Softpedia >Windows >System >Benchmarks >Geekbench >  Changelog

Geekbench Changelog

What's new in Geekbench 6.2.0

Sep 12, 2023
  • Windows on ARM support – Geekbench 6.2 introduces Windows on ARM support. Now, users of ARM-based Windows devices, such as the Lenovo ThinkPad X13s and the Microsoft Windows Dev Kit 2023, can use Geekbench 6 to benchmark and compare their system performance. Windows on ARM support is included as part of Geekbench 6 for Windows – no separate download is required.
  • RISC-V support – Geekbench 6.2 introduces support for RISC-V-based systems. RISC-V is gaining traction as an open and customizable instruction set architecture. The addition of RISC-V support enables users to run Geekbench 6 to gain valuable performance insights in this rapidly evolving ecosystem. Geekbench 6.2 for Linux/RISC-V is available as a preview build.
  • History – Geekbench 6.2 adds history and comparison features on Android and iOS. These new features help users track and analyze their device’s performance over time or compare it with other devices directly in Geekbench.

New in Geekbench 6.1.0 (Jun 8, 2023)

  • Geekbench 6.1 features the following changes:
  • Upgrade to Clang 16 Geekbench 6.1 is built with Clang 16 on all platforms. Geekbench 6.1 also improves the optimization switches used when building Geekbench.
  • Increase workload gap Geekbench 6.1 increases the workload gap (the pause between workloads) from two seconds to five seconds. The increased workload gap minimizes thermal throttling and reduces run-to-run variability on newer smartphones such as the Samsung Galaxy S23.
  • Introduce support for SVE instructions Geekbench 6.1 includes SVE implementations of several image processing and machine learning functions.
  • Introduce support for AVX512-FP16 instructions Geekbench 6.1 includes AVX512-FP16 implementations of several image processing functions.
  • Introduce support for fixed-point math Geekbench 6.1 introduces fixed-point implementations of several image processing functions. Geekbench uses fixed-point math to implement some image processing functions on systems without FP16 instructions.
  • Improve Multi-Core Performance Geekbench 6.1 improves the multi-core implementations of the Background Blur and Horizon Detection workloads, especially on high-end desktop processors such as 12- and 16-core AMD Ryzens, AMD Threadrippers, and Intel Xeons.

New in Geekbench 6.0.0 (Feb 14, 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 5.4.0 (May 3, 2021)

  • Preview support for Linux/ARM and Linux/RISC-V Preview builds are available for Linux/ARM and Linux/RISC-V. Given the diversity of these platforms, it’s difficult to provide one binary build that works well everywhere. These builds have known issues (especially around gathering accurate system information) and may not work everywhere. That said, in our tests, both builds work well on current systems, from single-board computers to servers, with at least 1GB of RAM.
  • Fix dark mode issues on iOS.
  • Fix Vulkan comparison page issues on Android.

New in Geekbench 5.3.0 (Nov 11, 2020)

  • Geekbench 5.3 features the following changes:
  • Introduce support for Apple Silicon Macs. Geekbench 5.3 is a Universal binary and can now measure the native performance of Apple Silicon Macs and Intel Macs. Geekbench 5.3 can also measure the Rosetta 2 performance of Apple Silicon Macs.
  • Introduce support for VAES256 instructions. Geekbench 5.3 includes a VAES256 implementation of the AES-XTS workload, which will improve performance on processors that support VAES256 instructions but not VAES512 instructions (e.g., the AMD Zen 3 processors). Processors that support both VAES256 and VAES512 instructions (e.g., the Intel Ice Lake and Tiger Lake processors) will use the existing VAES512 implementation of the AES-XTS workload.

New in Geekbench 5.2.0 (Jun 25, 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.

New in Geekbench 5.1.1 (Apr 26, 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)

  • Geekbench 5.1, the latest version of Primate Labs’ popular cross-platform benchmark, is now available for download. This update improves the performance of the CPU and Compute Benchmarks across all systems, and is a recommended update for all Geekbench 5 users.

New in Geekbench 5.0.4 (Nov 6, 2019)

  • Re-introduce support for Windows on ARM devices.

New in Geekbench 5.0.3 (Oct 18, 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.

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 11, 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 4.4.1 (Jul 23, 2019)

  • Update comparison results to include the latest Android, iOS devices.

New in Geekbench 4.4.0 (Jul 16, 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 that could prevent OpenCL benchmarks from running on Windows.
  • 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 4.3.1 (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 12, 2018)

  • Add native support for Windows on ARM devices. Users are now able to measure the full potential of their Windows on ARM devices, as Geekbench includes binaries compiled to target the AArch64 processors.
  • 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 4.2.2 (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 4.2.0 (Nov 7, 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.
  • Battery Benchmark Screenshot:
  • 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 (Oct 1, 2017)

  • Geekbench4.1.3 features the following changes:
  • 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 (Apr 3, 2017)

  • Geekbench 4.1 includes the following 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.
  • Geekbench 4.1 includes the following changes to the CPU workloads:
  • 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.
  • Geekbench 4.1 includes the following changes to the Compute workloads:
  • Consolidate optimization code for CUDA, Metal, and OpenCL workloads.
  • Convert Histogram Equalization, Sobel to use RenderScript intrinsics.
  • Users can expect a 35% increase in RenderScript scrores, and a 5% increase in OpenCL and CUDA scores with Geekbench 4.1. These changes should also eliminate crashes on systems with low-end GPUs.

New in Geekbench 4.0.4 (Jan 13, 2017)

  • Geekbench 4.0.4 features the following changes:
  • Fixes crashes that could occur on 32-bit Windows and Linux systems
  • Fixes a crash that could occur after transferring the boot drive from one system to another
  • Fixes a crash that occured when reading malformed or corrupted system information tables
  • Adds Chinese localization to Geekbench for Android

New in Geekbench 4.0.0 (Aug 31, 2016)

  • New benchmarks, redesigned interface, and more

New in Geekbench 3.4.1 (Feb 14, 2016)

  • 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 14, 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 3.3.2 (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 8, 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.

New in Geekbench 3.2.1 (Oct 8, 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 3.1.5 (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 10, 2014)

  • Added the ability to export benchmark results to XML.
  • Fixed an issue that broke Dropbox integration on 64-bit iOS devices.

New in Geekbench 3.1.3 (Dec 11, 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 64-bit iOS devices were reported as 32-bit iOS devices.

New in Geekbench 3.1.2 (Sep 21, 2013)

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

New in Geekbench 3.0.2 (Aug 20, 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.

New in Geekbench 3.0.0 (Aug 16, 2013)

  • New Benchmark Tests:
  • Geekbench 3 includes 15 new benchmark tests that are designed to model real-world processor intensive tasks. The new tests cover a number of different application domains, including encryption, image processing, signal processing, and physics simulation.
  • Geekbench 3 also includes 12 completely rewritten benchmark tests from Geekbench 2. These tests are now more representative of real-world applications and usage scenarios.
  • New Scoring Systems:
  • Geekbench 3 includes a completely new scoring system that separates single-core performance and multi-core performance into two separate scores.
  • While multi-core performance is becoming more relevant as applications are rewritten to take advantage of multi-core processors, single-core performance is still a very important metric because every application benefits from great single-core performance.
  • With Geekbench 3, if you know your applications can't take advantage of the latest multi-core processors, you can use the new single-core scores to find the fastest machine for your tasks.
  • Note that Geekbench 3 uses a different baseline system than Geekbench 2, so Geekbench 3 scores are not comparable to Geekbench 2 scores.
  • New File Format:
  • Geekbench 3 uses JSON as its native file format. JSON is a lightweight format based on JavaScript. Not only is JSON is easy for people to read and write, but it's also easy for computers to understand. Parsing a JSON file only takes one line of code in most languages. This will make writing scripts that use Geekbench data easier than ever.
  • Geekbench 3 also includes more information about each benchmark test in its file format, allowing users to dig deeper into their benchmark results.

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 9, 2013)

  • Added "Export License File" to Geekbench 2 Pro.
  • Fixed a bug that could cause unwanted characters to appear in messages.

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)

  • Improved support for Windows systems with more than 32 cores.
  • Fixed spurious high-resolution timer errors on older Windows systems.

New in Geekbench 2.3.1 (Apr 13, 2012)

  • Fixed "ordinal 344 could not be located" error on Windows XP and Windows Server 2003 R2.

New in Geekbench 2.3.0 (Apr 11, 2012)

  • 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 21, 2012)

  • 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.

New in Geekbench 2.2.6 (Jan 19, 2012)

  • Fixed a hang that could occur when running benchmarks on Windows.
  • Re-enabled multi-threaded tests on single-core systems.
  • Improved upload error messages.
  • Improved handling of corrupted Geekbench files.

New in Geekbench 2.2.3 (Nov 3, 2011)

  • Added support for the iPhone 4S.
  • Improved performance on systems with less than 512MB of RAM.
  • Fixed divide-by-zero errors that occurred on Windows XP 64-Bit Edition.
  • 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 2.2.0 (Aug 31, 2011)

  • Moved 32-bit and 64-bit benchmarks into the same user interface.
  • Added a new hardware stress test.
  • Added a new command-line tool
  • Added new "Export As..." commands.
  • Added a new document-based interface on Windows.
  • Added new hardware information on Windows (processor socket, processor codename, northbridge, and southbridge)
  • Added support for the latest AMD and Intel processors.
  • Redesigned Geekbench result presentation.
  • Improved hardware detection
  • Fixed a bug that caused some Geekbench workloads to misreport performance on 8-core systems.
  • Fixed processor cache detection bugs on late-model AMD and Intel processors.
  • Fixed a startup crash that could occur on Lion.
  • Fixed a crash that could occur when loading saved Geekbench files.
  • Fixed processor core counts for late-model AMD processors.
  • Fixed a bug that could cause Geekbench results to render incorrectly.
  • Fixed registration bugs some users encountered when registering.
  • Fixed thread affinity bugs on multi-socket systems.
  • Fixed several race conditions in multi-threaded workloads.

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 2.1.10 (Nov 10, 2010)

  • fixes some registration issues users could encounter

New in Geekbench 2.1.9 (Nov 10, 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