NVIDIA GeForce GTX 980 vs NVIDIA T600 Comparison

The NVIDIA GeForce GTX 980 and NVIDIA T600 occupy very different positions in the database, despite sharing the same manufacturer. The GTX 980 is a former flagship from the GeForce 900 generation, while the T600 is a low-profile workstation card built on the Turing architecture. The recorded benchmarks show a clear performance hierarchy, but the T600 has specific strengths that matter for certain workloads. The data below breaks down where each card wins and who should consider it.

Head-to-Head Benchmarks

The GTX 980 dominates the shared test suite, winning 8 out of 9 head-to-head comparisons. The largest margin comes in the compute test, where the GTX 980 scores 4753 against the T600's 2402. That is a 97.9% advantage, meaning the older card delivers nearly double the raw compute throughput. The Passmark DirectX 12 test shows a similar pattern, with the GTX 980 scoring 46 versus 25, an 84% lead. DirectX 11 also favors the GTX 980 significantly, with scores of 83 versus 49, a 69.4% gap.

The 3D graphics test reinforces the GTX 980's dominance. It scores 11095 in Passmark G3D, while the T600 manages only 6479. That is a 71.2% difference. DirectX 10 follows the same trend, with the GTX 980 scoring 53 against the T600's 32, a 65.6% lead. Even the legacy DirectX 9 test shows a substantial gap, with scores of 164 versus 114, a 43.9% advantage for the GTX 980.

The Geekbench OpenCL test also goes to the GTX 980, scoring 34676 versus 27875. That is a 24.4% win. The 2D graphics test is closer, with the GTX 980 at 792 and the T600 at 756, a modest 4.8% difference. The only test where the T600 comes out ahead is Geekbench Vulkan, where it scores 25580 versus the GTX 980's 22543. That is an 11.9% advantage for the T600, which is notable because it is the only modern API test in the shared suite where the newer architecture pulls ahead.

The overall average benchmark scores reflect this split. The GTX 980 averages 8167 across all recorded tests, while the T600 averages 7035. That places the GTX 980 at the 43rd percentile of all GPUs in the database, with the T600 slightly behind at the 39th percentile. The nearest rivals for the GTX 980 are the GeForce GTX 950M, with an average score of 8135 and a delta of 0.4%, and the Radeon R9 M360 at 8129 with a 0.5% delta. The T600's closest competitors are the GeForce GTX 680M at 7023 with a 0.2% delta, and the GeForce GTX 970, which scores 7157 and is 1.7% faster.

Architecture Differences

The GTX 980 uses the GM204 chip, built on the Maxwell 2.0 architecture. It is fabricated on a 28 nm process at TSMC, with 5,200 million transistors packed into a 398 mm² die. The transistor density works out to 13.1 million per square millimeter. The T600 uses the TU117 chip, based on the Turing architecture. It is made on a 12 nm process, also at TSMC, with 4,700 million transistors on a much smaller 200 mm² die. That gives it a higher transistor density of 23.5 million per square millimeter.

The core configurations differ sharply. The GTX 980 has 2048 shading units, 128 texture mapping units, and 64 raster output units. The T600 has 640 shading units, 40 TMUs, and 32 ROPs. That is roughly one third of the shading units and TMUs, and half the ROPs. Neither card has dedicated ray tracing cores or tensor cores, so those features are absent from both.

Clock speeds tell a different story. The GTX 980 runs at a base clock of 1127 MHz and a boost clock of 1216 MHz. The T600 has a lower base clock at 735 MHz but a higher boost clock at 1335 MHz. The memory clocks also differ, with the GTX 980 using 1753 MHz memory, which translates to 7 Gbps effective, while the T600 runs at 1250 MHz, or 10 Gbps effective.

Memory configurations are similar in capacity but not in type or bandwidth. Both cards have 4 GB of memory, but the GTX 980 uses GDDR5 on a 256-bit bus, delivering 224.4 GB/s of bandwidth. The T600 uses GDDR6 on a 128-bit bus, which gives it 160.0 GB/s. The wider bus on the GTX 980 provides a significant bandwidth advantage.

The pixel and texture rates reflect the hardware differences. The GTX 980 achieves 77.82 GPixel/s and 155.6 GTexel/s. The T600 achieves 42.72 GPixel/s and 53.40 GTexel/s. The FP32 compute performance is also far apart, with the GTX 980 at 4.981 TFLOPS and the T600 at 1.709 TFLOPS. The T600 does have FP16 capability at 3.418 TFLOPS with a 2:1 ratio, but the GTX 980 has no recorded FP16 figure.

Power and physical design differ as well. The GTX 980 has a TDP of 165 W, requires two 6-pin power connectors, and takes up a dual-slot width. It also needs a suggested PSU of 450 W. The T600 has a TDP of only 40 W, needs no power connectors, and is a single-slot card with a suggested PSU of 200 W. The GTX 980 measures 267 mm in length, 111 mm in height, and 40 mm in width. The T600 has no recorded dimensions.

The display outputs are different, with the GTX 980 offering one DVI, one HDMI 2.0, and three DisplayPort 1.2 connections. The T600 offers four mini-DisplayPort 1.4a connections. Both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4.

The Verdict

The GTX 980 is the clear winner for raw performance in nearly every recorded test. It leads by double-digit percentages in all but one shared benchmark, with margins ranging from 4.8% in the 2D test to 97.9% in compute. If the priority is maximum frame rates or compute throughput, the GTX 980 is the obvious choice based on the data.

The T600 wins only in the Geekbench Vulkan test, where it holds an 11.9% advantage. That single win suggests it may have better driver optimization or architectural efficiency for Vulkan workloads. The T600 also draws far less power, with a 40 W TDP versus 165 W, and fits in a single slot with no external power connectors. That makes it suitable for small form factor systems or workstations where space and power are constrained.

The GTX 980 sits at the 43rd percentile of all GPUs, while the T600 is at the 39th. Both are mid-pack performers in the broader database. The GTX 980's average benchmark score of 8167 is about 16% higher than the T600's 7035. The nearest rival data shows the GTX 980 trading blows with mobile GPUs like the GTX 950M, while the T600 is close to the GTX 680M and just behind the GTX 970.

For gaming or general compute tasks, the GTX 980 is the stronger card. For a low-power workstation with Vulkan-focused applications, the T600 has a specific edge. The choice depends entirely on whether raw performance or efficiency matters more.

FAQ

Q: Which card has a higher average benchmark score?

A: The GTX 980 averages 8167 across all recorded benchmarks, while the T600 averages 7035.

Q: In which test does the T600 beat the GTX 980?

A: The T600 wins the Geekbench Vulkan test with a score of 25580 versus 22543, an 11.9% advantage.

Q: What is the largest performance gap between the two cards?

A: The Passmark GPU compute test shows the biggest difference, with the GTX 980 scoring 4753 versus the T600's 2402, a 97.9% lead.

Q: How do the memory bandwidths compare?

A: The GTX 980 has a bandwidth of 224.4 GB/s on a 256-bit bus, while the T600 has 160.0 GB/s on a 128-bit bus.

Q: Are there any differences in API support?

A: Both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, so there is no difference in API support.

Q: Which card has a higher boost clock?

A: The T600 has a boost clock of 1335 MHz, while the GTX 980 has a boost clock of 1216 MHz.

Where Each One Wins

The GTX 980 wins in 8 of the 9 shared tests. Its biggest advantages are in compute, where it nearly doubles the T600's score, and in DirectX 12, where it leads by 84%. It also wins decisively in DirectX 11, DirectX 10, and DirectX 9, with leads of 69.4%, 65.6%, and 43.9% respectively. The 3D graphics test shows a 71.2% advantage, and the OpenCL test shows a 24.4% lead. Even the 2D test goes to the GTX 980, though by a slim 4.8%.

The T600 wins in one area: Geekbench Vulkan. Its score of 25580 beats the GTX 980's 22543 by 11.9%. This indicates the Turing architecture handles Vulkan workloads more efficiently, which could matter for specific applications that rely heavily on that API.

For gaming, the GTX 980 is the better choice across the board based on DirectX 9, 10, 11, and 12 results. For compute tasks, the GTX 980 also dominates, as shown by the GPU compute and OpenCL tests. The T600's only clear use case is Vulkan-based workloads, where it has a measurable edge.

Specification Differences

| Specification | NVIDIA GeForce GTX 980 | NVIDIA T600 |

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

| Chip | GM204 | TU117 |

| Architecture | Maxwell 2.0 | Turing |

| Process Node | 28 nm | 12 nm |

| Transistors | 5,200 million | 4,700 million |

| Die Size | 398 mm² | 200 mm² |

| Transistor Density | 13.1M / mm² | 23.5M / mm² |

| Base Clock | 1127 MHz | 735 MHz |

| Boost Clock | 1216 MHz | 1335 MHz |

| Memory Clock | 1753 MHz (7 Gbps effective) | 1250 MHz (10 Gbps effective) |

| Memory Size | 4 GB | 4 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 224.4 GB/s | 160.0 GB/s |

| Shading Units | 2048 | 640 |

| Texture Mapping Units | 128 | 40 |

| Raster Output Units | 64 | 32 |

| Pixel Rate | 77.82 GPixel/s | 42.72 GPixel/s |

| Texture Rate | 155.6 GTexel/s | 53.40 GTexel/s |

| FP32 Performance | 4.981 TFLOPS | 1.709 TFLOPS |

| FP16 Performance | Not recorded | 3.418 TFLOPS (2:1) |

| TDP | 165 W | 40 W |

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

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

| Suggested PSU | 450 W | 200 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 | 4x mini-DisplayPort 1.4a |

| DirectX Support | 12 (12_1) | 12 (12_1) |

| OpenGL Support | 4.6 | 4.6 |

| Vulkan Support | 1.4 | 1.4 |

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