Out of curiosity I built Geekbench with Xcode 4.5 (it's not available on the App Store yet) and took a look at the code generated for the armv7 and the armv7s architectures. Surprisingly there weren't a lot of differences between the two. The biggest difference I saw was that Xcode uses conditional VFP instructions (e.g., vaddeq.f64) for the armv7s but doesn't use them for the armv7 despite the fact that these instructions are supported by the armv7. My guess is that the A6 implementation of these instructions is much faster, but I won't know for sure until I can run benchmarks on the iPhone 5 myself.
Also, I could only find two instructions (sdiv and udiv) that Xcode generates for the armv7s architecture that aren't supported by the armv7 architecture.
Out of curiosity I built Geekbench with Xcode 4.5 (it's not available on the App Store yet) and took a look at the code generated for the armv7 and the armv7s architectures. Surprisingly there weren't a lot of differences between the two. The biggest difference I saw was that Xcode uses conditional VFP instructions (e.g., vaddeq.f64) for the armv7s but doesn't use them for the armv7 despite the fact that these instructions are supported by the armv7. My guess is that the A6 implementation of these instructions is much faster, but I won't know for sure until I can run benchmarks on the iPhone 5 myself.
Also, I could only find two instructions (sdiv and udiv) that Xcode generates for the armv7s architecture that aren't supported by the armv7 architecture.