Update 2025/12/22

• The PawnIO.sys driver conflict with third-party tools has been resolved. If you require a PawnIO installation for other applications, you may now install it. CapFrameX manages this component independently. Install latest .NET 9 runtime. Download here.
• Reworked CPU thread management
• Performance optimizations
• Reworked IGCL support (Intel GPUs and iGPUs) with multi adapter handling
• Fixed DIMM temperature sensors
• Fixed bug on Comparison tab when using standard MsBetweenPresents metrics
• Fixed bug when Drag&Drop captures in folder list
• Added PC Latency for Nvidia graphics cards. Feature is still beta state, reports NaN in some cases.
• Added voltage sensor for Nvidia GPUs
• Added monitor refresh rate for Nvidia GPUs
• Added D3D Dedicated GPU memory performance counter
• Reworked overlay entry defaults
• Added sorting overlay entries button
• Reworked sensor sorting
• Added selecting primary graphics adapter. Auto (default) filter removes iGPUs when at least one dGPU is detected. Restart CapFrameX after changing the primary adapter!

BENCHLAB Service

When using BENCHLAB service, unzip the folder in a suitable installation folder like C:\Benchlab Service or D:\Tools, then run the .bat script as admin. Don't install the service from the Download folder. Install latest .NET 9 runtime. Download here.

Update 2025/12/09

• Bugfix CPU loads (showing only 0 and 6 mostly)
• PawnIO.sys driver management via SCM (it's recommended to uninstall PawnIO)
• "Minimize to tray" option in settings menu
• Report GPU driver version AMD, Nvidia, and Intel

Enhancements

• OpenLibreMonitorLib support
  This beta adds support for OpenLibreMonitorLib.

Install .NET 9 for full library support: https://dotnet.microsoft.com/en-us/download/dotnet/9.0

• Integrated PawnIO installer
  The PawnIO installer is now built directly into the CapFrameX installer. No separate installation step is needed anymore.

• WinRing0.sys security issue resolved
  We have removed the dependency on WinRing0.sys, closing the related security risk.

• PresentMon updated to version 2.4
  The new PresentMon version adds support for Nvidia Multi Frame Generation (x2, x3, x4) when using the MsBetweenDisplayChange option in the settings menu.

What is the difference between MsBetweenDisplayChange and MsBetweenPresents?

• MsBetweenPresents measures the time between present calls from the application. This reflects how often the game submits frames.

• MsBetweenDisplayChange measures the time between actual displayed frames. This includes any generated frames (e.g., from Frame Generation). Because Multi Frame Generation produces additional frames that are not directly presented by the game, only MsBetweenDisplayChange can show the effective frame rate with FG x2, x3, or x4 enabled.

Update 2025/08/07

• New PresentMon version with ETW buffer overflow fix

Update 2025/08/04

New features

• Universal hybrid core detection for AMD (Performance + Dense cores) and Intel (Performance + Efficiency cores)
• Thread Affinity Controller working with AMD dense cores
• Support AMD Strix Point
• Experimental support Intel Nova Lake

Enhancements

• Eliminated lazy loading for capture files to resolve user-reported issues
• Performance optimization capture files management
• Performance optimization slider handling on Analysis tab (Real time update option)

Bugfixes

• Thread Affinity Controller fixed for Zen 5

New features

• Support Nvidia Blackwell
• Support AMD Strix Point
• Support PresentMon v2.3.1
• Frame time distribution chart

Important: This version is not compatible with Nvidia's Multi Frame Generation! We are working on a solution with Nvidia.

Blackwell support

Frame time distribution chart

Enhancements

• Lazy load capture files (aggregated file size > 512MB)
• Removed Windows Media Player dependency (NAudio library)

Bugfixes

• Fixed Zen 5 VID sensor readings
• Fixed frame time issues caused by ETW buffer overflow

When using BENCHLAB service, unzip the folder in a suitable installation folder like C:\Benchlab Service or D:\Tools, then run the .bat script as admin. Don't install the service from the Download folder. Install latest .NET 8 runtime. Download here.

Update 2025/04/15

• Bugfix capturing frame times when using XeFG
• Custom game name working again
• Custom CPU + GPU name on PMD Tab
• BENCHLAB support
• Windows service/client application architecture (see attached service installer)
• Unzip the folder in a suitable installation folder like C:\Benchlab Service or D:\Tools, then run the .bat script as admin. Don't install the service from the Download folder.

Important: Install latest .NET 8 runtime. Download here.

Update 2025/01/25

• Bugfix overlay metrics + performance optimization

Update 2025/01/21

• Graphical representation of MsBetweenDisplayChange times in frame time graph

Update 2025/01/18

• Bugfix overlay run history metrics when using MsBetweenDisplayChange

Update 2025/01/17

• Support Nvidia RTX 50 series
• Support DLSS 4 (Multi Frame Generation)
• Bugfix app crashing when importing FrameView logs
• Support Arrow Lake-H

Important: Enable MsBetweenDisplayChange metrics in option menu when using DLSS4!

Update 2025/01/12

• New MsBetweenDisplayChange metrics: real-time overlay metrics, Analysis + Comparison + Report tab

• MsBetweenDisplayChange metrics provide enhanced consistency when using frame interpolation technologies, offering a more accurate reflection of the user experience. This new option is disabled by default, but enabling it is strongly recommended for benchmarks with Intel's Arc B series and XeSS Frame Generation. Standard metrics fail to fully capture the true user experience, making MsBetweenDisplayChange metrics a valuable addition for precise performance evaluation.
• Bugfix MsBetweenDisplayChange metrics on Comparison tab

Important note: Nvidia's RTX 50 series + MFG will be supported soon!

MsBetweenDisplayChange metrics enabled

MsBetweenDisplayChange metrics disabled

Update 2025/01/11

• PresentMon v2.3.0 with tracking support for Intel XeSS XeFG and AMD Fluid Motion Frames

Update 2024/12/15

• Total Board Power sensor Intel Arc Battlemage

New features

• Support Intel Lunar Lake
• Support Intel Arc Graphics (130V, 140V)
• Experimental Support Intel Arc Battlemage
• New overlay real-time metrics

New features

• Support AMD Zen 5
• Support Intel Arrow Lake
• Thread Affinity Controller compatible with Arrow Lake core layout
• PresentMon v2.2 with new Start-to-PresentReturn / PresentReturn-to-PresentReturn frame time measurement approach
• New CPU Busy metric which indicates the duration the CPU was engaged in processing the frame before presenting it
• Added TBP Sim for AMD RDNA2 graphics cards

Image source: VideoCardz

Enhancements

• PMD metrics as floating point numbers with one decimal digit

Bugfixes

• Exception handling AMD ADLX API calls

Info

With the new PresentMon version the frame time measurement approach has changed from Present-to-Present to Start-to-PresentReturn / PresentReturn-to-PresentReturn. Taken from the PresentMon release notes:

"The majority of metrics are changed to use the time that the CPU started working on a frame as the reference point instead of the present() call, with values that are more aligned to measuring the quality of graphics applications (e.g., latency and duration of interaction and displayed frames). See README-ConsoleApplication.md for more details."

Unwinder (the author of RTSS):

"There is no best or preferable method. Both have their own different usage cases. Frame-start-to-frame-start frametime graph can be used to validate framepacing quality of latency oriented framerate limiting modes (low latency SK limiter mode, async/back edge sync RTSS limiter modes, NV CPL framerate limiter etc). Such graph should become "flat" when such framerate limiting strategy is in use. Present-to-present frametime graph can be used to validate framepacing quality of framerate limiters prioritizing presentation timings adjustment (latent sync or normal framerate limiter in SK, front edge sync or scanline sync in RTSS). Such graph is expected to jitter if latency oriented framerate limiting strategy is in use, but become "flat" if framerate limiter prioritize presentation timings adjustment. You may also switch between these two modes to determine which framerate limiting strategy is used by some other third party framerate limiters or in-game framerate limiters."

Update 2024/11/2

• Thread Affinity Controller compatible with Arrow Lake core layout
• Added TBP Sim for AMD RDNA2 graphics cards

New features

• Support Intel Arrow Lake
• PresentMon v2.2 with new Start-to-PresentReturn / PresentReturn-to-PresentReturn frame time measurement approach
• New CPU Busy metric which indicates the duration the CPU was engaged in processing the frame before presenting it

Image source: VideoCardz

Enhancements

• PMD metrics as floating point numbers with one decimal digit

Bugfixes

• Exception handling AMD ADLX API calls

Info

With the new PresentMon version the frame time measurement approach has changed from Present-to-Present to Start-to-PresentReturn / PresentReturn-to-PresentReturn. Taken from the PresentMon release notes:

"The majority of metrics are changed to use the time that the CPU started working on a frame as the reference point instead of the present() call, with values that are more aligned to measuring the quality of graphics applications (e.g., latency and duration of interaction and displayed frames). See README-ConsoleApplication.md for more details."

Unwinder (the author of RTSS):

"There is no best or preferable method. Both have their own different usage cases. Frame-start-to-frame-start frametime graph can be used to validate framepacing quality of latency oriented framerate limiting modes (low latency SK limiter mode, async/back edge sync RTSS limiter modes, NV CPL framerate limiter etc). Such graph should become "flat" when such framerate limiting strategy is in use. Present-to-present frametime graph can be used to validate framepacing quality of framerate limiters prioritizing presentation timings adjustment (latent sync or normal framerate limiter in SK, front edge sync or scanline sync in RTSS). Such graph is expected to jitter if latency oriented framerate limiting strategy is in use, but become "flat" if framerate limiter prioritize presentation timings adjustment. You may also switch between these two modes to determine which framerate limiting strategy is used by some other third party framerate limiters or in-game framerate limiters."

Update 2024/06/10

• Support AMD Zen 5 Granite Ridge
• Fixed FPS counter showing values for wrong process when multiple processes were detected

New features

• No new features for now

Enhancements

• UI/layout improvements for low display resolutions

Bugfixes

• Fixed missing TBP sensor (ADLX) for AMD graphics cards
• Bugfix minimize CX to tray

Update 2024/02/23

• Bugfix NVML PCIe throughput sensors

New features

• Updated PresentMon caputure service to v1.9.0, see PresentMon GitHub repository for more info.
• New metric: GPU Active Time (GPU Busy)
• GPU Active Time graph on Analysis tab. GPU Busy graph can be enabled via "Additional graphs".
• New overlay metrics: GPU Busy and GPU Busy Deviation. GPU Busy Deviation describes the deviation of GPU Active time from the frame time. The closer it is to 0% the more balanced the workload is.
• FPS <-> ms toggle on Analysis tab
• New real-time metrics: 1% and 0.2% Low Average
• More Powenetics v2 features
• PMD logs export (context menu)
• Mapping PMD data to frame time data points
• Smart data mapping via linear spline interpolation
• Real-time metrics reset button
• Updated AMD ADLX and Intel IGCL
• Optional ADL fallback (TBP Sim for RDNA2, Vega VRM temps etc.)
• Implementation network ping overlay entry
• Thread affinity controller (Intel hybrid architecture, AMD Ryzen with 2 CCDs)

Enhancements

• Performance optimization AMD ADLX readings
• Reset thread affinity to default when starting a new game
• Overlay entry showing current thread affinity state
• Better handling of integrated graphics (UHD Graphics and Iris Xe Graphics )

Bugfixes

• Bugfix detection error (Call of Duty MW2)
• Config files access exceptions (Moved folder from MyDocuments to AppData/Roaming)
• GPU PCIE Rx and Tx throughput unit

Update 2023/09/12

• Updated PresentMon caputure service to v1.9.2
• Bugfix detection error (Call of Duty MW2)

Update 2023/08/27

• Updated PresentMon caputure service to v1.9.0, see PresentMon GitHub repository for more info.
• New metric: GPU Active Time (GPU Busy)
  
• GPU Active Time graph on Analysis tab. GPU Busy graph can be enabled via "Additional graphs".
  
• New overlay metrics: GPU Busy and GPU Busy Deviation. GPU Busy Deviation describes the deviation of GPU Active time from the frame time. The closer it is to 0% the more balanced the workload is.
  
• FPS <-> ms toggle on Analysis tab
  
• Bugfix: GPU PCIE Rx and Tx throughput unit

Update 2023/07/15

• New real-time metrics: 1% and 0.2% Low Average

Update 2023/06/15

• More Powenetics v2 features
• PMD logs export (context menu)
• Mapping PMD data to frame time data points
• Smart data mapping via linear spline interpolation
• Real-time metrics reset button

PMD Analysis tab with export feature

Excel Export

Update 2023/03/25

• Updated AMD ADLX and Intel IGCL
• Better handling of integrated graphics (UHD Graphics and Iris Xe Graphics )
• Optional ADL fallback (TBP Sim for RDNA2, Vega VRM temps etc.)

Update 2023/03/08

• Reset thread affinity to default when starting a new game
• Overlay entry showing current thread affinity state

New features

• Implementation network ping overlay entry
• Thread affinity controller (Intel hybrid architecture, AMD Ryzen with 2 CCDs)

Thread Affinity

• Intel: default -> P-cores -> E-cores -> default
• AMD: default -> CCD0 -> CCD1 -> default

Warning: If a game has a large thread pool, forcing scheduling to half the number of threads can lead to increased context switches and thus noticeable frame times spikes. This was the case, for example, with Metro Exodus Enhanced Edition.

Toggle Thread Affinity

i9-12900K P-cores

i9-12900K E-cores

New features

• AMD Radeon RDNA 3 support
• ADLX implementation (e.g. GPU TBP)
• Support Intel Raptor Lake (Alder Lake Refresh) with Model ID 0xBF: i5-13400(F), i5-13500
• TBP Sim Sensor for Intel Arc GPUs

Enhancements

• Adjustable frame time and frame rate line graph color
• Slightly adjusted window size to also fit 768p screens

Bugfixes

• Wrong system info on PMD tab
• When Run History was enabled, switching overlay configs showed the overlay entry even on configs where it wasn't enabled

New features

• AMD Radeon RDNA 3 support
• ADLX implementation (e.g. GPU TBP)
• Support Intel Raptor Lake with Model ID 0xBF: i5-1300(F)

Enhancements

• Adjustable frame time and frame rate line graph color

Bugfixes

• Wrong system info on PMD tab