Early reports on data form 2012 and 2013 show that plans that entered the program did better if they entered earlier rather than later.  However the results are clearly mixed.

From the NEJM article.

In the Medicare Shared Savings Program (MSSP) — the largest of the Medicare accountable care organization (ACO) programs — participating provider organizations share in savings with Medicare if they keep spending for an attributed population of fee-for-service beneficiaries sufficiently below a financial benchmark. Greater shared-savings bonuses are awarded to ACOs with higher performance on a set of quality measures. Unlike ACOs in the Medicare Pioneer program, very few ACOs in the MSSP face penalties for spending in excess of benchmarks because such downside risk is not currently required.1The financial benchmark for an ACO is set by the Centers for Medicare and Medicaid Services (CMS) at the average level of Medicare spending for patients served by the ACO during a baseline period before the start of the contract and is updated for each contract year on the basis of national Medicare spending growth since the baseline period. On the basis of comparisons of ACO spending with these benchmarks, CMS has reported savings on average across all ACOs in the MSSP (not including shared-savings bonuses paid) and greater savings achieved by ACOs entering the program in 2012 than by those entering in 2013.2,3Savings based on these actuarial calculations, however, may differ from actual spending reductions. For example, the substantial geographic variation in Medicare spending growth calls into question the validity of savings estimated by comparing spending in an ACO with a benchmark derived from a national rate of spending growth.4,5 If an ACO is located in an area with high spending growth, its savings could be underestimated. Providers participating in ACO programs and different types of ACOs are not randomly distributed across geographic areas.6-8 Therefore, the extent to which ACOs in the MSSP have lowered spending overall remains unclear, as do differences in savings achieved by ACOs with different traits, times of program entry, or incentives.Using Medicare claims and CMS definitions of the 220 ACOs entering the MSSP in 2012 or 2013, we compared changes in spending and performance on claims-based quality measures for beneficiaries served by ACOs from before to after the start of ACO contracts with concurrent changes for beneficiaries served by non-ACO providers in ACO service areas.METHODSStudy Data and PopulationWe analyzed Medicare claims and enrollment data from 2008 through 2013 for a random 20% sample of fee-for-service beneficiaries. For each study year from 2009 through 2013, we included beneficiaries who were continuously enrolled in Parts A and B of fee-for-service Medicare in that year (during the time they were alive, in the case of beneficiaries who subsequently died) and in the previous year (to assess preexisting conditions).Using the CMS ACO Provider-level Research Identifiable File, which defines each ACO as a collection of provider taxpayer identification numbers and CMS Certification Numbers (for safety-net providers),9 we attributed each beneficiary in each study year to the ACO or non-ACO taxpayer identification number accounting for the most allowed charges for qualifying outpatient evaluation and management services delivered to the beneficiary by a primary care physician during the year (see the Supplementary Appendix, available with the full text of this article at NEJM.org). Beneficiaries attributed to non-ACO providers constituted the control group. We excluded beneficiaries with no qualifying services.We followed the MSSP rules for attributing beneficiaries10 but limited qualifying services to those provided by primary care physicians, because many ACOs include no or few specialty practices. This restriction improved balance in precontract spending levels between the ACO group and the control group. In a sensitivity analysis, we modified ACO definitions to account for major changes in the taxpayer identification numbers used by participating providers. (For more details on attribution of beneficiaries and modification of ACO definitions, see the Supplementary Appendix.)Study VariablesSpending and Quality MeasuresThe primary outcome of our study was total annual Parts A and B Medicare spending per beneficiary, as defined by ACO program specifications.11 In secondary analyses, we analyzed spending according to the type of service and care setting.As in a previous study,5 we assessed several claims-based measures of quality of care included in ACO contracts12: hospitalizations for two ambulatory care–sensitive conditions (ACSCs; conditions for which appropriate ambulatory care could potentially reduce the need for inpatient care) — congestive heart failure and chronic obstructive pulmonary disease or asthma13,14; all-cause 30-day readmissions among hospitalized beneficiaries; and screening mammography. We also assessed hospitalizations for ACSCs related to cardiovascular disease and diabetes14 and three preventive services for diabetes, because many contract measures that cannot be asse

Source: Early Performance of Accountable Care Organizations in Medicare — NEJM