Performance Index
Intel Technology Tour (ITT) 2025
For more information about Intel's announcements at ITT 2025, visit Intel Newsroom.
AI at Scale
| Claim | Claim Details/Citation |
|---|---|
| ~80% of AI compute cycles in inference by 2028 | Source: Gartner, published 08/2024 |
| Explosive Token Growth - 140x per month | Source: https://www.kisacoresearch.com/sites/default/files/documents/ai_infra_summit_2025_report_0.pdf |
| Cost Performance Today - Better perf/$ | Based on Intel internal analysis of information available as of Sept. 2025. Visualization for illustrative purposes only. |
| Up to 1.7x perf/TCO benefits | Date: 9/27/2025 Benchmarking Setups: B200- Supermicro: - Intel(R) Xeon(R) 6960P - 3 TB memory - 1 x Connect-X 7 - 400G ethernet - 8x B200 Gaudi3x8 -Supermicro - Intel(R) Xeon(R) 6960P - 2.2 TB memory - 1 x Connect-X 7 - 400G ethernet - 8x B200
SLA assumptions: - Max TTFT: 1 second (1 second for smaller models / context) - Max TBT: 50ms - ISL/OSL: 512-8192. - Date Types: BF16, FP8. The TCO model is fairly sensitive to data types and ISL/OSL ratios.
Cost Model: - B200 Cost: $40,000 - G3 Cost: $12,500 Interest rate: 8% Financing Term: 4 years Electricity + Hosting +mis ($/Kwh): $0.40.TDP is used for this number.
Software: Pre-release software. |
Intel Global Manufacturing Keynote
| Claim | Claim Details/Citation |
|---|---|
| 1.7x YoY AI Chips Volume Growth | Rand paper: www.rand.org/t/RRA3572-1. "AI's Power Requirements Under Exponential Growth" Page 2: " The green line displays the median estimate for AI data centers' future power demand at a 1.7-times annual growth rate in chip supply; the grey uncertainty range indicates demand growth between 1.3 and 2 times. |
| Up to 10% higher density and cell utilization | https://ieeexplore.ieee.org/document/10185208 |
| Up to 30%IR drop from package to transistor | https://ieeexplore.ieee.org/document/10185208 |
| Single pattern lower metal layers: Reduce frontside process cost, offsets cost of backside process | Source : Intel internal analysis, 2024.Results may vary |
| >15% perf/w increase vs. Intel 3 | Source : Intel internal analysis, 2024.Results may vary. |
| 1.3% Chip Density vs. Intel 3 | Source : Intel internal analysis, 2024.Results may vary. |
| 1.0x chip density vs. Intel 18A | Source : Intel internal analysis, 2025.Results may vary. |
| ~8x Perf/W Increase vs. Intel 18A | Source : Intel internal analysis, 2025.Results may vary. |
| Sustainability disclaimer | Intel is committed to the continued development of more sustainable products, processes, and supply chain as we strive to prioritize greenhouse gas reduction and improve our global environmental impact. Where applicable, environmental attributes of a product family or specific SKU will be stated with specificity. Refer to Intel Corporate Responsibility Report https://csrreportbuilder.intel.com/pdfbuilder/pdfs/CSR-2023-24-Full-Report.pdf or visit www.Intel.com/2030goals for further information. |
Client Strategic Overview
| Claim | Claim Details/Citation |
|---|---|
| >50% more CPU & GPU performance vs. Lunar Lake & Arrow Lake | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake reference validation platform as estimated by SPECrate®2017_int_base (n-copy) for long-term expected steady state processor power consumption. Data based on Panther Lake reference validation platform measurement vs Lunar Lake and Arrow Lake-H reference validation platforms as measured by 3Dmark Solar Bay, Cyberpunk2077and Borderlands 3. |
| 350+ ISVs | As of September,2025. |
| ~500 features available | As of September,2025. |
| 900+ AI Models Supported | As of September,2025. |
Panther Lake Unpacked
| Claim | Claim Details/Citation |
|---|---|
| IPU 7.5 | IPU 7.5 is available on select systems. OEM enablement required. Check with OEM or retailer for system configuration. |
| Big performance in its smallest footprint yet, both for area and power | >40% more TOPS/area vs. Lunar Lake. As measured by comparing peak TOPS to measured die area. |
| >10% more ST performance at similar power vs. Lunar Lake | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (1-copy) for long-term expected steady state processor power consumption. |
| >50% more MT performance at similar power vs. Lunar Lake | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (n-copy) for long-term expected steady state processor power consumption. |
| >30% lower power at similar MT performance vs. Arrow Lake | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s) as estimated by SPECrate®2017_int_base (n-copy) for long-term expected steady state processor power consumption. |
| >50% more performance vs. Lunar Lake & Arrow Lake | Testing by Intel as of Sept 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake and Arrow Lake-H reference validation platforms as measured by 3Dmark Solar Bay, Cyberpunk2077and Borderlands 3. |
| >40% more TOPS/area vs. Lunar Lake | As measured by comparing peak TOPS to measured die area. |
| 1.5W reduction in power with HDR staggered HDR vs. Lunar Lake | Power reduction is dependent on resolution. |
| Up to 10% lower power vs. Lunar Lake | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s) as estimated by SPECrate®2017_int_base (1-copy) for long-term expected steady state processor power consumption. |
| 40% lower power vs. Arrow Lake | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (1-copy) for long-term expected steady state processor power consumption. |
| Broadest set of Codecs supported | Codec capabilities may vary by device and configuration. Contact your manufacturer to understand the enabled hardware acceleration and codec capabilities for individual device. |
Wireless Connectivity
| Claim | Claim Details/Citation |
|---|---|
| Best-in-class Wireless forAI PCs | The Intel® Wi-Fi 7 (5 Gig) wireless solution available for the new Intel® Core® Ultra (series 3) AI PC platforms is best-in-class based on: support for optional performance-enhancing features of the latest unlicensed wireless standards (Wi-Fi 7 R2, Bluetooth® Core 6.0); PC-first focused wireless solution design, technology integration, and coordinated development in tandem with Intel AI PCs; extensive end-to-end platform-level wireless validation and performance testing; breadth of Intel platform connectivity innovations: new features, software applications, telemetry, analytics, and power savings; support for the highest levels of industry standards-based security protocols (WPA3, FIPS), and support for SIPP with vPro manageability (Active Management Technology); Intel is the only full-service PC WLAN card vendor (Silicon, M.2 cards, BIOS, drivers, software, world-wide regulatory services, safety testing, standards certification, supply-chain, logistics, and OEM & end-user customer support); expansive connectivity ecosystem enabling and interoperability testing (OSV/ISV/PC OEM/IHV); wireless Industry leadership as measured by a history of more than 20 years of delivering wireless solutions for Intel PC platforms and more than 120 leadership positions across wireless technology industry groups; and the nearly 2 billion unit global lifetime footprint of Intel® processor-based PC clients with Intel® WLAN since the initial launch of the Intel® Centrino® platform in 2003. Learn more at intel.com/wireless. |
| The only full-service PC wireless vendor | As of September,b2025. |
| Integrated Wi-Fi and Dual-Bluetooth ® technologies for superior performance, latency, and reliability | Refers to Intel® Wi-Fi 7 (5 Gig) solutions based on comprehensive feature support for the latest unlicensed wireless standards; PC-first wireless solution development with platform integration, validation, and new feature innovations; and support for the highest levels of wireless security; as of Sept. 2025. Details at intel.com/performance-wireless. Results may vary. |
| Improved PC client performance, latency, reliability, and security | Compared to Wi-Fi 6. |
| For more bandwidth per user | Compared to Wi-Fi 6. It is a function of the feature - instead of large channels being blocked because a small portion is occupied, we're now able to use the free sections of the large channel that were previously not available. |
| Intel® PC Wi-Fi 7 Leadership | Intel Casper Wireless Test Facility; Clients: (Intel) HP EliteBook X G1i 14 - Intel Core Ultra 200 - Intel BE201 - 23.140.0.1 - Windows 11 24H2, (QCOM) HP EliteBook Ultra G1q 14 - Qualcomm Snapdragon X Elite - FC7800 - 1.0.4267.800 - Windows 11 24H2, (AMD) HP EliteBook X G1a 14 - AMD AI PRO 300 - MediaTek MT7925 - 5.5.0.3390 - Windows 11 24H2; Wi-Fi 7 AP - ASUS RT-BE96U (BRCM) - FW: 3.0.0.6_102_37812 |
| Wi-Fi 7 Residential Trials | 4500+ ft 2 2-story home with basement; Client: Dell Latitude 5440 (Win 11), Card: Intel Wi-Fi 7 BE200 & Wi-Fi 6/6E AX210 Routers: ASUS RT-BE96U (Wi-Fi 7) & GT-AXE11000 (Wi-Fi 6E) https://wballiance.com/wi-fi-7-cablelabs-intel/ 7 |
| Wi-Fi 7 Enterprise Trials | 20,000+ ft 2 Intel Casper Enterprise Test Facility; Client: Dell Latitude 5440 (Win 11), Card: Intel Wi-Fi 7 BE200 & Wi-Fi 6 AX200 APs: Ruckus R770 (Wi-Fi 7) & Ruckus R750 (Wi-Fi 6) https://wballiance.com/wi-fi-7-trials-for-enterprise-scenarios-att-commscope-and-intel/ |
| Intel® PC Bluetooth® Leadership | Compared to Classic Bluetooth Intel Casper Wireless Test Facility; Clients: (Intel) HP EliteBook X G1i 14 - Intel Core Ultra 200 - Intel BE201 - 23.140.0.1 - Windows 11 24H2, (QCOM) HP EliteBook Ultra G1q 14 - Qualcomm Snapdragon X Elite - FC7800 - 1.0.4267.800 - Windows 11 24H2, (AMD) HP EliteBook X G1a 14 - AMD AI PRO 300 - MediaTek MT7925 - 5.5.0.3390 - Windows 11 24H2; Wi-Fi 7 AP - ASUS RT-BE96U (BRCM) - FW: 3.0.0.6_102_37812 |
| Dual Bluetooth Superior Range | Intel Taiwan Wireless Test Facility; Clients: (Intel) PTL RVP - Intel Whale Peak, BE200, AX211 - 23.90.24304 - Windows 11 24H2, (QCOM) Asus VivobookS 15 - Qualcomm Snapdragon X Elite - FC7800 - 1.0.404.8300 - Windows 11 24H2; Speaker - Harmon Kardon Luna Speaker; Playback Application - Microsoft Media Player |
| Intel® Connectivity Performance Suite (ICPS) enables up to 66% lower latency on real-time voice/video calls. (during network contention) | Intel Over The Air (OTA) Wi-Fi testing in a congested network environment demonstrated a dramatic reduction in Zoom videoconferencing latency due to ICPS application prioritization. |
| Intel® Connectivity Performance Suite (ICPS) enables up to 4X better resolution for 4K video streaming. (during network contention) | Intel Over The Air (OTA) Wi-Fi testing in a congested network environment demonstrated a major improvement in video streaming resolution due to ICPS application prioritization. |
| Intel® Connectivity Performance Suite (ICPS) enables up to 30% faster speeds. (by choosing best available AP) | Intel Over The Air (OTA) Wi-Fi testing in a congested network environment demonstrated a significant improvement in Wi-Fi speeds due to ICPS Smart Access Point (AP) Switching. |
| Bluetooth® Low Energy Audio | 1) The Bluetooth® Low Energy Audio specification from the Bluetooth® SIG requires a new LC3 codec, which enables improved Bluetooth® audio quality at up to 50% lower bit rates and up to 50% lower Bluetooth® power consumption than Classic Bluetooth® Audio with the legacy SBC codec. Enjoy new wireless audio experiences with Bluetooth ® LE Audio accessories and select Intel ® Platforms with Intel ® Wireless Solutions that support Bluetooth ® Core 5.3 or higher Discover more at intel.com/wireless |
Next Gen IPU Architecture
| Claim | Claim Details/Citation |
|---|---|
| 75% of organizations use video conferencing | Source: https://market.biz/video-conferencing-statistics/?utm_source=chatgpt.com |
| 22% of U.S. workforce works remotely | Source: https://www.amraandelma.com/remote-work-statistics/?utm_source=chatgpt.com |
| 50 days a year spent in online meetings | Source: https://passport-photo.online/blog/75-mind-boggling-virtual-meeting-statistics/?utm_source=chatgpt.com |
| 83/100 VCX Score | As of September 2025 Source: https://vcx-forum.org/score/webcam-2025/devices/lenovo-think-pad-x9g1-aura |
| IPU 7.5 | IPU 7. 5 is available on select systems. OEM enablement required. Check with OEM or retailer for system configuration. |
| Up to 1.5W power reduction | Power reduction is dependent on resolution. |
Compute & Software
| Claim | Claim Details/Citation |
|---|---|
| Darkmont IPC is on-par with Raptor Cove IPC on LLC/Ring | Results are based on Intel's internal projections&estimates as of September 2025(+/- 10% Margin of Error)on SPEC CPU® 2017 Rate(est.), GCC12.1-O2Linux (ISO) at Fixed Frequency (ISO) with similar memory + fabric for general (not vector heavy) workloads. |
| >10% more performance at similar power vs. ARL H & LNL | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (1-copy) for long-term expected steady state processor power consumption. |
| >40% lower power at similar performance vs. ARL H& LNL | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (1-copy) for long-term expected steady state processor power consumption. |
| >30% lower power at similar performance vs.ARLH | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (n-copy) for long-term expected steady state processor power consumption. |
| >50% more performance at similar power vs. LNL | Testing by Intel as of September 2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake & Arrow Lake reference validation platform(s)as estimated by SPECrate®2017_int_base (n-copy) for long-term expected steady state processor power consumption. |
| Up to 19% performance uplift in DC performance | As of September 2025, based on performance estimated with measurements on Panther Lake reference platform with power optimizations enabled vs. power optimizations disabled. |
GPU & NPU Accelerators
| Claim | Claim Details/Citation |
|---|---|
| Various GPU functions have been improved in Xe3 IP | Results are based on an internal suite of micro benchmarks and collected on a pre-release Panther Lake engineering platform with pre-release GFX software. The comparison is a selected subset of micro benchmarks normalized for clock frequency, comparing a 12 Xe-cores Xe3 configuration to an 8 Xe-cores Xe2 configuration. |
| Up to 36% traffic reduction on SoC fabric with 16MB GPU L2 | Results are based on internal analysis of various cache configurations on a pre-release Panther Lake engineering platform with pre-release GFX software. |
| >50% graphics performance vs Lunar Lake | Testing by Intel as ofSept2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake and Arrow Lake-H reference validation platforms as measured by3Dmark Solar Bay, Cyberpunk 2077 and Borderlands 3. |
| >40% graphics performance/watt vs Arrow Lake-H | Testing by Intel as ofSept2025. Data based on Panther Lake reference validation platform measurement vs Lunar Lake and Arrow Lake-H reference validation platforms as measured by 3Dmark Solar Bay, Cyberpunk 2077 and Borderlands 3. |
| >40% improvement in TOPs/Area | As measured by comparing peak TOPS to measured die area vs. Lunar Lake. |
| Various NPU functions have been improved in NPU5 IP | Results are based on an internal suite of micro benchmarks and collected on a pre-release Panther Lake engineering platform with pre-release NPU software. The comparison is a selected subset of micro benchmarks normalized for clock frequency, comparing NPU5 as implemented in Panther Lake to NPU4 as implemented in Lunar Lake. |
| NPU5 is >50% more power efficient when running FP8 vs FP16 | Testing by Intel as ofSept2025. Data based on Panther Lake reference validation platform measurement when running Stable Diffusion with FP8 processing vs FP16 processing. |
Power Efficient Gaming
| Claim | Claim Details/Citation |
|---|---|
| Panther Lake renders a frame faster | Results are based on internal workload analysis data collected on a pre-release Panther Lake platform with pre-release GFX software. |
| A power management update in Q2 delivered 10% more FPS and 25% better 99 th percentiles on Intel Core Ultra 7 258V with Intel Arc 140V GPU. | See intel.com/performanceindex |
Agentic AI on PCs
| Claim | Claim Details/Citation |
|---|---|
| Up to 2x performance uplift for agentic workloads with latest OpenVINO SW stack | Testing by Intel as ofSept2025. Data based on Panther Lake reference validation platform measurement when running32K context inference with OpenVINO 2025.3 SW stack vs OpenVINO 2024.5. |
| Up to 6x reduction in memory consumption | Testing by Intel as ofSept2025. Data based on Panther Lake reference validation platform measurement when running 32K context inference with OpenVINO 2025.3 SW stack vs OpenVINO 2024.5. |
Data Center Strategic Overview & Clearwater Forest Unpacked
| Claim | Claim Details/Citation |
|---|---|
| Ericsson claims of 3.8xgreaterperformance per watt | Ecosystem Achieves Power Efficiency Breakthrough on Xeon 6 with E-Cores - Intel Newsroom |
| 5x TP gain per server | Ecosystem Achieves Power Efficiency Breakthrough on Xeon 6 with E-Cores - Intel Newsroom |
| 8 to 1 rack consolidation | Claim, Integer Throughput: Use 20 racks (180 servers) of Intel® Xeon® Clearwater Forest based servers running Integer Throughput, while delivering similar performance, instead of 70 racks (1400 servers) of Intel®Xeon® 8280 based servers and save 750 kW of fleet power. Fleet power reduction based on 50 fewer Intel® Xeon® Clearwater Forest based racks at 15kW/Rack is 750kW (rack power distribution). Intel Xeon Clearwater Forest based servers delivers 7.81x higher performance per server and 3.5x higher fleet performance/watt vs Intel Xeon 8280 on Integer Throughput. Assumptions: 1x 42U, 15KW Rack, supporting 20x 2U rack servers, 1x TOR switch. Fleet power for 70 racks of Intel Xeon 8280 based servers estimated as of Aug 2025: Power: 1050kW (70 racks * 15kW/rack). Fleet power for 20 rack of Intel Xeon Clearwater Forest based servers estimated as of Aug 2025: Power: 300kW (20 racks * 15kW/rack). Clearwater Forest: 1-node, 2x Intel(R) Xeon(R) Clearwater Forest CPU, 288 cores, HT NA, Turbo On, Total Memory 1536GB (24x64GB DDR5), 1x Gigabit Network Connection, 2x Ethernet Controller, 1x hard drive, as estimated by SPECcpu®2017 int-rate, gcc8.1, estimated by Intel as of August 2025. 8280: 1-node, 2x Intel(R) Xeon(R) Platinum 8280 CPU @ 2.70GHz, 28 cores/205W, HT On, Turbo On, Total Memory 384GB (12x32GB DDR4 2933 MT/s [2933 MT/s], 2x Ethernet Connection, 2x Ethernet Controller, 1x hard drive, as estimated by SPECcpu®2017 int-rate, gcc8.1, estimated by Intel as of April 2024. Results may vary. |
| #1 product security assurance | https://www.intel.com/content/www/us/en/security/security-as-a-component-of-tech.html#:~:text=Independent research names Intel a,Intel topped the competitive assessment. |
| Over 90% cell utilization | https://www.intel.com/content/dam/www/central-libraries/us/en/documents/2024-02/intel-tech-clearwater-wp.pdf |
| Reduce losses 4-5% | VLSI-symposium https://www.intel.com/content/dam/www/central-libraries/us/en/documents/2024-02/intel-tech-clearwater-wp.pdf |
Experience Zone: Clearwater Forest for Cloud & 5G
| Claim | Claim Details/Citation |
|---|---|
| Improves standard cell utilization by up to 10% and ISO-power performance by up to 4% | Intel PowerVia Technology: Backside Power Delivery for High Density and High-Performance Computing | IEEE Conference Publication | IEEE Xplore. https://newsroom.intel.com/client-computing/powervia-test-shows-industry-leading-performance |
| Darkmontvs. Crestmont - μ Architecture Power & Performance | Performance varies by use, configuration and other factors. Results may vary. Power Efficiency Workload (Performance/CPU power (W) vs. Load) Pre-Production Xeon 6+ platform : 1-node, 2x Pre-production, 288 core Intel Xeon 6+ processor, Turbo On, Total Memory 1536GB (24x64GB DDR5 6400MT/s), BIOS BHSDCRB1.86B.3544.P97.2508180759, microcode 0x80000340, 2x Ethernet Controller 10-Gigabit X540-AT2, 1x 1.7T SAMSUNG MZQL21T9HCJR-00A07, CentOS Stream 9, 6.14.0-cwf.bkc.6.14.10.3.13.x86_64. Test by Intel as of Sep 19 2025. 6780E: 1-node, 2x Intel(R)Xeon(R) 6780E, 144 cores, 330W TDP, Turbo On, Total Memory 1024GB (16x64GB DDR5 6400MT/s), BIOS BHSDREL1.86B.3544.O05.2507310954, microcode 0x3000382, 2x Ethernet Controller 10-Gigabit X540-AT2, 1x 1.7T SAMSUNG MZWLJ1T9HBJR-00007, Ubuntu 24.04.3 LTS, 6.8.0-79-generic. Test by Intel as of Mon Sep 15 2025. Software: Power Efficiency workload; cpu power measured across loadline |
| 8:1server rack consolidation 750kW Fleet Power Reduction 71%Fleet Space Reduction 3.5xFleet Performance/W gain 2.3xvCPU/Rack gain | Claim, Integer Throughput: Use 20 racks (180 servers) of Intel® Xeon® Clearwater Forest based servers running Integer Throughput, while delivering similar performance, instead of 70 racks (1400 servers) of Intel® Xeon® 8280 based servers and save 750 kW of fleet power. Fleet power reduction based on 50 fewer Intel® Xeon® Clearwater Forest based racks at 15kW/Rack is 750kW (rack power distribution). Intel Xeon Clearwater Forest based servers delivers 7.81x higher performance per server and 3.5x higher fleet performance/watt vs Intel Xeon 8280 on Integer Throughput. Assumptions: 1x 42U, 15KW Rack, supporting 20x 2U rack servers, 1x TOR switch. Fleet power for 70 racks of Intel Xeon 8280 based servers estimated as of Aug 2025: Power: 1050kW (70 racks * 15kW/rack). Fleet power for 20 rack of Intel Xeon Clearwater Forest based servers estimated as of Aug 2025: Power: 300kW (20 racks * 15kW/rack). Clearwater Forest: 1-node, 2x Intel(R) Xeon(R) Clearwater Forest CPU, 288 cores, HT NA, Turbo On, Total Memory 1536GB (24x64GB DDR5), 1x Gigabit Network Connection, 2x Ethernet Controller, 1x hard drive, as estimated by SPECcpu®2017 int-rate, gcc8.1, estimated by Intel as of August 2025. 8280: 1-node, 2x Intel(R) Xeon(R) Platinum 8280 CPU @ 2.70GHz, 28 cores/205W, HT On, Turbo On, Total Memory 384GB (12x32GB DDR4 2933 MT/s [2933 MT/s], 2x Ethernet Connection, 2x Ethernet Controller, 1x hard drive, as estimated by SPECcpu®2017 int-rate, gcc8.1, estimated by Intel as of April 2024. Results may vary. |
Experience Zone: Panther Lake for Edge
Notices & Disclaimers
| The preceding presentation contains product features that are currently under development. Information shown through the presentation is based on current expectations and subject to change without notice. Results that are based on pre-production systems and components as well as results that have been estimated or simulated using an Intel Reference Platform (an internal example new system), internal Intel analysis or architecture simulation or modeling are provided to you for informational purposes only. Results may vary based on future changes to any systems, components,specificationsor configurations. Performance varies by use, configuration and other factors. Learn more at www.intel.com/PerformanceIndex . AI features may require software purchase, subscription or enablement by a software or platform provider, or may have specific configuration or compatibility requirements. Details at www.intel.com/AIPC . No product or component can be absolutely secure. Intel technologies may require enabled hardware, software or service activation. All product plans and roadmaps are subject to change without notice. Some images may have been altered or simulated and are for illustrative purposes only. Codec capab ilities may vary by device and configuration. Contact your manufacturer to understand the enabled hardware acceleration and codec capabilities for individual device. Built into the hardware, Intel® Thread Director is provided only in performance hybridarchitecture configurations of 12th Gen or newer Intel® Core processors; OS enablement is required. Available features and functionality vary by OS. Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy. While Wi-Fi 7 is backward compatible with previous generations , new Wi-Fi 7 features require PCs configured with Intel Wi-Fi 7 solutions, PC OEM enabling, operating system support, and use with appropriate WiFi 7 routers/APs/gateways. 6 GHz Wi-Fi 7 may not be available in all regions. Performance varies by use, configuration, and other factors. For details on performance claims, learn more at www.Intel.com/performance-wireless . SPE C®,SPECrate® and SPEC CPU® are registered trademarks of the Standard Performance Evaluation Corporation. See http://www.spec.org/spec/trademarks.html for more information. © Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others. |