+1 to djangoringo and killerhurtalot about GeForce performance consistency. What's interesting about the results is not how badly the Radeons do (that's nothing new) but how well the GeForces do. Previously, both companies were putting out inconsistent performance. Radeons were most consistent in some cases, GeForces in others. So it's significant that the GeForces are so much smoother now, and my best guess for that is drivers. When TR approached them last year about performance inconsistency (they asked AMD too), nVidia said they're actaully working on a project specifically to address the inconsistency. Maybe that's what we're seeing the result of here?
As for it being only TR, reason is not so much equipment (with the exception of the high-speed cameras) but the time-consuming nature of the testing. It's always a race for tech media sites to be the first with new benchmarks/reviews and traditional frames/sec testing is quick and easy. I've been speaking with Chris Angelini (Tom's Hardware's editor-in-chief for anyone who doesn't read the articles) and that was the main reason up until now for the lack of frame latency benchmarking. But it is coming.
And as for 'one frame in thirty' being slower, it's often a hell of a lot more than that. Constant up/down fluctuations within a very small time scale.
With regards to RadeonPro, Mautari did some really impressive work there! Makes you wonder why AMD have been unable to do this for their own cards (they seriously need to hire this guy!).
There are some drawbacks though compared to the nVidia solution. Most notably the fact that you need to benchmark each game individually and then calibrate RadeonPro for that game according to your benchmark results. Tom's Hardware said in the review that it's a complicated and time-consuming procedure. Do it wrong (even if you're off by just 10fps) and you get some massive lag spikes (right up to 100 millisecond frames, which equates to a drop to 10fps).
With nVidia on the other hand, you don't need to do a thing - the hardware is already designed to deliver consistently smooth performance out of the box. So a Radeon with RadeonPro is definitely an improvement over normal Radeon performance, but it's still not as good as normal nVidia performance, which doesn't require you to recalibrate it for each game.
Finally, +1 to technoholic about the GTX660 and GTX670 being nVidia's strongest value points - I'd personally save a bit and take the GTX660 over the Ti. You'd never notice the difference. Technoholic, would be interested in the article that exposes the nVidia/TechReport bribery? That's a pretty huge deal if it's true.
EDIT: Or spend a bit extra and get a GTX670 - that's a good option too
GTX670 is the minimum to max Far Cry 3 at 1080p.