NVIDIA GeForce GTX 650 Ti Boost vs NVIDIA T600 Comparison

Head-to-Head Benchmarks

The recorded data paints a decisive picture in favor of the NVIDIA T600 across the two shared benchmark tests. In Geekbench OpenCL, the T600 scores 27,875, which is a massive 66.6% lead over the GeForce GTX 650 Ti Boost’s 9,302. This is not a marginal victory; it is a generational gap expressed in raw compute throughput. The GTX 650 Ti Boost trails by more than two-thirds, indicating that the older Kepler architecture is thoroughly outclassed in this workload.

The Vulkan results tell a similar but slightly less extreme story. The T600 posts 25,580, while the GTX 650 Ti Boost manages 10,041. The delta here is 60.7%, meaning the T600 outperforms the older card by nearly two-thirds in this API. Both wins belong to the T600, and the database records zero benchmark victories for the GTX 650 Ti Boost in the head-to-head comparisons. The data shows a clean sweep: two tests, two wins for the Turing-based card.

It is worth contextualizing these scores against the broader database rankings. The GTX 650 Ti Boost holds an average benchmark score of 8,067, which places it in the 42nd percentile of all GPUs. Its closest rivals in the database include the NVIDIA GRID K2 (8,080, a 0.2% difference), the GeForce GTX 650 Ti (8,053, a 0.2% difference), and the GeForce GTX 880M (8,040, a 0.3% difference). This indicates that the GTX 650 Ti Boost sits in a tightly clustered performance band, where tiny margins separate it from peers. The Quadro P5000 also appears at 8,039, just 0.3% behind, reinforcing the notion that this card is operating near the ceiling of its architectural capability.

The T600, by contrast, has an average benchmark score of 7,035, which places it in the 39th percentile. This is intriguing because its average score is lower than the GTX 650 Ti Boost’s average, yet it wins the head-to-head tests overwhelmingly. The explanation lies in the benchmark distribution. The T600’s nearest rivals include the GeForce GTX 970 (7,157, a 1.7% lead), the GeForce GTX 680M (7,023, a 0.2% deficit), and the AMD Radeon R5 M240 (6,975, a 0.9% deficit). The T600’s average is dragged down by poor results in legacy DirectX tests, such as Passmark DirectX 10 (32), DirectX 11 (49), and DirectX 9 (114). These low scores are likely attributable to driver optimization priorities rather than raw hardware capability.

In the two modern API tests that both cards share, the T600 is unequivocally superior. The OpenCL gap of 66.6% and the Vulkan gap of 60.7% are both decisive. The data suggests that the T600’s architecture is far more efficient at extracting performance from compute-heavy and modern graphics workloads, while the GTX 650 Ti Boost relies on a different, older design that cannot keep pace.

FAQ

Q: Which card wins the Geekbench OpenCL benchmark?

A: The NVIDIA T600 wins decisively, scoring 27,875 against the GTX 650 Ti Boost’s 9,302, a 66.6% advantage.

Q: How does the GTX 650 Ti Boost compare to its nearest rivals in average score?

A: The GTX 650 Ti Boost averages 8,067, sitting just 0.2% behind the NVIDIA GRID K2 (8,080) and 0.2% ahead of the GeForce GTX 650 Ti (8,053). It also leads the GeForce GTX 880M and Quadro P5000 by 0.3% each.

Q: What is the T600’s percentile ranking among all GPUs?

A: The T600 sits in the 39th percentile of all GPUs in the database, with an average benchmark score of 7,035.

Q: Does the GTX 650 Ti Boost have any benchmark wins over the T600?

A: No. The database records zero wins for the GTX 650 Ti Boost and two wins for the T600 in the shared head-to-head tests.

Q: Why does the T600 have a lower average score than the GTX 650 Ti Boost despite winning head-to-head?

A: The T600’s average score of 7,035 is pulled down by low legacy DirectX scores, including 32 in DirectX 10, 49 in DirectX 11, and 114 in DirectX 9. The GTX 650 Ti Boost’s average of 8,067 reflects only its three Geekbench scores, which are more consistent.

Q: How close is the T600 to the GeForce GTX 970 in average performance?

A: The T600 trails the GeForce GTX 970 by 1.7% in average score, with the GTX 970 at 7,157 and the T600 at 7,035.

Architecture Differences

The architectural gulf between these two cards is stark, and it explains the benchmark results more than any single specification. The GTX 650 Ti Boost uses the GK106 chip built on Kepler architecture, manufactured on a 28 nm process at TSMC. It packs 2,540 million transistors into a 221 mm² die, yielding a transistor density of 11.5 million per square millimeter. The T600, in contrast, uses the TU117 chip on Turing architecture, fabricated on a 12 nm process, also at TSMC. It contains 4,700 million transistors on a slightly smaller 200 mm² die, achieving a density of 23.5 million per square millimeter. That is more than double the transistor density, a direct reflection of the newer process node.

The memory subsystems diverge significantly. The GTX 650 Ti Boost offers 2 GB of GDDR5 memory on a 192-bit bus, delivering 144.2 GB/s of bandwidth. The T600 doubles the capacity to 4 GB of GDDR6, but narrows the bus to 128-bit. Despite the narrower bus, the T600 achieves 160.0 GB/s of bandwidth due to the higher memory clock. The effective memory speed tells the story: the GTX 650 Ti Boost runs at 6 Gbps effective, while the T600 runs at 10 Gbps effective.

Compute resources differ in configuration. The GTX 650 Ti Boost has 768 shading units, 64 texture mapping units, and 24 raster operations pipelines. The T600 has fewer shading units at 640, fewer TMUs at 40, but more ROPs at 32. The pixel rate favors the T600 dramatically: 42.72 GPixel/s versus 16.51 GPixel/s for the older card. Texture rate, however, favors the GTX 650 Ti Boost at 66.05 GTexel/s versus 53.40 GTexel/s for the T600. Floating-point performance is close in FP32, with the T600 at 1.709 TFLOPS and the GTX 650 Ti Boost at 1.585 TFLOPS. The T600 also supports FP16 at 3.418 TFLOPS with a 2:1 ratio, a feature the Kepler card lacks entirely.

Clock speeds show a different strategy. The GTX 650 Ti Boost runs at a 980 MHz base and 1032 MHz boost. The T600 has a lower 735 MHz base but a much higher 1335 MHz boost, indicating aggressive boost behavior. The T600’s power envelope is radically different: a 40 W TDP versus 134 W for the GTX 650 Ti Boost. The T600 requires no power connectors and fits in a single slot, while the GTX 650 Ti Boost needs a 6-pin connector and occupies a dual-slot footprint. The suggested PSU also reflects this, with 200 W for the T600 and 300 W for the GTX 650 Ti Boost.

API support differs as well. The GTX 650 Ti Boost supports DirectX 12 (11_0) and Vulkan 1.2.175. The T600 supports DirectX 12 (12_1) and Vulkan 1.4. Both cards support OpenGL 4.6. The T600’s display outputs are exclusively 4x mini-DisplayPort 1.4a, while the GTX 650 Ti Boost offers 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2.

The Verdict

The data directs different users to different cards, but the head-to-head results are unambiguous. For anyone running modern compute workloads, OpenCL, or Vulkan applications, the T600 is the clear choice. It wins both shared benchmarks by margins of 66.6% and 60.7%, and it does so while consuming only 40 W against the GTX 650 Ti Boost’s 134 W. The T600 also offers double the VRAM capacity at 4 GB versus 2 GB, and a newer memory type in GDDR6. Its single-slot, connector-free design makes it far easier to integrate into dense or constrained systems.

The GTX 650 Ti Boost does hold a higher average benchmark score of 8,067 versus 7,035, and it sits in a higher percentile at 42 versus 39. However, this advantage is an artifact of the test set. The GTX 650 Ti Boost’s average is computed from three Geekbench results, all of which are relatively consistent. The T600’s average is dragged down by legacy Passmark DirectX tests where it scores extremely low, such as 32 in DirectX 10 and 25 in DirectX 12. In the tests that matter for modern use, the T600 is superior.

The GTX 650 Ti Boost’s nearest rivals in the database are all within 0.3% of its score, indicating it is firmly a mid-pack performer from its era. The T600’s nearest rivals include the GeForce GTX 970, which leads it by only 1.7%, suggesting the T600 is competitive with much higher-tier cards from older generations in certain workloads. The verdict is straightforward: the T600 is the better modern card, with superior efficiency, newer architecture, and decisive wins in the benchmarks that count. The GTX 650 Ti Boost is an end-of-life product that retains value only in legacy scenarios where its specific output configuration or Kepler-era driver behavior is required.

Specification Differences

| Specification | NVIDIA GeForce GTX 650 Ti Boost | NVIDIA T600 |

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

| Chip | GK106 | TU117 |

| Architecture | Kepler | Turing |

| Generation | GeForce 600 | Quadro Turing (Tx000) |

| Process Node | 28 nm | 12 nm |

| Transistors | 2,540 million | 4,700 million |

| Die Size | 221 mm² | 200 mm² |

| Transistor Density | 11.5M / mm² | 23.5M / mm² |

| Base Clock | 980 MHz | 735 MHz |

| Boost Clock | 1032 MHz | 1335 MHz |

| Memory Clock | 1502 MHz, 6 Gbps effective | 1250 MHz, 10 Gbps effective |

| Memory Size | 2 GB | 4 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 144.2 GB/s | 160.0 GB/s |

| Shading Units | 768 | 640 |

| TMUs | 64 | 40 |

| ROPs | 24 | 32 |

| Pixel Rate | 16.51 GPixel/s | 42.72 GPixel/s |

| Texture Rate | 66.05 GTexel/s | 53.40 GTexel/s |

| FP32 | 1.585 TFLOPS | 1.709 TFLOPS |

| FP16 | Not specified | 3.418 TFLOPS (2:1) |

| TDP | 134 W | 40 W |

| Slot Width | Dual-slot | Single-slot |

| Power Connectors | 1x 6-pin | None |

| Suggested PSU | 300 W | 200 W |

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

| Vulkan Support | 1.2.175 | 1.4 |

| Display Outputs | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 | 4x mini-DisplayPort 1.4a |

| Length | 241 mm (9.5 inches) | Not specified |

| Release Date | 2013-03-25 | 2021-04-11 |

| Production Status | End-of-life | End-of-life |

| Launch MSRP | 169 USD | Not specified |