Data Center PUE by Operator and Campus: Published Benchmarks
Power usage effectiveness (PUE) is a data center's total energy divided by the energy that reaches its IT equipment, so 1.0 would mean no overhead at all. Lawrence Berkeley National Laboratory put the U.S. average at 1.40 in 2023. Among operators that publish a fleet figure for 2024 or later, PUE runs from 1.08 (Meta) to 1.59 (CyrusOne), and the lowest single-campus figure published is 1.04 (Google, Central Ohio (Lancaster), Ohio).
Below: a PUE calculator, the most efficient campuses by published PUE, every operator's fleet average, and 168 published PUE and water figures from 12 operators, each with its source and period.
- 1.40
- LBNL estimate, 2023
- 1.08
- Meta, 2024 annual
- 1.04
- Google, Central Ohio (Lancaster), Ohio
- 12
- 168 published figures
The default price is the U.S. average industrial rate for January to August 2026 (EIA). Starting energy values are an example.
Most efficient data centers by published PUE
| # | Campus | Operator | PUE | Period | Source |
|---|---|---|---|---|---|
| 1 | Central Ohio (Lancaster), Ohio | 1.04 | trailing twelve months ending Q2 2026 | Source | |
| 2 | Fort Wayne, Indiana | 1.05 | quarter Q2 2026 only (Google publishes no TTM until a campus has twelve months of data) | Source | |
| 3 | Omaha, Nebraska | 1.05 | trailing twelve months ending Q2 2026 | Source | |
| 4 | Central Ohio (Columbus), Ohio | 1.06 | trailing twelve months ending Q2 2026 | Source | |
| 5 | Fredericia, Denmark | 1.06 | trailing twelve months ending Q2 2026 | Source | |
| 6 | The Dalles, Oregon (2nd facility) | 1.06 | trailing twelve months ending Q2 2026 | Source | |
| 7 | Central Ohio (New Albany), Ohio | 1.07 | trailing twelve months ending Q2 2026 | Source | |
| 8 | Eemshaven, Netherlands | 1.07 | trailing twelve months ending Q2 2026 | Source | |
| 9 | Council Bluffs, Iowa (2nd facility) | 1.08 | trailing twelve months ending Q2 2026 | Source | |
| 10 | Dublin, Ireland | 1.08 | trailing twelve months ending Q2 2026 | Source | |
| 11 | Loudoun County, Virginia | 1.08 | trailing twelve months ending Q2 2026 | Source | |
| 12 | Loudoun County, Virginia (2nd facility) | 1.08 | trailing twelve months ending Q2 2026 | Source | |
| 13 | Quilicura, Chile | 1.08 | trailing twelve months ending Q2 2026 | Source | |
| 14 | St. Ghislain, Belgium | 1.08 | trailing twelve months ending Q2 2026 | Source | |
| 15 | The Dalles, Oregon (3rd facility) | 1.08 | trailing twelve months ending Q2 2026 | Source |
Campus figures only (regions and fleets are averages over many sites). Of the operators covered, only Google publishes PUE campus by campus, so every row is Google; the full list of 35 campuses is in the table further down. Fleet averages by operator: Meta 1.08, Google 1.09, Amazon Web Services 1.14, Microsoft 1.17, Digital Realty 1.20, Equinix 1.37, NTT DATA (Global Data Centers) 1.38, QTS 1.38, Iron Mountain Data Centers 1.41, CyrusOne 1.46.
Fleet averages operators publish
| Operator | Metric | Value | Unit as published | Period | Source |
|---|---|---|---|---|---|
| Meta | PUE | 1.08 | ratio | 2024 annual | Source |
| PUE | 1.09 | ratio | trailing twelve months ending Q4 2025 (calendar 2025) | Source | |
| PUE | 1.09 | ratio | trailing twelve months ending Q2 2026 | Source | |
| Amazon Web Services | PUE | 1.14 | ratio | 2025 annual (January 1 to December 31, 2025) | Source |
| Microsoft | PUE | 1.17 | ratio | FY25 (July 1, 2024 to June 30, 2025) | Source |
| Switch | PUE | 1.18 | ratio | not stated (undated web page claim marked with an asterisk that the page does not explain) | Source |
| Digital Realty196 MW of IT capacity delivered in 2025 (subset) | PUE | 1.2 | ratio | capacity delivered in 2025 | Source |
| Vantage Data Centers | PUE | 1.26 | ratio | 2023 (latest ESG report found) | Source |
| Equinix | PUE | 1.37 | ratio | 2025 annual | Source |
| Digital Realty | PUE | 1.38 | ratio | 2025 annual | Source |
| NTT DATA (Global Data Centers) | PUE | 1.38 | ratio | FY2024 (NTT DATA fiscal year; months not restated on page) | Source |
| QTS | PUE | 1.38 | ratio | 2025 annual | Source |
| LBNL (US national estimate)United States, all data centers | PUE | 1.4 | ratio | 2023 annual | Source |
| Iron Mountain Data Centers | PUE | 1.41 | ratio | 2025 annual | Source |
| CyrusOne | PUE | 1.46 | ratio | 2025 annual | Source |
| CyrusOneStandard Dry Facilities (76% of critical load capacity) | PUE | 1.46 | ratio | 2025 annual | Source |
| CyrusOneNonstandard Wet Facilities (21% of critical load capacity) | PUE | 1.47 | ratio | 2025 annual | Source |
| CyrusOneNonstandard Dry Facilities (3% of critical load capacity) | PUE | 1.59 | ratio | 2025 annual | Source |
| CyrusOneStandard Dry Facilities (76% of critical load capacity) | WUE | 0 | L/kWh | 2025 annual | Source |
| CyrusOneNonstandard Dry Facilities (3% of critical load capacity) | WUE | 0 | L/kWh | 2025 annual | Source |
| Digital RealtySites with non-evaporative cooling (subset) | WUE | 0.07 | not stated in table (report states WUE targets in L/kWh IT) | 2025 annual | Source |
| Amazon Web Services | WUE | 0.12 | L/kWh (liters withdrawn per kWh of IT load) | 2025 annual (January 1 to December 31, 2025) | Source |
| Meta | WUE | 0.19 | L/kWh (water withdrawal in liters divided by IT electricity load in kWh) | 2024 annual | Source |
| CyrusOne | WUE | 0.25 | L/kWh | 2025 annual | Source |
| Microsoft | WUE | 0.27 | L/kWh | FY25 (July 1, 2024 to June 30, 2025) | Source |
| LBNL (US national estimate)United States, all data centers | WUE | 0.36 | L/kWh | through 2023 | Source |
| QTS | WUE | 0.44 | not stated (report cites The Green Grid WUE methodology) | 2025 annual | Source |
| Digital Realty | WUE | 0.59 | not stated in table (report states WUE targets in L/kWh IT) | 2025 annual | Source |
| NTT DATA (Global Data Centers) | WUE | 0.72 | l/kWh | FY2024 (NTT DATA fiscal year; months not restated on page) | Source |
| Iron Mountain Data Centers | WUE | 0.82 | liters per kWh of IT load (per the report's WUE definition) | 2025 annual | Source |
| Equinix | WUE | 0.91 | not stated in source | 2025 annual | Source |
| CyrusOneNonstandard Wet Facilities (21% of critical load capacity) | WUE | 1.35 | L/kWh | 2025 annual | Source |
| EquinixData centers with evaporative cooling (subset) | WUE | 1.41 | not stated in source | 2025 annual | Source |
| NTT DATA (Global Data Centers)Evaporative sites only (subset) | WUE | 1.42 | l/kWh | FY2024 (NTT DATA fiscal year; months not restated on page) | Source |
| Digital RealtySites with evaporative cooling (subset) | WUE | 1.73 | not stated in table (report states WUE targets in L/kWh IT) | 2025 annual | Source |
Campus and regional figures
Showing 133 of 133
| Amazon Web Services | Europe (Ireland), IE | WUE | 0.02 |
| Amazon Web Services | Europe (Stockholm), SE | WUE | 0.02 |
| Microsoft | Europe, Middle East & Africa | WUE | 0.03 |
| Amazon Web Services | Canada (West), CA | WUE | 0.04 |
| Amazon Web Services | Europe | WUE | 0.05 |
| Amazon Web Services | Asia-Pacific (Melbourne), AU | WUE | 0.06 |
| Amazon Web Services | U.S. East (Northern Virginia) | WUE | 0.06 |
| Amazon Web Services | U.S. East (Ohio) | WUE | 0.06 |
| Amazon Web Services | Canada (Central), CA | WUE | 0.06 |
| Amazon Web Services | North America | WUE | 0.08 |
| Amazon Web Services | Central/South America | WUE | 0.09 |
| Amazon Web Services | South America (Sao Paulo), BR | WUE | 0.09 |
| Amazon Web Services | Asia-Pacific (Sydney), AU | WUE | 0.10 |
| Amazon Web Services | Europe (Spain), ES | WUE | 0.12 |
| Amazon Web Services | U.S. West (Oregon) | WUE | 0.12 |
| Amazon Web Services | Europe (London), GB | WUE | 0.14 |
| Amazon Web Services | Europe (Frankfurt), DE | WUE | 0.17 |
| Digital Realty | EMEA | WUE | 0.19 |
| Microsoft | Asia Pacific | WUE | 0.25 |
| Microsoft | Americas | WUE | 0.34 |
| Amazon Web Services | U.S. West (Northern California) | WUE | 0.39 |
| Digital Realty | North America | WUE | 0.68 |
| Central Ohio (Lancaster), Ohio | PUE | 1.04 | |
| Central Ohio (Lancaster), Ohio | PUE | 1.04 | |
| Omaha, Nebraska | PUE | 1.05 | |
| Fort Wayne, Indiana | PUE | 1.05 | |
| Omaha, Nebraska | PUE | 1.05 | |
| Central Ohio (Columbus), Ohio | PUE | 1.06 | |
| Central Ohio (New Albany), Ohio | PUE | 1.06 | |
| The Dalles, Oregon (2nd facility) | PUE | 1.06 | |
| Central Ohio (Columbus), Ohio | PUE | 1.06 | |
| Fredericia, Denmark | PUE | 1.06 | |
| The Dalles, Oregon (2nd facility) | PUE | 1.06 | |
| Amazon Web Services | Europe (Spain), ES | PUE | 1.06 |
| Eemshaven, Netherlands | PUE | 1.07 | |
| Fredericia, Denmark | PUE | 1.07 | |
| Central Ohio (New Albany), Ohio | PUE | 1.07 | |
| Eemshaven, Netherlands | PUE | 1.07 | |
| Amazon Web Services | Asia-Pacific (Melbourne), AU | PUE | 1.07 |
| Council Bluffs, Iowa (2nd facility) | PUE | 1.08 | |
| Dublin, Ireland | PUE | 1.08 | |
| Loudoun County, Virginia | PUE | 1.08 | |
| Loudoun County, Virginia (2nd facility) | PUE | 1.08 | |
| Quilicura, Chile | PUE | 1.08 | |
| St. Ghislain, Belgium | PUE | 1.08 | |
| Council Bluffs, Iowa (2nd facility) | PUE | 1.08 | |
| Dublin, Ireland | PUE | 1.08 | |
| Loudoun County, Virginia | PUE | 1.08 | |
| Loudoun County, Virginia (2nd facility) | PUE | 1.08 | |
| Quilicura, Chile | PUE | 1.08 | |
| St. Ghislain, Belgium | PUE | 1.08 | |
| The Dalles, Oregon (3rd facility) | PUE | 1.08 | |
| Berkeley County, South Carolina | PUE | 1.09 | |
| Bristow, Virginia | PUE | 1.09 | |
| Douglas County, Georgia | PUE | 1.09 | |
| Henderson, Nevada | PUE | 1.09 | |
| Montgomery County, Tennessee | PUE | 1.09 | |
| Papillion, Nebraska | PUE | 1.09 | |
| Bristow, Virginia | PUE | 1.09 | |
| Douglas County, Georgia | PUE | 1.09 | |
| Hamina, Finland | PUE | 1.09 | |
| Henderson, Nevada | PUE | 1.09 | |
| Montgomery County, Tennessee | PUE | 1.09 | |
| Papillion, Nebraska | PUE | 1.09 | |
| Amazon Web Services | Europe (Stockholm), SE | PUE | 1.09 |
| Hamina, Finland | PUE | 1.10 | |
| Jackson County, Alabama | PUE | 1.10 | |
| Lenoir, North Carolina | PUE | 1.10 | |
| Midlothian, Texas | PUE | 1.10 | |
| The Dalles, Oregon | PUE | 1.10 | |
| Berkeley County, South Carolina | PUE | 1.10 | |
| Inzai, Japan | PUE | 1.10 | |
| Lenoir, North Carolina | PUE | 1.10 | |
| The Dalles, Oregon | PUE | 1.10 | |
| Amazon Web Services | Asia Pacific (excl. China) | WUE | 1.10 |
| Amazon Web Services | Europe (Ireland), IE | PUE | 1.10 |
| Council Bluffs, Iowa | PUE | 1.11 | |
| Inzai, Japan | PUE | 1.11 | |
| Council Bluffs, Iowa | PUE | 1.11 | |
| Jackson County, Alabama | PUE | 1.11 | |
| Mayes County, Oklahoma | PUE | 1.11 | |
| Midlothian, Texas | PUE | 1.11 | |
| Amazon Web Services | Europe | PUE | 1.11 |
| Mayes County, Oklahoma | PUE | 1.12 | |
| Singapore, SG | PUE | 1.12 | |
| Singapore, SG | PUE | 1.12 | |
| Amazon Web Services | U.S. East (Ohio) | PUE | 1.12 |
| Amazon Web Services | U.S. West (Oregon) | PUE | 1.12 |
| Changua County, Taiwan | PUE | 1.13 | |
| Changua County, Taiwan | PUE | 1.13 | |
| Amazon Web Services | Canada (West), CA | PUE | 1.13 |
| Singapore (2nd facility), SG | PUE | 1.14 | |
| Storey County, Nevada | PUE | 1.14 | |
| Red Oak, Texas | PUE | 1.14 | |
| Amazon Web Services | North America | PUE | 1.14 |
| Amazon Web Services | Central/South America | PUE | 1.14 |
| Amazon Web Services | Asia-Pacific (Sydney), AU | PUE | 1.14 |
| Amazon Web Services | South America (Sao Paulo), BR | PUE | 1.14 |
| Singapore (2nd facility), SG | PUE | 1.15 | |
| Storey County, Nevada | PUE | 1.15 | |
| Amazon Web Services | U.S. East (Northern Virginia) | PUE | 1.15 |
| Microsoft | Americas | PUE | 1.16 |
| Microsoft | Europe, Middle East & Africa | PUE | 1.16 |
| Amazon Web Services | U.S. West (Northern California) | PUE | 1.18 |
| Amazon Web Services | Africa | PUE | 1.19 |
| Amazon Web Services | Africa (Cape Town), ZA | PUE | 1.19 |
| Amazon Web Services | Canada (Central), CA | PUE | 1.19 |
| Amazon Web Services | Asia-Pacific (Tokyo), JP | WUE | 1.22 |
| Amazon Web Services | Europe (London), GB | PUE | 1.23 |
| Amazon Web Services | Europe (Frankfurt), DE | PUE | 1.24 |
| Amazon Web Services | Asia Pacific (excl. China) | PUE | 1.25 |
| Amazon Web Services | China, CN | PUE | 1.25 |
| Amazon Web Services | Middle East (UAE) | PUE | 1.25 |
| Amazon Web Services | Asia-Pacific (Tokyo), JP | PUE | 1.25 |
| Amazon Web Services | China (Ningxia), CN | PUE | 1.25 |
| Amazon Web Services | Middle East (Tel Aviv), IL | PUE | 1.27 |
| Mesa, Arizona | PUE | 1.28 | |
| Microsoft | Asia Pacific | PUE | 1.28 |
| Amazon Web Services | Middle East | PUE | 1.29 |
| Amazon Web Services | Asia-Pacific (Jakarta), ID | PUE | 1.29 |
| Amazon Web Services | Asia-Pacific (Singapore), SG | PUE | 1.30 |
| Digital Realty | EMEA | PUE | 1.31 |
| Amazon Web Services | Middle East (Bahrain), BH | PUE | 1.33 |
| Amazon Web Services | Europe (Paris), FR | PUE | 1.35 |
| Amazon Web Services | Asia-Pacific (Bangkok), TH | PUE | 1.38 |
| Digital Realty | APAC | PUE | 1.38 |
| Amazon Web Services | Asia-Pacific (Mumbai), IN | PUE | 1.40 |
| Digital Realty | North America | PUE | 1.41 |
| Amazon Web Services | Asia-Pacific (Hyderabad), IN | PUE | 1.43 |
| Amazon Web Services | Asia-Pacific (Osaka), JP | PUE | 1.46 |
| Amazon Web Services | Asia-Pacific (Singapore), SG | WUE | 1.57 |
| Digital Realty | APAC | WUE | 1.66 |
| Amazon Web Services | Asia-Pacific (Jakarta), ID | WUE | 2.85 |
- Fleet, regional and campus figures from 12 operators' own reports and pages, mostly for 2024 and 2025, plus LBNL's national estimates.
- Google Data Centers: Power usage effectiveness (efficiency page, 2026 and 2025 PUE yearly reports), Google 2026 Environmental Report (covers calendar year 2025), Meta Platforms: Meta 2025 Environmental Data Index (covers 2024), Microsoft Datacenters: Measuring datacenter energy and water use (PUE and WUE by region)
- , 168 published figures
How this was built
Power usage effectiveness is total data center energy divided by the energy delivered to IT equipment, as standardized in ISO/IEC 30134-2 and used by The Green Grid; 1.0 would mean every kWh reaches IT equipment (source: Mytton 2021, eq. 1, citing ISO/IEC 30134-2:2016; Lei et al. 2025 citing The Green Grid 2011). Water usage effectiveness, defined by The Green Grid (white paper WP#35, 2011), is annual site water usage divided by IT equipment energy, reported in liters per kWh of IT energy; it counts on-site water only, and The Green Grid's separate WUE source adds the water used to generate the electricity (source: Mytton 2021, eqs. 2 and 3, citing The Green Grid WP#35).
Every figure is copied as the operator publishes it, with its unit, period and basis (measured, design, trailing twelve months). Where a report does not state the unit for WUE, the unit column says so. We do not convert or estimate missing values. To turn a PUE into dollars, use the calculator above or the power cost calculator.
Limits of this data
- Operators draw their measurement boundaries differently (which buildings, which losses, which period), so figures are not strictly comparable across companies.
- Hyperscale operators run large owned campuses; colocation operators run many smaller, multi-tenant sites. Their PUEs differ partly for that reason.
- WUE counts on-site water only. It leaves out the water used to generate the electricity; the water calculator shows both.
- Several operators publish only a fleet average, and the Uptime Institute's survey average sits behind a registration form, so it is not included.
Sources
- 1.Google Data Centers: Power usage effectiveness (efficiency page, 2026 and 2025 PUE yearly reports)
- 2.Google 2026 Environmental Report (covers calendar year 2025)
- 3.Meta Platforms: Meta 2025 Environmental Data Index (covers 2024)
- 4.Microsoft Datacenters: Measuring datacenter energy and water use (PUE and WUE by region)
- 5.Microsoft 2026 Environmental Sustainability Report
- 6.Amazon Sustainability: AWS Cloud (PUE and WUE by geography and AWS Region)
- 7.Equinix 2025 Sustainability Report
- 8.Equinix 2025 Sustainability Data Summary
- 9.Digital Realty 2025 Impact Report
- 10.Iron Mountain Data Centers Sustainability Overview 2025
- 11.NTT DATA Group ESG Data: Environment Data
- 12.CyrusOne 2026 Sustainability Report (covers 2025)
- 13.QTS Data Centers: QTS 2025 Sustainability Report
- 14.Switch: Sustainability (web page)
- 15.Vantage Data Centers 2023 ESG Report
- 16.Lawrence Berkeley National Laboratory: 2024 United States Data Center Energy Usage Report (Shehabi et al., LBNL-2001637, December 2024)
Frequently asked questions
What is a good PUE for a data center?
Lower is better, and 1.0 is the theoretical floor. The lowest fleet figures operators publish are around 1.08, while LBNL estimated the U.S. average at 1.40 for 2023. Climate, size and cooling design all affect what is achievable.
Which data center has the best PUE?
Of the campus figures operators publish, the lowest is 1.04 at Google's Central Ohio (Lancaster), Ohio campus (trailing twelve months ending Q2 2026). Most operators publish only fleet or regional averages, so a campus that is not listed may be as efficient without saying so.
How do you calculate PUE?
Divide the total energy the facility used over a period by the energy its IT equipment used over the same period. Measure both over a full year so seasonal cooling loads are included.
Related datasets and tools
- Data Center Power Cost Calculator
A data center's yearly power bill from its IT load, PUE and state electricity rate, and how much a 0.1 PUE improvement would save each year.
- How Much Water Does a Data Center Use? Calculator and Facility Data
Estimate a data center's daily and yearly water use as a low, mid and high range, then compare it with what operators report for their own sites.
- Data Center Cooling Types and Water Use: Published WUE by System
Water use effectiveness published for evaporative, adiabatic and air-cooled data centers, side by side, with the source and page of each figure.
- Data Center Tax Incentives by State
State sales tax exemptions and other data center incentives: investment and job thresholds, duration, sunset dates and the statute. CSV download.