Specs and synthetics
We'll get our customary start with a look at specs and some synthetic benchmarks designed to test them. The thing you need to know about the numbers below is that they come from the actual cards we tested. In some cases, those cards ran at clock speeds somewhat higher or lower than the official reference clocks established by the GPU makers, which may explain why our numbers sometimes vary from the official specifications.

Peak
pixel
fill rate
(Gpixels/s) 		Peak bilinear
texel
filtering
rate
(Gtexels/s)		 Peak bilinear
FP16 texel
filtering
rate
(Gtexels/s)		 Peak
memory
bandwidth
(GB/s)		 Peak shader
arithmetic (GFLOPS)
Single-issue Dual-issue
GeForce 9500 GT 4.4 8.8 4.4 25.6 90 134
GeForce 9600 GSO 6.7 26.6 13.3 38.5 259 389
GeForce 9600 GT 11.6 23.2 11.6 62.2 237 355
GeForce 9800 GT 9.6 33.6 16.8 57.6 339 508
GeForce 9800 GTX+ 11.8 47.2 23.6 70.4 470 705
GeForce 9800 GX2 19.2 76.8 38.4 128.0 768 1152
GeForce GTX 260 16.1 36.9 18.4 111.9 477 715
GeForce GTX 260 216 SPs 18.1 46.7 23.3 117.9 607 910
GeForce GTX 280 19.3 48.2 24.1 141.7 622 933
Radeon HD 4650 4.8 19.2 9.6 16.0 384 -
Radeon HD 4670 6.0 24.0 12.0 32.0 480 -
Radeon HD 3850 11.6 11.6 11.6 57.6 464 -
Radeon HD 4830 9.2 18.4 9.2 57.6 736 -
Radeon HD 4850 10.0 25.0 12.5 63.6 1000 -
Radeon HD 4870 12.0 30.0 15.0 115.2 1200 -
Radeon HD 4870 X2 24.0 60.0 30.0 230.4 2400 -

On paper, the 4830 matches up well against the GeForce 9800 GT. The two share the exact same memory bus width and clock speed, so they have the same peak theoretical memory bandwidth. The 9800 GT would appear to have quite a bit more texturing power, and the 4830 seems to have a pronounced edge in shader arithmetic rates.

In practice, the picture is a little different. The Radeon HD 4830 takes both the color and fill rate tests and three out of the four shader tests, although its margins of victory in the shader tests aren't as resounding as the gigaflops numbers might suggest.