about the tool.

Since the tool is for judges, with a presumption that some judges will use it and may have sentencing decisions influenced by it, prosecution and defense counsel should be familiar with how it works.

The Sentencing Law and Policy Blog has herea good post (with further links) titled “Sentencing Commission Data Tool Is Deeply Flawed” (quotation marks in the title, to indicate that it is reporting on a Law360 article (paywall).  The SLP Blog quotes the Law 360 article by Michael Yaeger extensively, so access to the Law360 article may not be required for some useful information.  It is interesting that the illustrative example Yaeger offers for his concerns about the limitations of the tool is a tax example as follows:

When JSIN is queried for stats on the position of the sentencing table for U.S. Sentencing Commission Section 2T1.1 — tax evasion, offense level 17 and criminal history I — JSIN reports the median sentence as 18 months.  But when one uses the commission’s full dataset to calculate the median on that same cohort (Section 2T1.1, level 17, history I, no 5K1.1) and includes sentences of probation, the median is significantly lower.  Instead of JSIN’s 18 months, the median is just 12 months. That’s a whole six months lower — and a 33% decrease….

Yeager then is quoted as concluding:

[B]y conducting a more complete study of the Sentencing Commission’s data than the JSIN provides, the defense could also examine particular aspects of a guidelines calculation, such as loss or drug weight.  The defense could strip out mandatory minimum sentences or do an analysis of 10 or 15 years of cases, not just five.  They could also break down cases by circuit or district, not just nationally.  Now that JSIN is available, defense attorneys should consider all the above.  It was already a good idea to use accurate and complete data analysis of similarly situated defendants. But now the need has increased. The defense now has to counter JSIN and the false impression it creates.

Using the example Yaeger chose (tax offense level 17 and criminal history of 1), here are snapshots of the information offered (I repeat the explanation portion of each draft immediately below it for easier readability:

FEDERAL OFFENDERS IN SELECTED CELL
During the last five fiscal years (FY2016-2020), there were 165 offenders whose primary guideline was §2T1.1, with a Final Offense Level of 17 and a Criminal History Category of I, after excluding offenders who received a §5K1.1 substantial assistance departure. For the 131 offenders (79%) who received a sentence of imprisonment in whole or in part, the average length of imprisonment imposed was 16 month(s) and the median length of imprisonment imposed was 18 month(s).
The sentencing data provided does not reflect the Commission’s recommendation regarding the appropriate sentence to be imposed or represent the Commission’s official position on any issue or case. Nor does the information provided reflect the Commission’s position regarding the weight to be given, if any, to the above sentencing information in a court’s determination of the appropriate sentence to be imposed.
If the court does consider the above sentencing information as part of its consideration of the factors in 18 U.S.C. § 3553(a) in imposing sentence, it should do so only after considering the properly calculated guideline range and any applicable departures provided for in the Guidelines Manual.

Note: The figure includes the 202 offenders reported to the Commission whose primary guideline was §2T1.1, with a Final Offense Level of 17 and a Criminal History Category of I, including offenders who received a §5K1.1 substantial assistance departure. Cases missing information necessary to complete the analysis were excluded from this figure. Offenders who received a §5K1.1 substantial assistance departure are included in this analysis but are excluded from other analyses below. As such, the number of offenders included in this analysis may exceed the number of offenders in other analyses. Total percentages displayed in the figure may not sum to 100% due to rounding.

Note: The figure includes the 165 offenders reported to the Commission whose primary guideline was §2T1.1, with a Final Offense Level of 17 and a Criminal History Category of I, after excluding offenders who received a §5K1.1 substantial assistance departure. Cases missing information necessary to complete the analysis were excluded from this figure. Total percentages displayed in the figure may not sum to 100% due to rounding.
The Offenders Receiving Imprisonment category includes offenders sentenced to a term of imprisonment (in whole or in part) and who received a commitment to the Bureau of Prisons. This category includes (1) offenders sentenced to a term of imprisonment only, with no additional conditions of community confinement, home detention or intermittent confinement (Prison Only) and (2) offenders sentenced to imprisonment and conditions of alternative confinement as defined in USSG §5C1.1 (Prison and Alternatives). This category includes, but is not limited to, Zone A, Zone B, or Zone C cases receiving prison with additional conditions of a term of community confinement, home detention, or intermittent confinement.
The Offenders Receiving Probation category includes offenders sentenced to a term of probation with or without a condition of community confinement, intermittent confinement, or home detention (Probation Only and Probation and Alternatives). This category also includes offenders who received no prison, no probation, and no time of alternative confinement as defined in USSG §5C1.1, but instead who received a fine and/or a special assessment (Fine Only).

Note: The figure includes the 131 offenders reported to the Commission (1) whose primary guideline was §2T1.1, with a Final Offense Level of 17 and a Criminal History Category of I, after excluding offenders who received a §5K1.1 substantial assistance departure; and (2) the offender received a sentence of imprisonment in whole or in part. Cases missing information necessary to complete the analysis were excluded from this figure.
Average and Median Length of Imprisonment reports the average and median term of imprisonment imposed in months for cases in which a term of imprisonment was imposed. Probation sentences are excluded. Any portion of a sentence that is an alternative confinement as described in USSG §5C1.1 is also excluded. Cases in which a sentence is imposed, but where the length is indeterminable, are excluded. When sentences are expressed as “time served” on the J&C, Commission staff uses the dates in federal custody to determine the length of time served when an offender has been in custody the entire time. If the offender has been in and out of custody, or the start date is unclear/missing, then the Commission assigns a value of one day as a minimal time served amount for these cases. In cases where the court imposes a sentence of life imprisonment, sentences are reported as 470 months, a length consistent with the average life expectancy of federal criminal offenders given the average age of federal offenders. Sentences of greater than 470 months are also reported as 470 months.