Has anybody documented if there had been any actual comparisons between the Pi Model B+ and an old Intel Celeron system (either desktop or laptop). I ask as, while I have seen plenty of comparisons between other SBC's, there are none with laptop or desktop. The reason is lot of people claim that it is best device for computing for the price, it would be nice if somebody has documented that. Even if it failed or something, there would be some idea as to how much catching it would have to do.

Looking forward to know.

  • I think you need to define "The reason is lot of people claim that it is best device for computing for the price" in sufficient detail for an unambiguous assessment to be made. For me it is far to vague a question.
    – joan
    Oct 17 '15 at 9:08
  • I don't recall seeing anyone claim the pi is the "best device for computing for the price", if you mean pure processing power. Although it might be true (since there is not a whole lot of competition in the "<$40 US" category), this is not the reason most people buy them, I think. Hence, you see them compared to other SBC's which have similar features -- primarily, the GPIO breakout -- which laptops and desktops simply do not have, so there is not much point in a comparison.
    – goldilocks
    Oct 17 '15 at 12:03
  • The new model 2 can run a modern Java ide like IntelliJ in raspian, but you will need usb storage instead of sdcard. Oct 17 '15 at 22:03

It's rare to find a direct comparison of ARM and Intel CPUs in one benchmark. If you want to compare processing power, a good indicator is a reply on the raspberry.org forums. From Andrew Oakley's answer on https://www.raspberrypi.org/blog/benchmarking-raspberry-pi-2/ regarding benchmarking the new RPi 2:

Transcoding Skinny Puppy’s “Pro-Test”, 360×270 Quicktime .MOV, 256kbps MP3, to same resolution MP4 at CRF 26, 96kbps, using avconv:

Raspberry Pi 1 (1x 700MHz ARMv6, 512MB RAM, Raspbian Wheezy): Average 1 frame per second. 18 mins to complete.

Raspberry Pi 2 (4x 900MHz ARMv7, 1GB RAM, Raspbian Wheezy): 28 FPS, 4 min 9 secs to complete –

Intel Celeron dual-core (2x 2.5GHz 686, 2GB RAM, Ubuntu Precise): 114 FPS, 1 min 3 secs

Unfortunately, the type of Celeron was not specified. For this encoding task, it is apparent that the Celeron is a little more than 4 times more powerful than a RPi 2.


I follow @goldilocks in his "cannot recall anyone claim ... pure processing power" statement. On the contrary, there's rather many threads on this stack that claim the Pi is underpowered for the task one wants to do. In many occasions there's absolutely no need for plenty of processing power and unused processor overhead will just results in higher power bills.

Many claims that, product A is better spec'ed or better priced than product B, are unfunded. There's a lot of parameters which needs to be included to make a valid claim. However on the other side, user cases vary a lot and therefore most comparasions are very subjective.

I can sum up a lot of cases where the Pi is a completely overpriced and/or underperforming product. And as much cases where the opposite is true.

If you want to compare the Pi with other solutions especially for your user case, open a new thread. I'm sure the community will share their honnest opinion.


The only sure way to find out is to get your hands on one of each of your candidate platforms and benchmark them. And when benchmarking, the test program should match your actual workload as close as possible. By the way, should you end up actually benchmark Raspberry Pi against Celeron, post your results somewhere and notify me, I am interested to see (since I cannot do this as all my other computational platforms except my iPhone 4S and iPad 2, both powered by Apple A5 45nm, will crush the Pi, powered by Intel Core 2 Quad Q9300, Intel Xeon E3-1231v3 and dual Xeon E5-2620v2 respectively)

If you say gut feeling I would like to say unless you are talking old pre-P6 Celerons or bottom-of-the-line Atom-based Celerons, they will annihilate Pi.

Not the answer you're looking for? Browse other questions tagged or ask your own question.