Softpedia >Mac >System Utilities >Geekbench >  Changelog

Geekbench Changelog

What's new in Geekbench 6.3.0

Apr 11, 2024
  • Introduce support for Arm Scalable Matrix Extensions (SME) instructions.
  • Reduce Horizon Detection run-to-run variability.
  • Disable OpenCLOn12 on Windows.
  • Fix a crash that could occur on Meteor Lake laptops.

New in Geekbench 6.2.2 (Jan 10, 2024)

  • Add support for 16K pages on Linux/AArch64.
  • Improve hardware detection for recently released Macs.

New in Geekbench 6.2.1 (Oct 22, 2023)

  • Update target Android version to comply with Google Play requirements.

New in Geekbench 6.2.0 (Sep 12, 2023)

  • Introduce support for Windows on ARM.
  • Introduce support for RISC-V.
  • Add history and comparison features to Android and iOS.

New in Geekbench 6.1.0 (Jun 8, 2023)

  • Upgrade compilers to Clang 16 on all platforms.
  • Increase the workload gap from two seconds to five seconds.
  • Introduce support for SVE instructions.
  • Introduce support for AVX512-FP16 instructions.
  • Introduce support for fixed-point math.
  • Improve Background Blur and Horizon Detection multi-core performance.

New in Geekbench 6.0.3 (Apr 23, 2023)

  • Fix an issue where Geekbench may not display benchmark results on Windows.
  • Improve NVIDIA GPU detection under OpenCL.

New in Geekbench 6.0.2 (Apr 7, 2023)

  • Improve GPU detection.

New in Geekbench 6.0.1 (Mar 3, 2023)

  • Add an option to skip the Pro upgrade dialog at startup on Windows and macOS.
  • Fix visual issues that could occur on HiDPI displays on Windows.
  • Fix an issue where Geekbench did not display verification badges on Windows.
  • Fix an issue that could cause Geekbench to exit with an ASTCENC_ERR_BAD_CPU_ISA error on older hardware or on virtual machines.

New in Geekbench 6.0.0 (Feb 15, 2023)

  • New and Updated Real-World Tests:
  • Geekbench tests have always been grounded in real-world use cases and use modern. With Geekbench 6, we’ve taken this to the next level by updating existing workloads and designing several new workloads, including workloads that:
  • Blur backgrounds in video conferencing streams
  • Filter and adjust images for social media sites
  • Automatically remove unwanted objects from photos
  • Detect and tag objects in photos using machine learning models
  • Analyse, process, and convert text using scripting languages
  • Modern Data Sets:
  • We also updated the datasets that the workloads process so they better align with the file types and sizes that are common today. This includes:
  • Higher-resolution photos in image tests
  • Larger maps in navigation tests
  • Larger, more complex documents in the PDF and HTML5 Browser tests
  • More (and larger) files in the developer tests
  • True-to-Life Scaling:
  • The multi-core benchmark tests in Geekbench 6 have also undergone a significant overhaul. Rather than assigning separate tasks to each core, the tests now measure how cores cooperate to complete a shared task. This approach improves the relevance of the multi-core tests and is better suited to measuring heterogeneous core performance. This approach follows the growing trend of incorporating “performance” and “efficient” cores in desktops and laptops (not just smartphones and tablets).

New in Geekbench 5.5.1 (Feb 8, 2023)

  • Fix an issue that caused Geekbench to misreport CPU cluster core counts on Android.
  • Fix an issue that caused Geekbench to report memory speeds in MHz rather than MT/s.

New in Geekbench 5.5.0 (Jan 17, 2023)

  • Improve hardware detection on systems with heterogeneous CPU cores (e.g., Apple M1, Intel Alder Lake).
  • Fix a crash that could occur on systems with Intel Arc GPUs.
  • Fix an issue that prevented the OpenCL benchmark from running on Android 12 or later.
  • Fix an issue that could prevent the Vulkan benchmark from running on the latest GPU drivers.
  • Improve hardware detection on recently released hardware.

New in Geekbench 5.4.6 (Dec 2, 2022)

  • Improve hardware detection on recently released hardware.

New in Geekbench 5.4.5 (May 16, 2022)

  • Improve hardware detection on recently released hardware.
  • Fix a crash that could occur on Windows when biometric security features are enabled.

New in Geekbench 5.4.4 (Dec 21, 2021)

  • Improve hardware detection on Apple Silicon Macs.
  • Fix a crash that could on Windows and Linux with the latest Vulkan 1.2 drivers.

New in Geekbench 5.4.3 (Nov 5, 2021)

  • Fix a crash that could occur in the GPU Compute Benchmark on Android 12.
  • Fix frequency detection on Alder Lake CPUs.

New in Geekbench 5.4.2 (Oct 29, 2021)

  • Update device information to include the latest iPhones and iPads.
  • Report GPU core count for Metal on Apple Silicon Macs.
  • Fix crashes on Android that could occur when running the OpenCL Compute Benchmark.

New in Geekbench 5.4.1 (May 3, 2021)

  • Improve system information reporting on Linux.
  • Fix a crash on Android that could occur after a benchmark finishes.

New in Geekbench 5.4.0 (Mar 12, 2021)

  • Preview support for Linux/ARM and Linux/RISC-V.
  • Fix dark mode issues on iOS.
  • Fix Vulkan comparison page issues on Android.

New in Geekbench 5.3.2 (Feb 7, 2021)

  • Report memory transfer rate on macOS and Windows.
  • Improve Vulkan error handling.
  • Improve timer error handling.
  • Fix an issue where the Preferences dialog was empty on Apple Silicon Macs.

New in Geekbench 5.3.1 (Nov 15, 2020)

  • Improve hardware detection on Apple Silicon Macs.
  • Fix a bug that prevented the Metal Compute Benchmark from running on Apple Silcion Macs.

New in Geekbench 5.3.0 (Nov 11, 2020)

  • Add support for Apple Silicon Macs.
  • Add support for VAES256 instructions.

New in Geekbench 5.2.5 (Oct 19, 2020)

  • Update result comparison database.

New in Geekbench 5.2.4 (Oct 5, 2020)

  • Fix "internal timer error" error messages.

New in Geekbench 5.2.3 (Oct 5, 2020)

  • Improve processor identification on Windows on ARM devices.
  • Fix a bug that prevented benchmark comparisons from working on iOS.

New in Geekbench 5.2.2 (Oct 5, 2020)

  • Bug fixes.

New in Geekbench 5.2.1 (Oct 5, 2020)

  • Fix a crash that could occur when uploading results to the Browser.
  • Fix a memory leak in the Vulkan Compute Benchmark.

New in Geekbench 5.2.0 (Jun 12, 2020)

  • Re-introduce support for 32-bit Android devices. Geekbench 5.0 and 5.1 only support 64-bit devices, in part because Geekbench 5 uses large datasets that can quickly exhaust available memory in multi-core mode on 32-bit devices. However, 32-bit Android devices continue to be popular with users who have been asking us to support these devices. Geekbench 5.2 re-introduces support for 32-bit Android devices. 32-bit support comes with a limitation – due to limited memory, 32-bit devices can only run up to 4 threads in multi-core workloads.
  • Add support for Vulkan 8-bit storage types. Vulkan, unlike other Compute APIs, does not support 8-bit storage types except through an extension. Geekbench 5.0 worked around this limitation by packing 8-bit values into 32-bit storage. This technique makes efficient use of memory at the cost of runtime overhead. Geekbench 5.2 can takes advantage of 8-bit storage type extensions, removing the need to use 32-bit storage on devices that support the 8-bit extension. Vulkan Compute Benchmark scores will be higher on devices that support the 8-bit storage extension.
  • Optimize Compute Benchmark transfer functions. The Compute Benchmark transfer functions transfer data to and from the GPU during the Compute Benchmark. If these functions take too long to run, then the GPU may “throttle down” to reduce power consumption. Geekbench 5.2 optimizes these functions to reduce the likelihood that the GPU will “throttle down” and affect Compute Benchmark scores.
  • Fix crashes that could occur when running the Compute Benchmark on Android.
  • Fix display issues that could occur when using Dynamic Type on iOS.
  • Geekbench 5.2 includes several changes that affect Compute Benchmark performance. We recommend users not compare Geekbench 5.2 Compute Benchmark scores with Geekbench 5.0 or Geekbench 5.1 Compute Benchmark scores.
  • Geekbench 5.2 CPU Benchmark scores are compatible with Geekbench 5.1 CPU Benchmark scores.

New in Geekbench 5.1.1 (Jun 12, 2020)

  • Geekbench 5.1.1 fixes issues that could prevent the Metal Compute Benchmark from working properly.

New in Geekbench 5.1.0 (Dec 24, 2019)

  • CPU Benchmark Changes:
  • Geekbench 5.1 includes the following changes to the CPU Benchmark:
  • Build Geekbench 5 for Android with Android NDK r21.
  • Build Geekbench 5 for Linux, Windows with Clang 9.0.
  • Build Geekbench 5 for iOS, macOS with Xcode 11.2.
  • Improve AES-XTS workload performance on processors with AVX512 support.
  • Improve Machine Learning workload performance on processors with AVX support.
  • Improve Image Inpainting workload performance on Linux.
  • Compute Benchmark Changes:
  • Geekbench 5.1 includes the following changes to the Compute Benchmark:
  • Improve Depth of Field workload performance on Vulkan.
  • Improve Horizon Detection workload performance on Vulkan.
  • Improve GPU buffer selection for Metal workloads on iOS, macOS.
  • Improve buffer management in Metal workloads on iOS, macOS.
  • Consolidate command buffers in Vulkan workloads, improving performance.
  • Disable bounds checking in Vulkan buffers, improving performance.
  • Comparing Geekbench 5 Scores:
  • Geekbench 5.1 is built with new compilers, and includes changes to both the CPU and Compute Benchmarks. These changes mean Geekbench 5.1 scores will be higher than Geekbench 5.0 scores. As a result, we recommend users not compare Geekbench 5.0 and Geekbench 5.1 results.

New in Geekbench 5.0.3 (Oct 21, 2019)

  • geekbench 5.0.3 includes the following changes:
  • Improve compatibility with macOS 10.15 Catalina.
  • Add more devices to the built-in comparison charts.
  • Fix a validation error with the ORB/Vulkan workload on Intel GPUs.
  • Geekbench 5.0.3 is a free update for all Geekbench 5 users.

New in Geekbench 5.0.2 (Sep 26, 2019)

  • Add support for Dark Mode on iOS 13.
  • Add support for CentOS 7 and RHEL 7.
  • Improve HiDPI support on Windows.
  • Improve Vulkan support on Linux.

New in Geekbench 5.0.1 (Sep 12, 2019)

  • Fix a crash that could occur when running the Vulkan Compute Benchmark on an AMD RX 5700 GPUs.
  • Fix an issue where the built-in comparison charts could display Geekbench 4 results instead of Geekbench 5 results.

New in Geekbench 5.0.0 (Sep 3, 2019)

  • CPU Benchmark:
  • The Geekbench 5 CPU Benchmark includes new benchmark tests that model the challenges your system faces when running the latest applications. These tests use cutting-edge technologies, including machine learning, augmented reality, and computational photography.
  • Geekbench 5 also increases the memory footprint of existing workloads to more accurately account for the effect memory performance has on CPU performance.
  • Finally, the Geekbench 5 CPU Benchmark includes new modes of multi-threaded benchmarks, allowing threads to work co-operatively on one problem rather than separately on different problems. With the addition of different threading models, Geekbench 5 better captures the performance of different multi-threaded applications on personal computing devices.
  • GPU Compute Benchmark
  • Geekbench 5 includes several improvements to the GPU Compute Benchmark.
  • The most exciting change is that the Compute Benchmark now supports Vulkan, along with CUDA, Metal, and OpenCL. Vulkan is the next-generation cross-platform graphics and compute API. Vulkan Compute Benchmarks are available on Android, Windows, and Linux.
  • The Compute Benchmark also includes new benchmark tests that model algorithms that are GPU accelerated in modern applications. These include computer vision tasks such as Stereo Matching, and augmented reality tasks such as Feature Matching.
  • Dark Mode:
  • Geekbench 5 includes a refreshed results interface with full support for Dark Mode on macOS 10.14. Support for Dark Mode on iOS 13 will be available later this year.
  • 64-Bit:
  • Geekbench 5 is 64-bit only, dropping support for 32-bit processors and operating systems. Geekbench 5 does not include any of the compromises required to run on 32-bit systems. This enables Geekbench 5 to include more ambitious benchmark tests with larger data sets and longer running times.

New in Geekbench 4.4.2 (Aug 30, 2019)

  • Fix a crash that could occur on systems with more than 128 cores.
  • Improve system information reporting on systems with recent AMD and Intel processors.

New in Geekbench 4.4.1 (Jul 23, 2019)

  • Update comparison results to include the latest Android, iOS devices
  • Geekbench 4.4.1 is a free update for all Geekbench 4 users.

New in Geekbench 4.4.0 (Jul 17, 2019)

  • Fix an issue with the Particle Physics OpenCL implementation, which caused Geekbench to overestimate performance on recent AMD and Intel GPUs. Since this fix can change OpenCL scores, we recommend users exercise caution when comparing OpenCL scores between Geekbench 4.3 and Geekbench 4.4.
  • This issue does not affect the Particle Physics implementations for other Compute APIs, nor does it affect the Compute Benchmark scores for those other APIs.
  • Fix an issue where Geekbench would not identify certain Intel processors.

New in Geekbench 4.3.4 (May 25, 2019)

  • Fix issues which caused Geekbench to misidentify some hardware.

New in Geekbench 4.3.3 (Jan 25, 2019)

  • Fix issues which caused Geekbench to misidentify some hardware.

New in Geekbench 4.3.2 (Dec 17, 2018)

  • Fix a crash that could occur on startup on iOS devices.
  • Fix an issue where Geekbench may not identify the Mac mini (Late 2018).

New in Geekbench 4.3.1 (Nov 9, 2018)

  • Fix Dropbox support on iOS and macOS.
  • Fix an issue that prevented Geekbench from measuring the processor frequency on iOS.
  • Fix a crash that could occur when running the Compute Benchmark on iOS devices with an A9 or A9X SoC running iOS 12.

New in Geekbench 4.3.0 (Sep 13, 2018)

  • Remove 32-bit benchmarks on iOS and macOS. iOS no longer supports 32-bit applications, and macOS warns users when applications include 32-bit components. Users interested in running 32-bit benchmarks on iOS or macOS should run Geekbench 4.2.3 (benchmark results are comparable between Geekbench 4.2.3 and 4.3.0).
  • Fix an issue that prevented AVX512 workloads from running on macOS.
  • Fix an issue that could cause runtime failures with Metal workloads on upcoming versions of iOS and macOS.
  • Fix an issue that could cause the LLVM workload to hang, especially on systems with more than 10 cores.

New in Geekbench 4.2.3 (May 24, 2018)

  • Improve support for iMac Pro.
  • Fix an issue that caused Geekbench to misreport the L3 cache on Ryzen, Threadripper processors.

New in Geekbench 4.2.2 (Feb 15, 2018)

  • Improve the design and functionality of the in-app comparison charts.
  • Update comparison chart results for CPU, Compute, and Battery Benchmarks.
  • Fix an issue that prevented keyboard shortcuts from working on Windows.
  • Improve error handling for Compute Benchmark command-line switches.

New in Geekbench 4.2.1 (Feb 15, 2018)

  • Change Battery Benchmark to cancel when Geekbench moves to background, not when Geekbench moves back to foreground.
  • Update comparison results for CPU, Battery Benchmarks.

New in Geekbench 4.2.0 (Nov 3, 2017)

  • Battery Benchmark:
  • Geekbench 4.2 re-introduces the Battery Benchmark on Android and iOS. The Battery Benchmark is designed to measure the battery life of a device when running processor-intensive applications such as games.
  • The Battery Benchmark operates in one of two modes. The Partial Discharge mode runs a (relatively) short test over three hours and provides an estimate of battery performance. The Full Discharge mode runs a complete discharge and provides the most accurate assessment of battery performance but can take up to twenty hours to complete and requires a fully-charged battery to run.
  • The Battery Benchmark provides a battery score which represents how much work the device can complete on a single battery charge. Like all Geekbench scores, higher scores are better, with double the score representing double the work.
  • Metal Compute Benchmark:
  • Geekbench 4.2 includes several fixes that resolve issues with the Metal Compute Benchmark on discrete GPUs. Metal scores will be significantly higher on systems with discrete GPUs such as the AMD Radeon RX 580, and Metal results are now competitive with OpenCL and CUDA results. Metal scores will be the same on systems with integrated GPUs.
  • The underlying issue was that data transfers to and from the GPU could occur during the Metal benchmarks (these transfers do not happen during the OpenCL or CUDA benchmarks). The transfers caused the Metal benchmarks to appear slower since extra work was happening during the benchmark.
  • This issue only affected discrete GPUs since the transfers occurred over the PCIe bus which is significantly slower than the system memory used by integrated GPUs.

New in Geekbench 4.1.3 (Sep 30, 2017)

  • Redesign how system information is displayed.
  • Improve Geekbench for Linux installation experience.
  • Report the current power scheme on Windows.
  • Fix an issue that could prevent the OpenCL Compute Benchmark from running on Linux.
  • Fix an issue that could cause Geekbench to report frequencies, multipliers as 0 on Windows.
  • Fix an issue that could cause Geekbench to report the wrong cluster configuration on Android.
  • Fix an issue that could cause Geekbench to report a negative number for the CUDA device memory frequency.

New in Geekbench 4.1.2 (Sep 22, 2017)

  • Add native support for 64-bit Intel devices on Android.
  • Report the minimum, maximum processor frequency and processor multiplier on Windows.
  • Report the frequency of both the big and LITTLE cores on Android.
  • Fix an issue that could prevent release notes from displaying on macOS.
  • Fix an issue that caused Geekbench to misreport system information on recent Samsung devices.
  • Fix an issue that caused Geekbench to misreport cache information on recent AMD processors.

New in Geekbench 4.1.1 (Jul 28, 2017)

  • Reduces Memory Latency memory usage on 32-bit devices.
  • Works around an issue where Windows GPU drivers do not include all of the components necessary to run OpenCL.
  • Fixes an issue that caused HDR to allocate more memory than needed.
  • Fixes an issue that could prevent the Compute Benchmark from running on recent NVIDIA GPUs under macOS.
  • Fixes crashes that could occur when loading malformed documents.
  • Fixes several crashes in the Android and iOS interfaces.

New in Geekbench 4.1.0 (Mar 31, 2017)

  • Changes:
  • Improve support for Ryzen processors
  • Fix memory leaks in OpenCL workloads
  • Fix a crash that could occur on Skylake-E processors
  • Fix crashes that could occur when running Compute Benchmarks on low-end GPUs.
  • CPU Workload Changes:
  • Build Geekbench for Linux with Clang 3.9.
  • Build Geekbench for Android with Android NDK 13b.
  • Build Geekbench for iOS, macOS with Xcode 8.2.
  • Enabled AArch32 cryptography instructions in Android ARMv7 build.
  • Change Memory Latency workload to avoid cache hits on Cortex A72, A73.
  • Report Memory Latency workload performance in nanoseconds.
  • Add AVX512 implementations to FFT, GEMM workloads.
  • Disable SQLite cache statistics to improve multi-core scalability.
  • Disable LLVM runtime assertations to improve multi-core scalability.
  • Users can expect a 2% increase in single-core scores, and at least a 5% increase in multi-core scores. Note that the multi-core score increase depends on the number of processor cores – systems with more cores will see a larger increase in the multi-core score.
  • Compute Workload Changes:
  • Consolidate optimization code for CUDA, Metal, and OpenCL workloads.
  • Convert Histogram Equalization, Sobel to use RenderScript intrinsics.

New in Geekbench 4.0.4 (Jan 13, 2017)

  • Fixes a crash that could occur after transferring the boot drive from one system to another.
  • Fixes a crash that occurred when reading malformed or corrupted system information tables.
  • Adds Chinese localization to Geekbench for Android.

New in Geekbench 4.0.3 (Nov 15, 2016)

  • Upgrades OpenSSL library to OpenSSL 1.0.2j.
  • Fixes a number of minor Android interface issues.

New in Geekbench 4.0.1 (Sep 16, 2016)

  • Adds support for OS X 10.10.
  • Adds support for the latest iOS and Android devices.
  • Fixes an issue where single-core scores are lower than expected when the CPU Benchmark is run through the GUI on dual-core Macs.
  • Fixes an issue where benchmark results were flagged as invalid or corrupted on some Windows systems.
  • Fixes an issue where the Compute Benchmark interface was enabled when no compatible compute devices were available.
  • Fixes an issue where Geekbench identified macOS 10.12 as Mac OS X 10.12.
  • Fixes an issue where the --workload-gap switch was being ignored.
  • Fixes an issue where Geekbench would generate block sizes that were too large for the current CUDA device, causing the Compute Benchmark to crash.

New in Geekbench 4.0.0 (Sep 16, 2016)

  • Geekbench 4 introduces several new and updated CPU workloads. These workloads are larger and more ambitious than the workloads in Geekbench 3, and are designed to put more stress on the CPU, its cache, and its memory subsystem. These updated workloads include several well-known codebases that are used every day on mobile devices, such as LLVM, SQLite, and PDFium. These updated workloads model real-world tasks and applications, and provide an objective measure of the performance of the CPU in your phone or laptop. A complete description of the CPU workloads, along with details on the runtime and scoring mechanisms, is available in the Geekbench 4 CPU Workloads PDF.
  • Geekbench 4 also introduces new GPU Compute workloads. These workloads measure the computational performance of GPUs. More and more applications use the GPU instead of the CPU for better performance or lower power usage. Geekbench 4 includes 8 GPU Compute workloads and include tasks such as image processing, computational photography, and computer vision, all of which are a natural fit for highly-parallel GPU architectures. Again, a complete description of the GPU Compute workloads, along with details on Compute API support, runtime and scoring mechanisms, is available in the Geekbench 4 GPU Compute Workloads PDF.

New in Geekbench 3.4.1 (Feb 15, 2016)

  • Geekbench 3.4.1 contains an important security fix for OS X and is recommended for all OS X users:
  • Changed to secure connections to download update information and release notes.
  • Updated comparison chart design to improve readability.
  • Updated Android, iOS comparison devices.

New in Geekbench 3.4.0 (Feb 15, 2016)

  • Added support for Intel SHA-NI instructions for the SHA-1 workload.
  • Added support to detect Low Power Mode on iOS 9.
  • Fixed L4 cache reporting on systems without an L4 cache.
  • Fixed errors that could occur when uploading results from Intel NUC systems.
  • Fixed interface issues on iOS 9.

New in Geekbench 3.3.4 (Jun 13, 2015)

  • Bug fixes.

New in Geekbench 3.3.2 (Mar 17, 2015)

  • Reduced AES multi-core score variability on systems with two or more NUMA nodes.
  • Fixed crashes that occurred in low memory situations on Android.
  • Fixed a bug that caused benchmark results to print incorrectly on OS X.
  • Fixed sharing benchmark results using "Share via Gmail" on Android Lollipop.
  • Fixed bugs that prevented the battery test from starting automatically on certain Android devices.
  • Fixed a bug that could prevent Geekbench from reporting the battery level on Android.
  • Fixed bugs that could cause the battery test to crash on iOS.
  • Fixed a crash that could occur when viewing battery test results on iOS.
  • Fixed a bug that prevented users from adding battery test results to their Geekbench Browser account.

New in Geekbench 3.3.0 (Dec 15, 2014)

  • Added new battery test for Android, iOS.
  • Added a brief summary to "Share Results" email on iOS.
  • Addressed 64-bit code generation issues on Android/AArch64.
  • Fixed a crash that occurred on Windows 10.
  • Fixed a crash that could occur on 32-core systems.
  • Reduced the memory footprint of the BlackScholes workload.

New in Geekbench 3.2.2 (Oct 7, 2014)

  • Added support for iOS 8, iPhone 6, and iPhone 6 Plus.
  • Added benchmark comparison charts on iOS.
  • Added support for High DPI mode on Windows.
  • Fixed code signing issues on OS X Mavericks, Yosemite.

New in Geekbench 3.2.1 (Oct 7, 2014)

  • Fixed crashes that could occur on Intel-based Android devices.

New in Geekbench 3.2.0 (Sep 9, 2014)

  • Added support for AArch32 processors on Android.
  • Added benchmark comparison charts on Android.
  • Redesigned benchmark results view to increase information density.

New in Geekbench 3.1.6 (Apr 24, 2014)

  • Bug fixes.

New in Geekbench 3.1.5 (Mar 11, 2014)

  • Added support for BlackBerry 10.
  • Added support for Android devices with MIPS processors.
  • Added Android CPU governor to system information.
  • Added L4 cache information to system information.
  • Fixed an issue where results uploaded to Dropbox were given meaningless names.

New in Geekbench 3.1.4 (Jan 9, 2014)

  • Added support for the Mac Pro (Late 2013).
  • Added the ability to export benchmark results to XML.

New in Geekbench 3.1.3 (Dec 11, 2013)

  • Added support for the iMac (Late 2013) and the MacBook Pro (Late 2013).
  • Added support for the latest Android and iOS devices.
  • Stress test now works as expected and uses approximately 100% of processor resources.
  • Processor information is now more accurate on Android devices with an Intel processor.
  • Fixed an issue where Geekbench mistook the Nexus 7 (2013) for the Nexus 7 (2012).
  • Fixed an issue where standalone mode did not work on OS X.
  • Fixed an issue where 64-bit iOS devices were reported as 32-bit iOS devices.
  • Fixed an issue where processor frequency could be misreported on Linux.

New in Geekbench 3.1.2 (Sep 21, 2013)

  • Re-introduced 64-bit benchmarks on iOS.
  • Removed support for iOS 6.

New in Geekbench 3.1.1 (Sep 21, 2013)

  • Removed 64-bit benchmarks on iOS, fixing a crash that occurred on iOS 6.

New in Geekbench 3.1.0 (Sep 19, 2013)

  • Enabled standard optimizations for STREAM workloads.
  • Reduced BlackScholes memory footprint.
  • Reduced STREAM memory footprint.

New in Geekbench 3.0.2 (Aug 21, 2013)

  • Fixed a bug that caused updates to fail with a "The update is improperly signed." message.
  • Fixed a typo in the Dropbox dialog box.
  • Fixed a misaligned icon on the iPad 2, iPad mini.

New in Geekbench 3.0.1 (Aug 21, 2013)

  • Added support for OS X 10.6.
  • Fixed a bug that caused Geekbench to crash on OS X 10.7.

New in Geekbench 2.4.3 (Apr 12, 2013)

  • Added support for sharing benchmark results with other applications on BlackBerry 10.
  • Improved interface layout on BlackBerry 10.
  • Improved processor model detection on BlackBerry 10.
  • Fixed a bug where system information was invisible on the BlackBerry Q10.
  • Fixed a bug where stress test output did not appear on the command line.
  • Fixed a bug where Geekbench misreported the processor frequency on BlackBerry 10.
  • Fixed a bug where Geekbench didn't prevent the screen from sleep when running benchmarks on BlackBerry 10.
  • Fixed a bug that could cause uploads to fail when using a proxy.
  • Fixed a bug that could cause uploads to fail on older hardware.

New in Geekbench 2.4.2 (Mar 8, 2013)

  • Ported Geekbench to BlackBerry 10.
  • Added "Export License File" to Geekbench 2 Pro.
  • Added support for iMac (Late 2012).
  • Added support for MacBook Pro (Retina Early 2013).
  • Added a comparison chart to the benchmark results on Android.
  • Added support for sharing benchmark results with other applications on Android.
  • Fixed a bug where Geekbench misidentified Qualcomm Snapdragon S4 processors.
  • Fixed a bug that could cause unwanted characters to appear in messages.
  • Worked around an issue that could cause Geekbench to underreport performance on Android 4.0.0 through 4.0.3.

New in Geekbench 2.4.0 (Nov 16, 2012)

  • Added support for Mac mini (Late 2012).
  • Added support for iPad (4th generation), iPad mini, and iPod touch (5th generation).
  • Added support for Nexus 4 and Nexus 10.
  • Added progress view to track benchmark progress on Android.
  • Added localizations on Android and iOS.
  • Removed the need to run Geekbench as root in order to gather accurate system information under Linux.
  • Improved support for Windows 8.
  • Improved support for Windows systems with more than 64 cores.
  • Improved support for systems with less than 512MB of memory.
  • Fixed a bug that misidentified the international iPhone 5.
  • Fixed a bug that caused benchmarks to cancel when the device was rotated on Android.
  • Disabled the idle timer that could cause the screen to sleep during benchmarks on iOS.
  • Refreshed results view design.

New in Geekbench 2.3.4 (Jul 11, 2012)

  • Added support for Mountain Lion and Gatekeeper.
  • Added support for Retina Display.
  • Added 'geekbench' tool to Geekbench for Linux.
  • Added support for Intel-based Android devices.
  • Improved support for Windows systems with more than 32 cores.
  • Improved results display on iPhone, iPod touch, and Android.
  • Improved handset and processor detection on Android.
  • Fixed spurious high-resolution timer errors on older Windows systems.

New in Geekbench 2.3.3 (Jun 13, 2012)

  • Renamed MacBook Pro (Retina) to match Apple's naming convention.

New in Geekbench 2.3.2 (Jun 12, 2012)

  • Added support for MacBook Air (Mid 2012).
  • Added support for MacBook Pro (Mid 2012).
  • Added preliminary support for MacBook Pro (15-inch Retina Display).

New in Geekbench 2.3.0 (Apr 11, 2012)

  • Removed support for PowerPC-based Macs.
  • Removed offline result management from tryout mode.
  • Added portable installs for Pro licenses.
  • Added support for Ivy Bridge processors.
  • Improved support for MacBook Pro (17-inch Mid 2009).
  • Improved "internal timer error" diagnostic message.

New in Geekbench 2.2.7 (Feb 20, 2012)

  • Fixed an unhandled exception on OS X 10.8 (Mountain Lion).
  • Fixed a bug that prevented "Check for Updates..." from working properly.
  • Fixed a bug that misidentified the iPhone 4 (CDMA).
  • Improved processor frequency detection on Windows.
  • Improved processor detection on Linux.

New in Geekbench 2.2.6 (Jan 19, 2012)

  • Fixed a hang that could occur when running benchmarks on Windows.
  • Fixed a bug that canceled benchmarks prematurely on Android.
  • Fixed a bug that misidentified some late model MacBook Pros.
  • Re-enabled multi-threaded tests on single-core systems.
  • Improved compatibility with Red Hat Enterprise Linux 5.
  • Improved upload error messages on Windows and Linux.
  • Improved handling of corrupted Geekbench files.

New in Geekbench 2.2.3 (Nov 3, 2011)

  • Removed support for Mac OS X 10.4.
  • Added support for the the MacBook Pro (Late 2011).
  • Added support for the iPhone 4S.
  • Improved performance on systems with less than 512MB of RAM.
  • Improved processor detection on Linux.
  • Improved compatibility with older Linux distributions.
  • Fixed divide-by-zero errors that occurred on Windows XP 64-Bit Edition.
  • Fixed floating-point exceptions that occurred on Debian Wheezy.
  • Fixed a deadlock that could occur when running benchmarks on Mac OS X and Windows.
  • Fixed a bug that caused the Mac App Store version to overreport performance.
  • Fixed a bug that could prevent uploading results to the Geekbench Result Browser.
  • Fixed processor core counts on computers with more than 64 cores.

New in Geekbench 2.2.2 (Jul 20, 2011)

  • Added support for Mac OS X 10.7 Lion
  • Added support for Intel Sandy Bridge processors.
  • Added support for iMac (Mid 2011).
  • Improved support for MacBook (Mid 2007) and Mac mini (Late 2009).
  • Fixed a crash that occurred when activating Geekbench with no open documents.

New in Geekbench 2.2.1 (Apr 19, 2011)

  • Updated the benchmark result interface.
  • Added support for MacBook Pro (Early 2011).
  • Fixed a bug that prevented users from claiming results in the Geekbench Result Browser.

New in Geekbench 2.1.13 (Mar 14, 2011)

  • Added support for MacBook Pro (Early 2011).
  • Fixed conflicts with Geekbench from the Mac App Store.

New in Geekbench 2.1.12 (Feb 11, 2011)

  • Fixed a crash that occurred when loading corrupted results.
  • Improved plain text result display.

New in Geekbench 2.1.11 (Jan 3, 2011)

  • Fixes some registration issues users could encounter.

New in Geekbench 2.2 Beta 2 (Nov 22, 2010)

  • Fixes the "build expired" error that some users encountered when running Geekbench.

New in Geekbench 2.2 Beta 1 (Nov 19, 2010)

  • Sports a unified interface (it's now one application instead of three).
  • Tweaked parts of the interface, such as updating the benchmark progress interface to provide more information about the current workload.
  • Built-in stress test.
  • The stress test runs Geekbench's multi-threaded processor workloads in a loop. This exercises your computer's processor, memory, and motherboard to try and uncover any hardware issues your computer might have.
  • Major hardware problems will cause obvious errors, but to help detect more subtle problems Geekbench calculates a stress test score for each loop iteration, and keeps track of the average, the top, and the latest iteration score. For example, if the average score is significantly lower than the top score, or the last score is lower than the average score, chances are your processor is running slower because your computer has a cooling problem.

New in Geekbench 2.1.10 (Nov 10, 2010)

  • Fixes some registration issues users could encounter.

New in Geekbench 2.1.9 (Nov 1, 2010)

  • Adds support for the new MacBook Air and MacBook Pro models.

New in Geekbench 2.1.8 (Oct 9, 2010)

  • Fixed a bug in processor identification on x86-based systems

New in Geekbench 2.1.7 (Sep 30, 2010)

  • Fixed a problem that prevented Geekbench from scaling beyond 32 cores.
  • Added support for Mac mini (Early 2010).
  • Added support for iMac (21.5-inch Mid 2010) and iMac (27-inch Mid 2010).
  • Added support for Mac Pro (Mid 2010).

New in Geekbench 2.1.6 (Apr 22, 2010)

  • Added Linux distribution reporting.
  • Added support for MacBook Pros (Early 2010).
  • Updated support for iMac (27-inch Late 2009).
  • Fixed a crash that occured on launch under Mac OS X 10.4.11.
  • Fixed a crash that could occur when submitting results under Mac OS X.
  • Fixed processor and core counts on Intel Core 2 Quad and Core i7 processors.
  • Fixed Solaris processor detection

New in Geekbench 2.1.5 (Mar 23, 2010)

  • added support for Windows Server 2008 R2
  • added support for iMac (Late 2009)
  • re-introduced support for Solaris 10
  • added the command-line version of Geekbench to Geekbench for Windows
  • corrected core and thread count for AMD processors
  • fixed a crash under VMWare Fusion 3 with Windows 7 as the guest OS
  • fixed an abnormal exit under Windows Server 2008 R2 running recent Intel processors
  • fixed a case where early-model PowerPC Macs were marked as Hackintoshes

New in Geekbench 2.1.4 (Aug 20, 2009)

  • Fixed a crash on Macs running Mac OS X 10.4.11

New in Geekbench 2.1.3 (Aug 3, 2009)

  • Added support for MacBook Pro (Mid 2009).
  • Added support for the latest AMD and Intel processors.

New in Geekbench 2.1.2 (Feb 27, 2009)

  • Added support for MacBook (Early 2009) and MacBook Pro (17-inch Early 2009).
  • Fixed a bug where PowerPC 64-bit results were flagged as invalid.
  • Fixed a bug where “threads” and “cores” labels were swapped in the results view.

New in Geekbench 2.1.1 (Feb 3, 2009)

  • fixed core/thread counting bugs for Intel Core i7 processors
  • fixed a startup crash that occurred under Vista's diagnostic mode
  • fixed a crash that occurred when running Geekbench for Windows under Wine
  • fixed a bug that exaggerated benchmark performance under Geekbench for Windows (64-bit version)
  • added support for MacBook (Late 2008), MacBook Air (Late 2008) and MacBook Pro (Late 2008)
  • added support for Intel Core i7 and AMD Phenom II processors
  • added the distinction between processor cores and processor threads
  • updated benchmark result user interface

New in Geekbench 2.0.19 (Sep 3, 2008)

  • Fixed a number of bugs relating to processor detection.

New in Geekbench 2.0.16 (Apr 30, 2008)

  • added preliminary support for iMac (Early 2008)
  • added better handling of corrupt SMBIOS strings
  • added the ability to save results on Windows
  • fixed a class of timeout errors that could occur when submitting results to the Geekbench Result Browser
  • improved support for machines running 32-bit operating systems with more than 4GB of RAM

New in Geekbench 2.0.15 (Apr 9, 2008)

  • improved support for the MacBook Air
  • improved support for Pentium 5xx and 6xx processors

New in Geekbench 2.0.14 (Mar 17, 2008)

  • Geekbench 2.0.14 features a number of system information changes, including the addition of BIOS information and changes to the way Geekbench reports motherboard information on Mac OS X.

New in Geekbench 2.0.13 (Mar 10, 2008)

  • added support for the MacBook (Early 2008) and the MacBook Pro (Early 2008)
  • added x86 processor database
  • improved logical/physical processor count detection
  • improved "Hackintosh" detection