Whats a good app to use to benchmark the performance of a given ROM? I want to start keeping track of benchmark scores between all the ROMs that I flash. I've found 3 that I've seen used around here.
1) BenchmarkPI
2) Benchmark by softweg
3) Linpack
There is no ONE good one. Just keep track of all three scores and compare, because they measure different things.
There is one you forgot, the benchmark in setCPU.
Related
Hi guys!
can you post your SGS configuration and tell us how do you score with Quadrant Benchmark?
mine is that:
SGS i9000m
kernel speedmod 13c - rom ZeroGingerMIUI with no OC Lagfix ---> 1800
kernel speedmod 13c - rom ZeroGingerMIUI with 1.2ghz OC Lagfix---> 2100
kernel super optimized - rom ZeroGingerMIUI with 1.2ghz OC Lagfix--->2350
kernel hacked Supercurio for GingerBread - rom Ultibread v1.4 Lagfix(no system) --->2000
yes, i'm a bench_maniac!
Stock I9000 XXJVK --> ~awesome scoreon my user experience benchmark.
Awesome... no words to describe!
Quadrant doesn't reflect real life performance at all. I used to get 2200+ with a lagfix on 2.1 but it was no where close to the real life performance of what I experience now on 2.3.3 JVK with no lagfix where Quadrant score is just 1020 .
Nice
Sent from my GT-I9000 using Tapatalk
quadrant doesn't reflect the actual user performance/experience because in the past i've had high quadrant scores but poor user experience.
but as the versions change (i.e eclair>froyo>gingerbread) i get lower scores but better user performance.
Agree my user experience benchmark is also off the scale .
Quadrant crap as always .
Why dont you post all these benchmark quadrant posts in the same place if you want to compare size.
jje
1200 on miui
Sent from my GT-I9000 using XDA App
Mine is scoring "awesome" too in user experience!
I personally think this thread should be removed I'm afraid.. For starters, there are a billion other quadrant threads, and nobody has F***king bothered, as mentioned to collate the values into a table. Also, nothing is worse than breeding a culture of people who believe that Quadrant accurately measures the mobile performance for all workloads.
Auzy said:
I personally think this thread should be removed I'm afraid.. For starters, there are a billion other quadrant threads, and nobody has F***king bothered, as mentioned to collate the values into a table. Also, nothing is worse than breeding a culture of people who believe that Quadrant accurately measures the mobile performance for all workloads.
Click to expand...
Click to collapse
I agree with Ausy that this kind of thread is not of much practical use. I run Quadrant weekly, but only to compare my phone to itself as a diagnostic. If the Q score changes radically, I try to find out why. I also use it to compare ROMs.
However, I don't see that the benchmark scores of two different phones will tell you anything of much value when you compare them.
my quadrant results are in the 4k while my wife's S2 is in the same range (slightly higher) both without any overclocking
I was happy with 4k but now I wonder why my wife's s2 can achieve similar numbers with no overclocking.
My GN overclocked at 1.7 with performance gov hardly go over 5k
I think I read some quadrant are in the 7k
what's yours ?
guessing here but since the cpu/chipset are the same and the note is a little slower in benchmarks, I'm gonna say its the bigger screen resolution that it has to power, more pixels to push.
Bingo.
I got around 4200. Fully stock.
Sent from my GT-N7000 using xda premium
I got 5800 quadrant score overclocked at 1.7
and scored 5005 at default 1.4 Ghz of frequency
I am happy with it...
Thanks guys for the input I feel better now
ArcticCat said:
Thanks guys for the input I feel better now
Click to expand...
Click to collapse
well you just made me feel worse, im getting 3900
Quadrant score fluctuates a lot, so I don't know if it is reliable. I had about 5k and the next benchmark I had over 6k, so.... ofcourse, i had it set to 1.7ghz.
Usually around 4000.
1st 3800
2nd 4000
3rd 4200
4th 4600
5th 4700
6th 4600
Not sure which result is accurate even knowing that quadrant means nothing.
Quadrant is such a badly flawed benchmark, it can't even be used to compare the real world performance between two ROMs, let alone two different devices!
Regards,
Dave
Sent from my GT-N7000 using Tapatalk
foxmeister said:
Quadrant is such a badly flawed benchmark, it can't even be used to compare the real world performance between two ROMs, let alone two different devices!
Regards,
Dave
Sent from my GT-N7000 using Tapatalk
Click to expand...
Click to collapse
Your proof?
WE hear it all the time but nobody ever explains it.
1.4ghz Non-Overclocked, but massively tweaked and I get:
1st Score: 5900
2nd Score: 6200
3rd Score: 6200
4th Score: 6000
5th Score: 6300
xAnimal5 said:
1.4ghz Non-Overclocked, but massively tweaked and I get:
1st Score: 5900
2nd Score: 6200
3rd Score: 6200
4th Score: 6000
5th Score: 6300
Click to expand...
Click to collapse
wow that's impressive!
What kind of tweaks are you taking about?
ArcticCat said:
wow that's impressive!
What kind of tweaks are you taking about?
Click to expand...
Click to collapse
Deleted pretty much everything you can to create a stable system
Adjusted the voltages based on my use
Added some build.prop tweaks
Tweaked the system UI for less RAM usage
No background widgets/No background activity
Double checked an triple checked all apps to make sure no mail process is in use
RAM Optmization tweaks
A bunch of other tweaks that I can't recall off the top of my head... haha
My Score ...
this is my score with quadrant !!
seepage said:
Your proof?
WE hear it all the time but nobody ever explains it.
Click to expand...
Click to collapse
My personal proof is my own personal experiences, but you only need to Google terms like "quadrant benchmark flawed" to find lots of examples.
I've owned a great number of Android devices, and seen widely varying Quadrant scores, yet not one of them has ever indicated the comparative real world experience between the devices.
For example, my Galaxy Tab 7" would only score around 800 (stock) whereas my Note gets over 3600. Is the Note 4.5 times faster in real world usage - not even close! It is faster, but I would subjectively place the performance at around 1.4x to 1.5x.
In a similar vein, when I changed my Galaxy Tab 7" to use EXT4 instead of RFS, but Quadrant score shot up to nearly 2000, but was it over twice as fast as stock? No, once again not even close! However, it still felt faster in real world usage than my HTC Sensation which gets around 2500 on Quadrant.
Quadrant basically performs a lot of individual benchmarks on a device and then amalgamates the result into a single number. Those individual benchmarks may well be of use, but the ultimate number is derives clearly "weights" each benchmark inconsistently/incorrectly to be of any real use when comparing real world performance.
Ultimately, what do these numbers mean if they can't give you an idea of comparative performance?
I find it quite amusing the number of people on this site who chase high Quadrant scores. It's like comparing an M-series BMW with a regular model which has a M-series bodykit and then saying how they perform based purely on looks.
Regards,
Dave
Phandroid (or AndroidCentral) had an article about the crapyness of Quadrant some time ago.
And actually, a lot of mobile review sites refuses to run Quadrant anymore.
Sent from my GT-N7000 using xda premium
Hi, i went down quite a lot of pages and did not find any antutu score tests on galaxy s.
I was just wondering whats the best ones in what rom's and what kernels. I tried to google i9000 antutu best scores but seems there was not really that many hits and best scores i found was like 4k what sound quite a lot but not sure how legit those are when there was no pics.
I mean my friend got a galaxy note and it get a bit over 7k point and then reading more the damn old sucker galaxy s2 best with pic proof is like 8k.
Was just wondering how my fine old faithful galaxy s can do. I got a decent gingerbread rom and i get a bit over 3k without OC. Can't remember how much more i got with ICS OC'd to 1,4ghz. it was over 3k too tough but not remembering how much above.
Would be nice if you can post your roms that score over 3k and what roms + kernels you are using and how much OC you done. I mean the i9000 is not the fastest phone by far at this point but would be intressed to see if people got how high antutu scores.
Nowadays benchmark doesnt mean anything. There's many ways to cheat, and even if those score were honest it doesn't matter much. What does matter is real life performance
Oh antutu score can be fixed too these days? I mean i now the quadrant score has been always a bit question mark and i heard lots of cheating in it. Well i was just wondering the honest score. I'm trying to find a decent fast rom and the better score in benchmarks the less processor power it uses on stuff and that means a bit better battery life too.. well not always.
I'm just trying to get all out of my sgs before sgs3 comes out.. i must say i just love t his phone.. when i had a fast rom where it worked stable at 1.4ghz it was as fast as iphone 4s in same internet pages on stock browser.
But if people could post the LEGIT non cheated scores it would be better than the cheating ones lol
an0nym0us_ said:
Nowadays benchmark doesnt mean anything. There's many ways to cheat, and even if those score were honest it doesn't matter much. What does matter is real life performance
Click to expand...
Click to collapse
+1. SGS with Froyo and EXT2 lagfix got a much higher score in Quadrant, but with ICS the experience is much better.
So the real question is what ROMs have given the best real life performance for you?
For me, it's 3827( on Antutu ) ;D with TiramiSlim RC2.0
Hey guys,
Posted under general questions and to my surprise not one reply in a week. So, I'm curious to know somethings about overclocking these tablets. What settings are you using? Have you had any issues with overheating and shutting down?What settings are recommended for web browsing, gaming etc? Let's talk linpack and benchmark testing. Where do you rank and how did you get there? Let's talk SetCPU benchmark scores, what kind of results can you squeeze out out of your device? How does someone pull off 41916.7 MFLOPS?! (Nexus) I'll start......
GT-7310 Running 3.2 / Motley Kernal / SetCPU
SetCPU Scores
Long Bench @ 178ms / Native @ 621.5ms
Linpack Scores
Single thread @ 42.4 MFLOPS / Multi thread @ 83.2 MFLOPS
Obtained running 1504MHz max / 216MHz min
Note: I have overheated and shutdown at 1504 web browsing. At 1400MHz I have had no issues. I see some scores are through the roof. I'm not to familiar with Overclocking and just would like to hear what you guys have to say. Thanks in advance. I may of posted this in the wrong area and I apologize. I would like this to be a thread on the topic rather than a Q & A.
Well I personally run my tab @1200Mhz with -25mV on the 1000&1200 steps, but anyhow, due to the interactive governor the most used setps are 216, 456 and 1200. I don't undervolt the lower test for stability reasons as I mostly work on the tablet so I don't want to test yet how low uV can go, don't have the time to test it right now. (Even though I'm pretty sure -25mV even on lower steps is still largely stable)
As for the set CPU test I tried them out on 1504Mhz: 150 and 595ms. I once pushed the tab to 1600Mhz but it ended up in an immediate freeze so I will skip on trying that again.
I don't have linpack but tried running GLBench 2.1 Egypt and the score was pretty embarrasing
Thanks for sharing. Since my post I have flashed aokp-34 galaxiansoup with v-3 of the Motley Kernal. Running 1400 on 216 no undervolting and am seeing a tiny increase in numbers. I'm still stumped on these linpack scores. This thing runs great. No complaints whatsoever. Anyone want to chime in on the best bench testing app or what the stock numbers on these 7310's are?
everyone will tell you that benchmark scores aren't very representative!
run the test 5 times and each time you will get a slightly different score.
i don't really care about benchmarking, as long as i feel that my tab runs smooth (which i think it does) im pretty happy. im normally at 1,4ghz and everything is smooth and stable!
Thanks for sharing. I couldn't agree more. My tab runs great at the same speed settings as yours. I just don't understand the numbers and how certain device's have like 100 times my mflops......I'm a numbers guy by nature, I like to see it on paper....but I am content with my device. Just always looking to make it cleaner and faster.....you know the addiction I'm sure.
Are you happy with this kernel? I found it stuttering and laggy...
zooster said:
Are you happy with this kernel? I found it stuttering and laggy...
Click to expand...
Click to collapse
Yes, I've not ran into any issues. Totally impressed and content with v3 motley. If there is a better kernel out there I'd love to hear about. I have yet to look, no need.
Been running a few custom profiles via Setcpu peaking @1.5GHz on B37 for a few weeks now. Other than a force close or two and an occasional browser freeze, which is normal with these roms, this thing is running pretty snappy. Gotta watch the temp though.
Sent from my GT-P7310 using xda premium
I sure hope that you've set up your profiles so that your tab overclocks to 1.5Ghz only occasionally, it's a thing that you HW can handle it, but will it on the long term?
Also, I regret that you can't overclock the bus frequency to get an overall performance boost (the GPU could really use it..) as on the Galaxy S
Yeah, I'm only pushing 1.5 on occasion, per profile. I normally run 1.4 all day everyday for the last 3 months with heavy use and no issues. Just gotta watch the temp. I've had mine to 113 degrees which kinda scared me.
Sent from my GT-P7310 using xda premium
What programmes do you guys recommend for the best benchmark tests and comparisons? I'm currently using AnTuNu, but their information seems a bit lean for decent comparisons to highest achieved scores. Also, I wanted to share my benchmark, it's quite impressive compared to the standard SM-G725 variants average.