Actually, I too was thinking about std deviation bars, but I didn't feel like trying to figure out how at first, put them like that to begin with and then just liked the way it looked. I also specifically recorded the order in which I did each run, mostly for myself. Since I did, I figured I might as well present it to the reader too. As for more data points, once again, to add even one more data point per bench means around 5-6 hours, not to be whiny about it, but that's the truth. And if you look at the results it's pretty clear that there's not even much variation between runs in each given OS. Whether I can show it statistically or not, 7 always scores lower than Vista in 05 for example. Even one run can tell you that. I could do more runs to make it more statistically sound, but pragmatically it wouldn't help a thing.
Probably plenty don't like the graphs not starting from zero, but it's conducive to what I'm trying to present. This is not supposed to be an academic paper, it's supposed to tell people clearly what OS scores the best. The real difference is tiny, yes. For example even between the averages of 7 64 and Vista 32, it's just 2.35%, which in real terms is tiny. However, on the 3DMark05 hall of fame, it's actually larger than the difference between 1st place and 5th place, which is a very big deal for anyone competitive.
