NVIDIA GeForce GTX 460 vs NVIDIA T600 Comparison

The GeForce GTX 460 and the T600 sit in an unusual corner of the database: a 2010 gaming card from the Fermi era measured against a 2021 workstation card from the Turing era. Both are end-of-life products now, both built by NVIDIA at TSMC, and both occupy a similar position in the overall database rankings, yet they represent entirely different design philosophies. The GTX 460 was a dual-slot, external-power gaming part; the T600 is a single-slot, slot-powered professional part. The recorded data makes the generational gap between them unusually easy to quantify, because the two cards share exactly one common benchmark, and that benchmark tells a stark story.

Where Each One Wins

The head-to-head record is one-sided. Of the single shared test in the database, geekbench_opencl, the T600 takes the win and the GTX 460 takes none: the T600 scores 27875 against 7925 for the GTX 460, which works out to roughly 3.5 times the compute throughput. That single result is the entirety of the direct comparison, so any conclusion about relative performance rests on it.

The GTX 460 does not win any recorded benchmark against the T600, but its profile is not without merit. Its percentile placement across all GPUs in the database is 41, slightly above the T600 at 39, meaning that when each card is ranked against the full population of measured GPUs, the GTX 460 sits marginally higher on that aggregate scale. Note that these percentile figures are computed against different underlying score sets, since the GTX 460 has only one recorded test while the T600 has nine. The GTX 460 also has a higher average benchmark score, 7925 versus 7035, though again that average mixes different test types, including low-value PassMark DirectX scores for the T600 that pull its mean down.

Where the T600 clearly wins is compute and modern API support. Where the GTX 460 holds its ground is aggregate percentile placement, a hair above its rival. That is the full extent of the split.

Architecture Differences

The two cards come from different worlds. The GTX 460 uses the GF104 chip on the Fermi architecture, part of the GeForce 400 generation, built on a 40 nm process at TSMC. It packs 1,950 million transistors into a 332 mm² die, for a density of 5.9 million transistors per square millimeter. The T600 uses the TU117 chip on the Turing architecture, from the Quadro Turing (Tx000) generation, built on a 12 nm process at the same foundry. Its 4,700 million transistors fit into a 200 mm² die, giving 23.5 million transistors per square millimeter, roughly four times the density of the older part despite the die being substantially smaller.

The functional block counts favor each card in different places. The GTX 460 has 336 shading units, 56 texture mapping units, and 24 render output units. The T600 has 640 shading units but only 40 TMUs, while pulling ahead with 32 ROPs. Neither card has RT cores or tensor cores in the recorded data, which is notable for the T600 given its Turing lineage: this database entry lists none for either GPU.

Clocking philosophies differ. The GTX 460 has no recorded base or boost clock, only memory running at 900 MHz, 3.6 Gbps effective. The T600 records a 735 MHz base and a 1335 MHz boost clock, with memory at 1250 MHz, 10 Gbps effective. The memory subsystem is where the generational leap is most visible: the GTX 460 pairs 768 MB of GDDR5 on a 192-bit bus for 86.40 GB/s of bandwidth, while the T600 pairs 4 GB of GDDR6 on a 128-bit bus for 160.0 GB/s. The T600 gives up bus width but delivers nearly double the bandwidth and more than five times the capacity.

Theoretical throughput figures follow the same pattern. The GTX 460 produces 9.450 GPixel/s of pixel fill, 37.80 GTexel/s of texture fill, and 907.2 GFLOPS of FP32. The T600 produces 42.72 GPixel/s, 53.40 GTexel/s, and 1.709 TFLOPS FP32, plus 3.418 TFLOPS of FP16 at a 2:1 ratio, a capability the GTX 460 entry does not list at all.

Feature support separates them sharply on the API side. The T600 covers DirectX 12 at feature level 12_1, OpenGL 4.6, and Vulkan 1.4, with four mini-DisplayPort 1.4a outputs over a PCIe 3.0 x16 interface. The GTX 460 covers DirectX 12 at feature level 11_0, OpenGL 4.6, and no recorded Vulkan support, with two DVI ports and one mini-HDMI 1.3a over PCIe 2.0 x16. For anything requiring a modern feature level or Vulkan, only the T600 qualifies.

Power and physical packaging could not differ more. The GTX 460 is a 160 W dual-slot card needing two 6-pin connectors and a suggested 450 W power supply. The T600 is a 40 W single-slot card with no power connectors at all and a suggested 200 W supply. The GTX 460 measures 210 mm long; no length is recorded for the T600.

Head-to-Head Benchmarks

Walking through the data: the only shared test is geekbench_opencl. The T600 posts 27875, the GTX 460 posts 7925, and the T600 wins. The gap is enormous, on the order of 252 percent in the T600's favor, or stated more simply, the T600 delivers about 3.5 times the score. For OpenCL compute workloads the recorded data leaves no ambiguity.

Context from each card's rival list sharpens the picture. The GTX 460's score of 7925 lands within a fraction of a percent of the Quadro K4100M at 7906, and sits just below the Quadro P5000 at 8039, the GTX 880M at 8040, and the GTX 650 Ti at 8053. It is tightly clustered with all four of its nearest rivals, all within about 1.6 percent. The T600's average of 7035 sits just above the GTX 680M at 7023, the Radeon R5 M240 at 6975, and the GTX 675M at 6946, and just below the GTX 970 at 7157. Despite the T600's crushing OpenCL win, its broader average places it in a neighborhood of much older mobile and mainstream cards, which is a reminder of how different metrics reward different capabilities.

The T600's full benchmark sheet adds texture that the head-to-head cannot. Its PassMark G3D score is 6479, GPU compute is 2402, and 2D graphics is 756, with DirectX subtest scores of 114 for DirectX 9, 32 for DirectX 10, 49 for DirectX 11, and 25 for DirectX 12. It also records a geekbench_vulkan result of 25580, close to its OpenCL figure. No comparable results exist for the GTX 460 in the database, so cross-comparison beyond OpenCL is not possible.

The Verdict

On the recorded data, the T600 is the stronger performer. It wins the only shared benchmark by a wide margin, offers far higher fill rates and FP32 throughput, double the memory bandwidth, and dramatically more modern API support including Vulkan 1.4 and DirectX 12 feature level 12_1. It does all this at a quarter of the power draw, in a single slot, with no external connectors. For compute, for modern workloads, and for constrained systems, the data clearly points to the T600.

The case for the GTX 460 rests on two slim reeds: its percentile across all GPUs is 41 versus 39, and its single-test average is higher because the averaging bases differ. It also holds a narrow texture-unit advantage, 56 TMUs against 40, though its actual recorded texture rate of 37.80 GTexel/s trails the T600's 53.40 GTexel/s due to clock speeds. Anyone choosing strictly from benchmark results should pick the T600. Anyone needing legacy DVI or mini-HDMI output, which the T600 lacks entirely, has a connectivity-based reason to consider the older card, since it offers two DVI ports and one mini-HDMI versus the T600's four mini-DisplayPorts.

FAQ

Q: Which card is faster in benchmarks?

A: The T600. It wins the only shared test, geekbench_opencl, with 27875 versus 7925 for the GTX 460, roughly 3.5 times the score.

Q: How do the two compare in database-wide ranking?

A: They are nearly tied. The GTX 460 sits at the 41st percentile versus all GPUs and the T600 at the 39th, a marginal edge for the older card on that aggregate scale.

Q: How much power does each card need?

A: The GTX 460 has a 160 W TDP, requires two 6-pin connectors, and carries a 450 W suggested power supply. The T600 has a 40 W TDP, needs no power connectors, and carries a 200 W suggested supply.

Q: Do both cards support Vulkan?

A: Only the T600, with Vulkan 1.4 recorded. No Vulkan support is listed for the GTX 460.

Q: Which card has more memory?

A: The T600, with 4 GB of GDDR6 and 160.0 GB/s of bandwidth. The GTX 460 has 768 MB of GDDR5 and 86.40 GB/s.

Q: What cards are closest in performance to each?

A: The GTX 460 clusters within about 1.6 percent of the Quadro K4100M, Quadro P5000, GTX 880M, and GTX 650 Ti. The T600 clusters near the GTX 680M, Radeon R5 M240, GTX 675M, and GTX 970.

Specification Differences

| Field | GTX 460 | T600 |

|---|---|---|

| Architecture | Fermi | Turing |

| Chip | GF104 | TU117 |

| Generation | GeForce 400 | Quadro Turing (Tx000) |

| Process node | 40 nm | 12 nm |

| Transistors | 1,950 million | 4,700 million |

| Die size | 332 mm² | 200 mm² |

| Transistor density | 5.9M / mm² | 23.5M / mm² |

| Base / boost clock | not recorded | 735 MHz / 1335 MHz |

| Memory clock | 900 MHz (3.6 Gbps effective) | 1250 MHz (10 Gbps effective) |

| Memory | 768 MB GDDR5, 192-bit, 86.40 GB/s | 4 GB GDDR6, 128-bit, 160.0 GB/s |

| Shading units | 336 | 640 |

| TMUs | 56 | 40 |

| ROPs | 24 | 32 |

| Pixel rate | 9.450 GPixel/s | 42.72 GPixel/s |

| Texture rate | 37.80 GTexel/s | 53.40 GTexel/s |

| FP32 | 907.2 GFLOPS | 1.709 TFLOPS |

| FP16 | not recorded | 3.418 TFLOPS (2:1) |

| TDP | 160 W | 40 W |

| Slot width | Dual-slot | Single-slot |

| Power connectors | 2x 6-pin | None |

| Suggested PSU | 450 W | 200 W |

| Bus interface | PCIe 2.0 x16 | PCIe 3.0 x16 |

| Display outputs | 2x DVI, 1x mini-HDMI 1.3a | 4x mini-DisplayPort 1.4a |

| DirectX | 12 (11_0) | 12 (12_1) |

| Vulkan | not recorded | 1.4 |

| Length | 210 mm | not recorded |

| Release date | 2010-07-11 | 2021-04-11 |

| Predecessor / successor | GeForce 200 / GeForce 500 | Quadro Volta / Workstation Ampere |

| Launch MSRP | 199 USD | not recorded |