Xbench1.3

Works well with 10.6, but doesn't work with OSX 10.7 (Golden Master)

Update, update, update… Who's got the update?

Looong overdue for an update. The latest officially recognized system is the Core 2 Duo. The thread test must be disabled to prevent freezing. Practically abandonware. Places too much weight on the speed of the storage media. NOT cross platform compatable If all other tests are disabled it makes a handy tool for comparing storage media and interfaces. Extensive db for comparing results with other systems.

Works well with 10.6, but doesn't work with OSX 10.7 (Golden Master)

These days, Geekbench seems to be the better tool (it's still updated and is a better indicator of modern Mac and Mac OS X performance). The only thing Geekbench is missing is a hard drive benchmarking feature. Xbench has this. http://www.macupdate.com/info.php/id/20855/geekbench

The app has always worked well for me and has just got better. To add to previous post anyone who doesn't read the documentation is asking for problems.

Xbench is a highly popular 'benchmarking' suite for Mac OS X. The current version is released as a universal binary and is only 52k larger than its 644k predecessor. While I am glad that more developers are releasing UB applications, I think this may represent a 1 step to the side two steps back approach for Xbench, merely because of the change in the baseline machine. A Baseline was established and existed for months prior to this. Most of the benchmarks on current machines that exist on the web and many older ones use the older standard. Now everything must be recalculated and adjusted. This is find for the Xbench site (simple recalculation) and for the application except smaller numbers mean slightly lower levels of precision. For third party sites that did reviews based on the previous baseline set it becomes a task. Do you round each task up, round down, leave it alone? A lot of the old reviews can't get the hardware to do this sort of test again. So, I think a markdown for the benchmark is required. The step forward is just that we can get a test result from an intel based mac. Note: Although there weren't any/many intel specific optimizations performed, the intel part was compiled w/ gcc 4 while the ppc w/ 3.3? Sounds like it should be fair. The text drawing (quartz) bug is still present; if you run it a couple of times the characters are mapped and the test result is about 4x larger than a first time run. For applications like this several runs should be done to get a good 'mark'. So, if you want to compare your machine to reviews online you may want to keep your older xbench version around since this one doesn't gain you much.

it just puts all that stuff in your computers memory making it go faster... indeed unreliable

Xbench does not work. I was running the graphics benchmarks many times in a row. After three times the text benchmark increased 100% all of a sudden. Other results improved as well, but not as much. If nothing in the setup has changed this should not happen. Therefore I do not believe Xbench is a reliable tool for benchmarking. When looking at some results reported at XLR8YourMac is see the same thing happening.

helped me solve a scare that my 867 was only running at 533mhz, according to terminal. i ran Xbench at 533 and 867 and received the same results, so it answered my question, great app.

I just downloaded this benchmark utility, and I have to say I'm reasonably impressed. It tests both the hardware and the OS of the system, with tests for things like FLOPS/sec and thread locks/sec. It was reasonably quick to run. My only complaint is that the submit function wasn't working for me. Also, I think that the program should come with sample data from a wider variety of systems, rather than just a G4/800. In particular, I was rather curious how many times faster than my system a new G5 would be, or how much faster the cheap systems I see on ebay would be. Since the website is down, I have to detract some points for useability. But, hopefully, when the website is back up, I'll be able to browse the submitted results, and get a better idea of how slow my G3 really is...

This is what is used by some prominent Macintosh reviewing sites, and it goes through the whole spectrum of tests to check your system. It doesn't really bother me that you can't compare. Because I am using it to check specific parts of my latest system (Quicksilver 2001) to see how new apps, firmwares and hardware affects the computer's ability as I add these. There's a reason why many people and websites swear by this application, because it works and it is consistent. iBook G4 500Mhz Quicksilver G4 733 Mhz upgraded to 1.2 Ghz Powerbook G3 500 Mhz Beige G3 Minitower 333 Mhz upgraded to 450 Mhz G4

decent app. would like to see comparisons of similiar Macs and other Macs without having to log onto a website. The website seems to choose random Macs to compare you against and compared my eMac 700 against a FULLY loaded eMac 800. That doesn't help me any because of course a machine with 1gb of RAM is going to be faster than mine. Maybe a screen that allows you to choose which makes you want to compare with? Otherwise a decent app and runs well with plenty of detail to the scores. It gets low scores on features and ease of use because of the comparison problem.

Excelent benchmarking app. My iMac is #1 out of all submitted iMac G3's on the site :D

They sure can design nice software, but the alert when you enter their web page which says you should not use Safari is... Anyway, nice program but too many updates for my taste.

This version is really great. Nice consistent scores. This app has come a long way since I first tried it. It's helped me identify performance weaknesses and helped me enhance my system's performance. I also like the new site to compare my system to others. Looking forward to more great improvements...whatever they may be.

No ratings? It's the best and only real benchmark utility for OS X...period.