NVIDIA GeForce GTX 1060 3 GB vs NVIDIA GeForce GTX 690 Comparison

Where Each One Wins

The recorded data splits these two cards cleanly. The NVIDIA GeForce GTX 1060 3 GB wins both head-to-head benchmark comparisons. The GeForce GTX 690 does not win a single recorded test. In the OpenCL workload, the GTX 1060 3 GB scores 27001 against the GTX 690's 17399, a 55.2% advantage. That is a decisive gap. In the Vulkan test, the GTX 1060 3 GB scores 17475 versus 16675, a smaller but still clear 4.8% lead.

The use-case split follows directly from these numbers. The GTX 1060 3 GB is the stronger choice for compute-oriented applications that leverage OpenCL, where its lead is enormous. For Vulkan-based workloads, the difference narrows considerably, but the GTX 1060 3 GB still holds the edge. The GTX 690's only measurable strengths are circumstantial: it has a higher average score relative to its nearest rivals in the database (17037 average, with rivals like the AMD Radeon HD 7970M at 17019 and the NVIDIA Tesla M4 at 16932), but that average sits well below the GTX 1060 3 GB's 19334 average. In direct comparison, the GTX 690 trails in every recorded metric.

The percentile data reinforces the split. The GTX 1060 3 GB sits at the 64th percentile among all GPUs, while the GTX 690 sits at the 60th. That four-point difference in percentile ranking aligns with the benchmark wins: the newer card is more capable across the board, but the gap is modest in absolute terms when looking at aggregate scores. The GTX 1060 3 GB's average benchmark score of 19334 is 13.5% higher than the GTX 690's 17037. The wins are consistent, but the margin varies by workload.

Architecture Differences

The two cards come from different eras of NVIDIA design. The GTX 1060 3 GB uses the GP106 chip on the Pascal architecture, built on a 16 nm process at TSMC. The GTX 690 uses the GK104 chip on the Kepler architecture, built on a 28 nm process, also at TSMC. The process node difference is substantial: 16 nm versus 28 nm means the GTX 1060 3 GB packs far more transistors into a smaller die. The GTX 1060 3 GB has 4,400 million transistors on a 200 mm² die, giving a density of 22.0M transistors per mm². The GTX 690 has 3,540 million transistors on a 294 mm² die, with a density of 12.0M per mm². The density advantage is nearly double.

The memory configurations differ too. The GTX 1060 3 GB has 3 GB of GDDR5 on a 192-bit bus, with 192.2 GB/s of bandwidth. The GTX 690 has 2 GB of GDDR5 on a 256-bit bus, with 192.3 GB/s of bandwidth. The bandwidth is nearly identical, but the GTX 1060 3 GB has 50% more capacity. The GTX 690 compensates with a wider bus, but the extra memory on the GTX 1060 3 GB is a practical advantage for modern workloads.

The core counts tell a different story. The GTX 690 has 1536 shading units, 128 texture mapping units, and 32 ROPs. The GTX 1060 3 GB has 1152 shading units, 72 TMUs, and 48 ROPs. The GTX 690 has more shading units and TMUs, but the GTX 1060 3 GB has 50% more ROPs. That ROP advantage explains the pixel rate difference: the GTX 1060 3 GB delivers 81.98 GPixel/s versus the GTX 690's 32.61 GPixel/s. The texture rates are closer: 123.0 GTexel/s for the GTX 1060 3 GB versus 130.4 GTexel/s for the GTX 690.

Clock speeds favor the newer card. The GTX 1060 3 GB runs at a 1506 MHz base and 1708 MHz boost. The GTX 690 runs at 915 MHz base and 1019 MHz boost. The GTX 1060 3 GB's boost clock is 67.6% higher. FP32 compute also favors the GTX 1060 3 GB: 3.935 TFLOPS versus 3.130 TFLOPS, a 25.7% lead. The GTX 690 has no recorded FP16 performance, while the GTX 1060 3 GB lists 61.49 GFLOPS with a 1:64 ratio.

API support differs as well. The GTX 1060 3 GB supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 690 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The DirectX feature level is notably higher on the GTX 1060 3 GB. Display outputs also diverge: the GTX 1060 3 GB offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The GTX 690 offers 3x DVI and 1x mini-DisplayPort 1.2.

Power characteristics place them in different tiers. The GTX 1060 3 GB has a 120 W TDP with a single 6-pin connector and a 300 W suggested PSU. The GTX 690 has a 300 W TDP with dual 8-pin connectors and a 700 W suggested PSU. The GTX 690 consumes 2.5 times the power of the GTX 1060 3 GB. Physical dimensions also differ: the GTX 1060 3 GB is 250 mm long, while the GTX 690 is 279 mm long, 111 mm tall, and 38 mm wide. Both are dual-slot cards.

FAQ

Q: Which card has more memory?

A: The NVIDIA GeForce GTX 1060 3 GB has 3 GB of GDDR5, while the NVIDIA GeForce GTX 690 has 2 GB of GDDR5. The GTX 1060 3 GB offers 50% more memory capacity.

Q: Which card is faster in OpenCL benchmarks?

A: The GTX 1060 3 GB scores 27001 in Geekbench OpenCL, while the GTX 690 scores 17399. That is a 55.2% advantage for the GTX 1060 3 GB.

Q: What is the power consumption difference?

A: The GTX 1060 3 GB has a 120 W TDP with a single 6-pin power connector and a 300 W suggested PSU. The GTX 690 has a 300 W TDP with dual 8-pin connectors and a 700 W suggested PSU. The GTX 690 requires 2.5 times the power.

Q: Which card has higher pixel throughput?

A: The GTX 1060 3 GB delivers 81.98 GPixel/s, more than double the GTX 690's 32.61 GPixel/s. This stems from the GTX 1060 3 GB's 48 ROPs versus the GTX 690's 32 ROPs.

Q: How do the average benchmark scores compare?

A: The GTX 1060 3 GB has an average benchmark score of 19334, while the GTX 690 averages 17037. The GTX 1060 3 GB is 13.5% higher in aggregate performance.

Q: Which card supports a newer DirectX version?

A: The GTX 1060 3 GB supports DirectX 12 (12_1), while the GTX 690 supports DirectX 12 (11_0). The GTX 1060 3 GB has a higher feature level.

Specification Differences

• Process node: 16 nm (GTX 1060 3 GB) versus 28 nm (GTX 690)
• Transistors: 4,400 million (GTX 1060 3 GB) versus 3,540 million (GTX 690)
• Die size: 200 mm² (GTX 1060 3 GB) versus 294 mm² (GTX 690)
• Transistor density: 22.0M / mm² (GTX 1060 3 GB) versus 12.0M / mm² (GTX 690)
• Base clock: 1506 MHz (GTX 1060 3 GB) versus 915 MHz (GTX 690)
• Boost clock: 1708 MHz (GTX 1060 3 GB) versus 1019 MHz (GTX 690)
• Memory clock: 2002 MHz / 8 Gbps effective (GTX 1060 3 GB) versus 1502 MHz / 6 Gbps effective (GTX 690)
• Memory size: 3 GB (GTX 1060 3 GB) versus 2 GB (GTX 690)
• Memory bus width: 192 bit (GTX 1060 3 GB) versus 256 bit (GTX 690)
• Memory bandwidth: 192.2 GB/s (GTX 1060 3 GB) versus 192.3 GB/s (GTX 690)
• Shading units: 1152 (GTX 1060 3 GB) versus 1536 (GTX 690)
• TMUs: 72 (GTX 1060 3 GB) versus 128 (GTX 690)
• ROPs: 48 (GTX 1060 3 GB) versus 32 (GTX 690)
• Pixel rate: 81.98 GPixel/s (GTX 1060 3 GB) versus 32.61 GPixel/s (GTX 690)
• Texture rate: 123.0 GTexel/s (GTX 1060 3 GB) versus 130.4 GTexel/s (GTX 690)
• FP32: 3.935 TFLOPS (GTX 1060 3 GB) versus 3.130 TFLOPS (GTX 690)
• TDP: 120 W (GTX 1060 3 GB) versus 300 W (GTX 690)
• Power connectors: 1x 6-pin (GTX 1060 3 GB) versus 2x 8-pin (GTX 690)
• Suggested PSU: 300 W (GTX 1060 3 GB) versus 700 W (GTX 690)
• Display outputs: 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.4a (GTX 1060 3 GB) versus 3x DVI, 1x mini-DisplayPort 1.2 (GTX 690)
• DirectX support: 12 (12_1) (GTX 1060 3 GB) versus 12 (11_0) (GTX 690)
• Vulkan support: 1.4 (GTX 1060 3 GB) versus 1.2.175 (GTX 690)
• Length: 250 mm (GTX 1060 3 GB) versus 279 mm (GTX 690)
• Release date: 2016-08-17 (GTX 1060 3 GB) versus 2012-05-02 (GTX 690)

Head-to-Head Benchmarks

The database records two direct comparisons between these cards. The first is Geekbench OpenCL. The GTX 1060 3 GB scores 27001, while the GTX 690 scores 17399. The delta is 55.2% in favor of the GTX 1060 3 GB. This is the largest gap in any recorded test. The OpenCL result reflects the GTX 1060 3 GB's architectural advantages: higher clocks, more ROPs, and a newer process node. The GTX 690's 1536 shading units and 128 TMUs cannot overcome the clock deficit and the older Kepler design.

The second test is Geekbench Vulkan. The GTX 1060 3 GB scores 17475, while the GTX 690 scores 16675. The delta narrows to 4.8%. This is a much closer contest. The GTX 690's higher shading unit count and texture rate help bridge the gap in Vulkan workloads, which tend to utilize these resources more heavily. Still, the GTX 1060 3 GB maintains its winning record. The Vulkan result shows that the GTX 690 is not obsolete in every scenario, but it remains behind.

The aggregate picture matters. The GTX 1060 3 GB's average benchmark score is 19334, which places it at the 64th percentile. Its nearest rivals include the AMD Radeon RX 7900 XTX (19410, 0.4% ahead) and the NVIDIA TITAN Xp (19177, 0.8% behind). The GTX 690's average is 17037, at the 60th percentile, with nearest rivals like the AMD Radeon HD 7970M (17019, 0.1% behind) and the NVIDIA GeForce RTX 3070 (17208, 1% ahead). The GTX 690 sits in a lower performance band, and its direct comparison losses confirm that placement.

The Verdict

The data points to a clear winner. The NVIDIA GeForce GTX 1060 3 GB outperforms the NVIDIA GeForce GTX 690 in every recorded benchmark. It wins both head-to-head tests, has a higher average benchmark score (19334 versus 17037), and occupies a higher percentile ranking (64th versus 60th). The GTX 1060 3 GB also requires far less power: 120 W TDP versus 300 W, with a single 6-pin connector instead of dual 8-pins, and a 300 W suggested PSU instead of 700 W. It supports newer APIs, including DirectX 12 (12_1) and Vulkan 1.4, and has 50% more memory.

The GTX 690 retains some theoretical advantages. It has more shading units (1536 versus 1152), more TMUs (128 versus 72), and a wider memory bus (256 bit versus 192 bit). Its texture rate is slightly higher (130.4 GTexel/s versus 123.0 GTexel/s). But these advantages do not translate into benchmark wins. The GTX 690 loses both recorded tests, and the OpenCL loss is severe at 55.2%. The GTX 690's higher power draw and older architecture make it a less practical choice for modern workloads.

For a user prioritizing compute performance, the GTX 1060 3 GB is the clear pick. For a user who values the GTX 690's higher shading unit count and texture throughput, the Vulkan result (within 4.8%) suggests it can still hold its own in specific scenarios. But the recorded data offers no scenario where the GTX 690 wins outright. The GTX 1060 3 GB is the better card across the board, with the only caveat being that its closest rivals in the database, like the AMD Radeon RX 7900 XTX, sit just 0.4% higher in average score. The GTX 690, meanwhile, sits 13.5% below the GTX 1060 3 GB in aggregate performance. Choose the GTX 1060 3 GB unless the specific workload heavily favors the GTX 690's unique core configuration, which the current benchmark data does not demonstrate.