Benchmark duel: Apple Mac Pro vs. Power Mac G5

Geek Patrol has pitted an Apple Mac Pro against a Power Mac G5.

The configs of the two test machines:

Mac Pro
• Intel Xeon 5150 @ 2.66GHz (two dual-core processors)
• 1024MB RAM
• Mac OS X 10.4.7 (Build 8K1079)
• Geekbench 2006 (Build 190)

Power Mac G5
• PowerPC G5 @ 2.5GHz (two dual-core processors)
• 1024MB RAM
• Mac OS X 10.4.7 (Build 8J135)
• Geekbench 2006 (Build 180)

Geek Patrol reports, “Overall, the Mac Pro is 7% faster than the Power Mac G5. In individual tests, the Mac Pro is between 34.9% and 280.4% of the performance of the Power Mac G5. The Mac Pro outperforms the Power Mac G5 when it comes to integer calculations and scalar floating point calculations, while the Power Mac G5 outperforms the Mac Pro when it comes to vector floating point calculations and standard library memory performance. Of course, we’ve tested a mid-range Mac Pro ($2500 US) against a top-of-the-line Power Mac G5 ($3000 USD), so even though the Mac Pro is only a little bit faster than the Power Mac G5, it’s significantly cheaper!”

Full article with benchmark details here.

MacDailyNews Take: Obviously, we’d like to see the top-of-the-line Mac Pro (with two 3.0GHz Dual-Core Intel Xeon “Woodcrest” processors, US$3,299 as configured above) vs. the old top-of-the-line Power Mac G5 (Original price: US$3,299) that Geek Patrol has used in their testing.


  1. What may be more helpful is to time the two machines doing the tasks that customers would use them for…CS2, video work, etc.

    What I’m wondering is how the faster processors, etc., would compensate for the Rosetta effect on non universal applications like CS2.

  2. Regardless of what people would like to see, a year old Quad G5 standing up to a brand new Core Duo 2 proves that the PowerPC architecture was solid.

    IBM failed PowerPC. When IBM wrote off Apple as not being important enough to keep PowerPC and the G5 a cutting edge processor they seem to have doomed PowerPC. Even the G5 was a lackluster effort on their part.

    What is done is done and for reasons outside of performance I like the move to Intel processors. Dual Boot, Virtualized OS Environments and possibly a Wine type implementation in OS X is reason enough to make the switch.

  3. as a video geek – i’m not 100% in awe of the new intel machines – they’ve always put integer perf ahead of fp and vector perf.

    of course, in the end, the intels always beat the snot out of the PPCs after a time… so i expect this trend to also continue.

  4. Interesting that the 2.66GHz Dual Duo is 7% overall faster than the 2.5GHz Quad G5, and that 2.66GHz is 6.4% faster than 2.5GHz. Seems clock-for-clock they are the same.

    Not bad for a chip that came out a year ago to be on par with one of Intel’s latest & greatest, huh?

    Now where’s my 3GHz G5????

  5. I have a 2.5 with 2 gig of ram. I really would have thought the new model it would have been alot faster even as a mid-line model. I wasn’t in the market to upgrade, but now I know even the 3Ghz probably wouldn’t be worth a $3,500(or more) hit to upgrade, for me at least.

  6. There is no indication that the GeekBench test suite was compiled to take advantage of the “128-bit SSE3 vector engine” that is part of the new chips but un-mentioned with the older chips. Given that the Quad PM has long used G5s with their Velocity Engines, the test compiled for them likely takes advantage of that technology … thus a huge advantage in processing vector floating point calculations. Had they upgraded the memory in the new model they would have seen a jump in memory performance as well.

Reader Feedback

This site uses Akismet to reduce spam. Learn how your comment data is processed.