AMD Radeon RX 5700 XT vs NVIDIA GeForce GTX 770 Comparison

AMD
RADEON

AMD Radeon RX 5700 XT

CORE STATE Navi 10
VRAM 8 GB
CLOCK SPEED 1905 MHz
TDP 225 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 1.0
nm
PROCESS 7 nm
LAUNCH DATE 2019
VS
NVIDIA
GEFORCE

GeForce GTX 770

CORE STATE GK104
VRAM 2 GB
CLOCK SPEED 1085 MHz
TDP 230 W
BUS WIDTH 256 bit
ARCHITECTURE Kepler
nm
PROCESS 28 nm
LAUNCH DATE 2013

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,134
N/A
geekbench_metal
74,647
9,369
geekbench_opencl
9,524
15,707
geekbench_vulkan
68,310
19,166
passmark_directx_10
97
N/A
passmark_directx_11
116
N/A
passmark_directx_12
64
N/A
passmark_directx_9
226
N/A
passmark_g2d
922
N/A
passmark_g3d
16,277
N/A
passmark_gpu_compute
7,650
N/A

Analysis: AMD Radeon RX 5700 XT vs NVIDIA GeForce GTX 770

Head-to-Head Benchmarks

The recorded data includes three shared benchmark tests between the AMD Radeon RX 5700 XT and the NVIDIA GeForce GTX 770, and the results are not subtle. The AMD card wins two of the three comparisons, and it does so by margins that are frankly enormous.

The clearest victory for the RX 5700 XT comes in Geekbench Metal. The AMD card scores 74,647 while the GTX 770 manages only 9,369. That is a 696.7% difference, meaning the RX 5700 XT delivers roughly eight times the Metal performance of the older NVIDIA card. In practical terms, this is not a close contest; it is a generational gap made visible in a single number.

The Vulkan test tells a similar story, though the margin is smaller. The RX 5700 XT scores 68,310 against the GTX 770's 19,166, a 256.4% advantage. Again, the AMD card is more than three times faster in this API. For any workload that relies on Vulkan, the data is unambiguous.

The one benchmark where the GTX 770 strikes back is Geekbench OpenCL. Here the NVIDIA card scores 15,707 while the RX 5700 XT records only 9,524. That gives the GTX 770 a 39.4% lead in this specific test. It is the only head-to-head win for the older card, and it is notably this is a compute-oriented benchmark rather than a pure graphics workload. The result suggests that in certain OpenCL compute tasks, the older Kepler architecture still has some life, but it does not change the overall picture.

Looking at average benchmark scores across all recorded tests, the RX 5700 XT posts 16,361 while the GTX 770 averages 14,747. That is a difference of roughly 11% in favor of the AMD card. The percentile ranks are close, with the RX 5700 XT at the 59th percentile of all GPUs and the GTX 770 at the 57th percentile, but the average score gap tells the real story.

Architecture Differences

The two cards come from different eras of GPU design, and the architecture gap explains most of the performance delta. The AMD Radeon RX 5700 XT uses the Navi 10 chip built on RDNA 1.0 architecture, manufactured on a 7 nm process at TSMC. The NVIDIA GeForce GTX 770 uses the GK104 chip with Kepler architecture, manufactured on a 28 nm process, also at TSMC. The process node difference alone is massive: 7 nm versus 28 nm translates directly into transistor density. The RX 5700 XT packs 10,300 million transistors into a 251 mm² die, giving a density of 41.0 million transistors per square millimeter. The GTX 770 has 3,540 million transistors on a 294 mm² die, which works out to 12.0 million per square millimeter. The AMD chip is both smaller and far denser.

Shader configuration also differs sharply. The RX 5700 XT has 2,560 shading units, 160 texture mapping units, and 64 ROPs. The GTX 770 has 1,536 shading units, 128 TMUs, and only 32 ROPs. The AMD card has nearly double the shader count and double the ROP count. Neither card has ray tracing cores or tensor cores, so that is not a differentiator here.

Memory architecture is another clear divide. The RX 5700 XT uses 8 GB of GDDR6 on a 256-bit bus, delivering 448.0 GB/s of bandwidth. The GTX 770 uses 2 GB of GDDR5 on a 256-bit bus, delivering 224.4 GB/s. The AMD card has four times the capacity and exactly double the bandwidth. Clock speeds also favor the newer card: the RX 5700 XT has a base clock of 1605 MHz and a boost of 1905 MHz, while the GTX 770 operates at 1046 MHz base and 1085 MHz boost.

API support reflects the age difference. The RX 5700 XT supports DirectX 12 (feature level 12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 770 supports DirectX 12 (feature level 11_0), OpenGL 4.6, and Vulkan 1.2.175. Both cards are dual-slot designs with the same power connector configuration (1x 6-pin plus 1x 8-pin) and the same suggested PSU of 550 W.

Where Each One Wins

The benchmark data makes it clear where each card has its strengths, and the split is not simply "newer wins everywhere." The RX 5700 XT dominates in Metal and Vulkan workloads. Its Metal score of 74,647 is in a different universe from the GTX 770's 9,369. For Vulkan, the RX 5700 XT's 68,310 versus 19,166 means the AMD card is the only realistic choice for modern Vulkan-based games or applications. The RX 5700 XT also has a substantial lead in pixel rate (121.9 GPixel/s versus 34.72 GPixel/s) and texture rate (304.8 GTexel/s versus 138.9 GTexel/s), which translates directly to better rasterization performance in most graphics workloads.

The GTX 770's sole win in OpenCL is interesting. Its score of 15,707 against 9,524 suggests that for specific OpenCL compute tasks, the older card can actually outperform the newer one. This may be relevant for legacy applications that are optimized for OpenCL rather than Vulkan or Metal. However, this is a narrow victory. The GTX 770 also has a lower TDP on paper, 230 W versus 225 W for the RX 5700 XT, but that difference is negligible in practice.

It is also notably the GTX 770 has no recorded score in several modern benchmark suites. The database includes DirectX 9, 10, 11, 12, G2D, G3D, and compute scores for the RX 5700 XT, but the GTX 770 only has entries for Metal, OpenCL, and Vulkan. This means the GTX 770 simply cannot be evaluated in many of the tests that matter for modern gaming, which is itself a form of evidence about its limitations.

Specification Differences

The specification sheet highlights how far GPU design advanced between 2013 and 2019. The RX 5700 XT uses a 7 nm process; the GTX 770 uses 28 nm. Transistor count is 10,300 million versus 3,540 million. Die size is 251 mm² versus 294 mm², meaning the AMD chip is physically smaller despite holding nearly three times the transistors.

Memory is a major differentiator: 8 GB GDDR6 versus 2 GB GDDR5. Bus width is the same at 256 bit, but bandwidth is 448.0 GB/s versus 224.4 GB/s. The RX 5700 XT has 2,560 shading units, 160 TMUs, and 64 ROPs, against the GTX 770's 1,536 shading units, 128 TMUs, and 32 ROPs. Pixel rate is 121.9 GPixel/s versus 34.72 GPixel/s, and texture rate is 304.8 GTexel/s versus 138.9 GTexel/s.

FP32 compute is 9.754 TFLOPS for the RX 5700 XT versus 3.333 TFLOPS for the GTX 770, nearly triple the raw compute throughput. The AMD card also supports FP16 at 19.51 TFLOPS with a 2:1 ratio, while the GTX 770 has no recorded FP16 capability. The RX 5700 XT supports PCIe 4.0 x16; the GTX 770 is limited to PCIe 3.0 x16.

Display outputs differ as well. The RX 5700 XT has 1x HDMI 2.0b and 3x DisplayPort 1.4a. The GTX 770 has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The GTX 770 is slightly longer at 267 mm versus 272 mm, but the RX 5700 XT is thinner at 36 mm versus 38 mm. Both cards have a 225 W and 230 W TDP respectively, both dual-slot, both requiring a 550 W PSU.

FAQ

Q: Which card is faster in Vulkan?

A: The AMD Radeon RX 5700 XT scores 68,310 in Geekbench Vulkan, which is 256.4% higher than the GTX 770's 19,166.

Q: Does the GTX 770 win any benchmark?

A: Yes, it wins Geekbench OpenCL with a score of 15,707, a 39.4% advantage over the RX 5700 XT's 9,524.

Q: How much VRAM does each card have?

A: The RX 5700 XT has 8 GB of GDDR6, while the GTX 770 has 2 GB of GDDR5.

Q: What is the average benchmark score difference?

A: The RX 5700 XT averages 16,361 across all tests, while the GTX 770 averages 14,747, a difference of roughly 11%.

Q: Do both cards support ray tracing?

A: No. Neither card has ray tracing cores or tensor cores in their recorded specifications.

Q: Which card has better memory bandwidth?

A: The RX 5700 XT delivers 448.0 GB/s, exactly double the GTX 770's 224.4 GB/s, despite both using a 256-bit bus.

The Verdict

The data points to a clear conclusion for anyone deciding between these two cards today. The AMD Radeon RX 5700 XT is the superior GPU in nearly every meaningful category. Its Metal score is 696.7% higher, its Vulkan score is 256.4% higher, and its average benchmark score is 11% higher. It has four times the VRAM, double the memory bandwidth, nearly triple the FP32 compute, and a much more efficient 7 nm process versus 28 nm.

The GTX 770 is not without merit. Its OpenCL win shows that it can still handle certain compute tasks, and its 57th percentile rank against all GPUs means it is not a useless piece of hardware. But the absence of benchmark scores in DirectX 9 through 12, G2D, G3D, and compute tests for the GTX 770 in the database is telling. It simply was not tested in those workloads, likely because it cannot run them at a competitive level or because those tests did not exist or matter during its lifespan.

For modern gaming, Vulkan-based titles, Metal-based macOS workloads, or any application that uses more than 2 GB of VRAM, the RX 5700 XT is the only sensible pick. For legacy OpenCL compute tasks where the GTX 770's architecture has an edge, the older card has a narrow use case. But as an overall GPU, the RX 5700 XT wins decisively. The 59th percentile rank versus the 57th percentile rank understates the gap because the average score difference of 1,614 points is what actually matters. If you have to choose one, choose the RX 5700 XT, unless your specific workload is locked to OpenCL.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 5700 XT
GTX 770
Core Specs
Shading Units
2,560
1,536 -40.0%
Shaders
2,560
1,536 -40.0%
TMUs
160
128 -20.0%
ROPs
64
32 -50.0%
Compute Units
40
—
Clocks
Base Clock
1605 MHz
1046 MHz
Boost Clock
1905 MHz
1085 MHz
Game Clock
1755 MHz
—
Memory Clock
1750 MHz 14 Gbps effective
1753 MHz 7 Gbps effective
Memory
Memory Size
8 GB
2 GB
VRAM (MB)
8,192
2,048 -75.0%
Memory Type
GDDR6
GDDR5
Memory Bus
256 bit
256 bit
Bandwidth
448.0 GB/s
224.4 GB/s
Cache
L1 Cache
—
16 KB (per SMX)
L2 Cache
4 MB
512 KB
Performance
Pixel Rate
121.9 GPixel/s
34.72 GPixel/s
Texture Rate
304.8 GTexel/s
138.9 GTexel/s
FP32 (TFLOPS)
9.754 TFLOPS
3.333 TFLOPS
FP64 (TFLOPS)
609.6 GFLOPS (1:16)
138.9 GFLOPS (1:24)
FP16 (TFLOPS)
19.51 TFLOPS (2:1)
—
Power
TDP
225 W
230 W
TDP (W)
225
230 +2.2%
Suggested PSU
550 W
550 W
Power Connectors
1x 6-pin + 1x 8-pin
1x 6-pin + 1x 8-pin
Architecture
Architecture
RDNA 1.0
Kepler
GPU Name
Navi 10
GK104
Generation
Navi (RX 5000)
GeForce 700
Process Size
7 nm
28 nm
Transistors
10,300 million
3,540 million
Die Size
251 mm²
294 mm²
Foundry
TSMC
TSMC
Density
41.0M / mm²
12.0M / mm²
API Support
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.2.175
OpenCL
2.1
3.0
CUDA
—
3.0
Shader Model
6.8
6.5 (5.1)
Physical
Slot Width
Dual-slot
Dual-slot
Length
272 mm 10.7 inches
267 mm 10.5 inches
Height
111 mm 4.4 inches
111 mm 4.4 inches
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Other
Launch Price
399 USD
399 USD
Production
End-of-life
End-of-life
Predecessor
Vega
GeForce 600
Successor
Navi II
GeForce 900
View Radeon RX 5700 XT Details View GeForce GTX 770 Details