Skip to main content

Exporting benchmarks v2



  • Thomas D.
    Threadripper 3960X Stock, 64 GB 2666 ECC.

    Tiff 16 Bit, 2x W8100 GPU: 18 sec. 90° both

    Tiff 16 Bit, 1x RTX 5000 GPU: 24 sec. 65°

    Tiff 16 Bit, CPU: 87 Sec.

    From a Perfomance point CO is a Strange piece of Software.
  • Cary Hatakeda

    Can you post the link for the original zip file to download to do these tests.

  • Igor Dmitriev

    Updated links to new forum format

  • Andrea wee

    with the new phundervolt, I am now no longer able to undervolt my zbook. 


    2286m 128Gb ram with RTX5000

    CPU seems to idle at @26% when using GPU. 

  • Whitesnake

    Ryzen 3900X + Radeon VII + 32 GB RAM (3800 CL16) + very very fast SSD + C1 v12:

    CPU+GPU+TIFF: 10

    Before I sold my Mac Mini:

    Mac Mini i7 (Hexa-Core), 32 GB RAM + Vega 56 + C1 v12:

    CPU+GPU+JPG: 35
    CPU+GPU+TIFF: 21

    I think the Radeon VII is the fastest GPU for C1.

  • Ladislav Starý

    iMac 27" late 2015, i5 3.3 GHz, AMD Radeon R9 M395, Capture One 20



    JPEG: 76 s

    TIFF: 65 s


    only CPU:

    JPEG: 140 s

    TIFF: 132 s


  • Ladislav Starý

    iMac 27" 2019, i5 3,7 GHz, AMD Radeon Pro 580X 8GB, 40 GB RAM DDR4, Capture One 20


    JPEG: 50 s

    TIFF: 39 s


    only CPU:

    JPEG: 77 s

    TIFF: 78 s


  • Robert Whetton

    Been a couple of years. Thought I'd throw in some numbers with V20
    Spec is still the same
    Ryzen 1700
    R9 Fury
    32GB RAM

    GPU: 0:34

    GPU: 0:31

    GPU: 0:31

    Upgraded GPU to a Vega 64
    GPU: 0:27

  • Sebastian Cohen

    C1 v20.04 / WIN10
    3900XT / 32GB DDR4-3200 / GTX1080 / EVO970 Pro

    JPEG CPU+GPU = 0:43
    JPEG CPU only = 1:33

    TIFF CPU+GPU = 0:30
    TIFF CPU only = 1:22


  • Igor Dmitriev

    Windows PC (Win10 b2004)
    CaptureOne 21 (14.2)
    CPU – AMD Ryzen-3600X (6-core, 12-threads)
    GPU – NVidia GTX 1080

    CPU+GPU – 39s
    CPU only – 93s
    The GPU speed up factor is about 2.38x.

    CPU+GPU – 26s
    CPU only – 79s
    The GPU speed up factor is about 3.04x.

  • Oscar Lai

    Lurking around a while, set up my new desktop back in 2020 Dec and finally have time to test. Contribute my parts to the community, as I decided to buy 2nd hand Radeon card back in the fall of 2020 after referencing to this thread (decide between Nvidia vs AMD card, and between the new RX 6xxx and Vega series).

    Windows 10 Professional

    OS build 19042.1348

    Version 20H2

    MB - Asus Crosshair VIII Hero WIFI

    AMD 3900XT no OC

    64gb DDR 3600 small OC to 3733

    MSI Radeon RX Vega 64 8gb Liquid Cooled edition

    Samsung 970 pro 512gb m c drive

    Samsung 860 pro 1tb d drive

    Fresh Windows 10 pro install, with Office 2016 and Capture One 21 v.



    1st run - 37.98s

    2nd run - 37.13s

    3rd run - 37.20s

    CPU only - 73.22s; only have 1 run

    Did not try TIFF output as I know it will be faster from all others' result above

    Vega 64 LC edition is a few seconds slower than Vii or Frontier Edition, but the cost is much lower. Hope this info will be helpful to choose between the new RX 6xxx services and the previous generation from AMD.

  • Brian Jones

    I've updated my benchmarks for the 4 Macs that are my production computers. The 2013 Mac Pro and 2018 MPB have been replaced by the M1 MBPs.

    All times are on C1 14.4.1 Interestingly the times are slower than the last test on 12.2

    2021 MBP M1 Pro 16core video 16gb

    Tiff with GPU 31.08

    Tiff Without 54.52

    JEPG with GPU 39.05

    Jpeg without 1:25.35


    2021 MBP M1 Max 32 video core 32gb

    Tiff with gpu 18.65

    Tiff without 46.08

    Jpeg with 25.63

    Jpeg without 1:02.40


    2018 MPB i9

    Tiff with epgu 29.85

    Tiff egpu preferred 34.33

    Tiff gpu 57.0   

    Tiff no gpu 1:20.31

    Jpeg egpu 51.0

    Jpeg no gpu 1:14.05 

    Jpeg epgu preferred 48.95

    Jpeg gpu 1:13.72


    2013 Mac Pro 3.5ghz 6 core D500

    Tiff GPU 34.71

    Tiff no gpu 1:44.31

    Jpeg gpu 55.40

    Jpeg no gpu 2:08.08


  • Matthew Varney

    Results from version 15.2 and the new Mac Studio.

    2022 Mac Studio
    macOS 12.3.1
    M1 Max (10 core CPU, 32 core GPU)
    32GB RAM
    Internal SSD
    C1 v15.2.0

    JPEG CPU+GPU: 26s (0:26)
    JPEG CPU Only:  61s (1:01)

    TIFF CPU+GPU: 19s (0:19)
    TIFF CPU Only:  54s (0:54)

    Mac Pro 5,1
    macOS 10.14.6
    X5675, 12 cores, 3.06 GHz
    48GB RAM
    Vega 64 8GB
    C1 v15.2.0

    JPEG CPU+GPU: 51s (0:51)
    JPEG CPU Only:  118s (1:58)

    TIFF CPU+GPU: 27s (0:27)
    TIFF CPU Only:  101s (1:41)

    Asus Prime X470-Pro
    Windows 10 Pro 21H2
    Ryzen 7 3800X
    32GB DDR4 3600 CL16
    Vega 64 8GB (Sapphire Nitro+)
    NVMe SSDs
    C1 v15.2.0

    JPEG CPU+GPU: 34s (0:34)
    JPEG CPU Only:  80s (1:20)

    TIFF CPU+GPU: 17s (0:17)
    TIFF CPU Only:  73s (1:13)

    Best of three runs. Restarted Capture One between runs (this makes a difference).

  • Fernando Javier Giménez Cepero

    Capture one 16.1
    I7 920
    Gpu r9 280x 3Gb ram Gpu
    18gb ram ddr3
    Ssd sata ii

    CPU +Gpu
    jpeg 85 secs
    Tiff 72 secs

    CPU only jpg 285 secs

    I tried using 2 r9 280x without crossfire but had several crashes
    I manage to get 72 secs in cpu + 2 Gpu in jpegs

    I observed that the first 50 first secs the cpu load goes to 80-90% and the falls to 20% while the Gpu usage in windows only goes 2-3% in one Gpu. And nothing on the other. Only the ram is used in the 2 gpus

    Does anyone observed this behavior in using two gpus in windows?
    it doesn’t seem to be very efficient


  • BeO
    Top Commenter
    Notebook DELL XPS13
      (model 7390 2-in-1 from year 2020)
    NVMe disk drive
    RAM 16 GB
    CPU: Intel Core i7-1065G7 CPU @ 1.30GHz, 1498 Mhz, 4 Cores, 8 Logical Processors
    GPU: Intel(R) Iris(R) Plus Graphics
      OpenCL Compute Units : 64
      OpenCL CL_DEVICE_GLOBAL_MEM_SIZE : 6461 mb
      C1 ImageCore Benchmark: 0.268607
    Windows 10 Home 22H2 
    C1 version
    JPEG CPU+GPU: 02:50 (170s)
    JPEG CPU Only:  02:44 (164s)
    (best of two runs each. C1 not retarted in-between)
    Export Adjustments: "no output sharpening"

Please sign in to leave a comment.