The Tesla K20 features a 7.1 billion transistor 28nm chip with 13 SMX clusters enabled, each cluster has 192 cores, making a grand total of 2,496 CUDA cores. Unfortunately, the amount of memory on this board will be maximum 6GB GDDR5, of which 5GB will be usable with ECC enabled. VR Zone claims this is because Samsung and Hynix refused to manufacture 4Gbit GDDR5 memory chips due to a lack of interest.
The number of cores is not the only change, though - Nvidia was working hard on optimizing the Double Precision performance, failing short of self-imposed target of 1.5 TFLOPS DP. As it stands right now, the K20 will barely outperform the Xeon Phi (ex-Larrabee, now Knights Corner / Knights Ferry) and AMD's own FirePro S9000 (which is hidden on AMD's website so well that you can't find it unless you use a search engine).
The GPU will only work at 705MHz, meaning that you can expect double-precision performance to the tune of 1.17 TFLOPS, barely double than C2075/M2075/M2090. Single-precision performance is quite solid at 3.52 TFLOPS, but still lags behind AMD's Tahiti GL GPU (4TFLOPS Single, 1TFLOPS Double).