AMD Radeon RX 5700 vs NVIDIA GeForce RTX 3070 Mobile Comparison

AMD
RADEON

AMD Radeon RX 5700

CORE STATE Navi 10
VRAM 8 GB
CLOCK SPEED 1725 MHz
TDP 180 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 1.0
nm
PROCESS 7 nm
LAUNCH DATE 2019
VS
NVIDIA
GEFORCE

GeForce RTX 3070 Mobile

CORE STATE GA104
VRAM 8 GB
CLOCK SPEED 1560 MHz
TDP 115 W
BUS WIDTH 256 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,862
2,380
geekbench_metal
86,079
N/A
geekbench_opencl
69,603
92,939
geekbench_vulkan
64,166
86,768
passmark_directx_10
87
113
passmark_directx_11
101
138
passmark_directx_12
54
64
passmark_directx_9
209
160
passmark_g2d
877
641
passmark_g3d
14,314
15,309
passmark_gpu_compute
6,517
6,827

Analysis: AMD Radeon RX 5700 vs NVIDIA GeForce RTX 3070 Mobile

The AMD Radeon RX 5700 and NVIDIA GeForce RTX 3070 Mobile represent two distinct approaches to high-performance graphics, separated by a generation and fundamentally different design philosophies. The data shows a clear overall winner in the NVIDIA part, but the AMD card secures specific and notable victories. Across ten head-to-head benchmark comparisons, the RTX 3070 Mobile claims eight wins, while the RX 5700 takes two. This analysis breaks down those results, examining the magnitude of the performance gaps and the architectural decisions that drive them.

Head-to-Head Benchmarks

The most decisive victories for the NVIDIA GeForce RTX 3070 Mobile come in modern compute and API-specific workloads. In the 3DMark Steel Nomad DX12 test, the RTX 3070 Mobile scores 2380 against the RX 5700’s 1862, a 21.8% advantage. This is a substantial lead in a demanding, modern DirectX 12 benchmark, indicating the Ampere architecture's efficiency in handling current-generation rendering paths. The Geekbench OpenCL results reinforce this trend, with the RTX 3070 Mobile posting 92939 compared to 69603, a 25.1% margin. The Vulkan API shows an even larger gap, with the RTX 3070 Mobile leading by 26% (86768 vs. 64166).

The pattern continues across legacy DirectX APIs, where the RTX 3070 Mobile maintains a consistent, albeit smaller, lead. In Passmark's DirectX 10 test, the NVIDIA card wins 113 to 87, a 23% difference. The DirectX 11 result is similarly lopsided, with the RTX 3070 Mobile scoring 138 against the RX 5700’s 101, a 26.8% advantage. Even in the older DirectX 12 test, the RTX 3070 Mobile prevails, scoring 64 versus 54, a 15.6% margin. The overall Passmark G3D score, a broad measure of graphics performance, also favors the RTX 3070 Mobile, which scores 15309 to the RX 5700’s 14314, a 6.5% lead. The Passmark GPU Compute test shows a closer race, with the RTX 3070 Mobile winning 6827 to 6517, a 4.5% margin.

However, the AMD Radeon RX 5700 secures two significant wins that should not be overlooked. The first is in the Passmark DirectX 9 test, where the RX 5700 scores 209 against the RTX 3070 Mobile’s 160. This is a 30.6% advantage for the AMD card, a massive lead in a legacy API that suggests a fundamental difference in how the two architectures handle older, fixed-function workloads. The second victory is in the Passmark G2D (2D graphics) test, where the RX 5700 scores 877 versus 641, a 36.8% margin. This substantial win in 2D performance is an outlier in an otherwise dominant NVIDIA showing.

The win counts and deltas tell a clear story. The RTX 3070 Mobile is faster in the vast majority of tests, with its largest wins coming in modern APIs and compute tasks. The RX 5700, while losing overall, demonstrates a specific strength in legacy DirectX 9 and 2D performance that is worth noting for users with older software libraries.

The Verdict

Based strictly on the benchmark data, the NVIDIA GeForce RTX 3070 Mobile is the superior performer for the vast majority of workloads. Its victories in modern APIs like DX12 and Vulkan, combined with its lead in compute benchmarks, make it the clear choice for contemporary gaming and general-purpose GPU tasks. The data shows an 8-2 win record in favor of the RTX 3070 Mobile, with the NVIDIA card holding a significant lead in several key areas.

The RTX 3070 Mobile is the pick for users who prioritize performance in current and future titles that rely on DirectX 12, Vulkan, or compute-heavy effects. Its 21.8% lead in 3DMark Steel Nomad and 26% lead in Geekbench Vulkan are decisive. The AMD Radeon RX 5700, however, is not without merit. Its 30.6% win in DirectX 9 and 36.8% win in 2D tests are not trivial, especially for a user whose primary software is older. For those running legacy applications or games that are heavily optimized for DirectX 9, the RX 5700 offers a clear advantage. The verdict is not a total rejection of the RX 5700, but rather a recognition that its strengths are narrowly focused on an older software ecosystem, while the RTX 3070 Mobile is the more future-proof and broadly capable card.

Where Each One Wins

The benchmark results provide a clear use-case split. The NVIDIA GeForce RTX 3070 Mobile is the definitive winner for all modern gaming scenarios. Its performance in 3DMark Steel Nomad (DX12) and the Geekbench Vulkan test indicates that it will excel in titles built on these APIs, which include the vast majority of AAA games released in recent years. Its lead in Passmark DirectX 11 and the general Passmark G3D test further cements its position as the superior choice for a wide range of current software. The RTX 3070 Mobile is also the better choice for compute-focused tasks, as evidenced by its wins in Geekbench OpenCL and Passmark GPU Compute, making it more suitable for tasks like video encoding, rendering, and scientific simulations that leverage GPGPU compute.

In contrast, the AMD Radeon RX 5700 carves out a niche in the legacy software space. Its significant victory in Passmark DirectX 9 is its primary selling point from a performance perspective. Users with a library of older games that use DirectX 9, or professional applications that rely on this API, will find the RX 5700 to be noticeably faster. The RX 5700's win in the Passmark G2D test also suggests it may be a better choice for 2D graphics workloads, though the practical applications for this are less common in a modern gaming context. For a user whose system is primarily used for older titles, the RX 5700's performance advantage is clear and measurable.

FAQ

Q: Which GPU is faster in the 3DMark Steel Nomad DX12 benchmark?

A: The NVIDIA GeForce RTX 3070 Mobile is significantly faster, scoring 2380 compared to the AMD Radeon RX 5700's 1862, a 21.8% advantage.

Q: Is the AMD Radeon RX 5700 better in any benchmark?

A: Yes. The AMD Radeon RX 5700 wins in the Passmark DirectX 9 test with a score of 209 versus 160 (a 30.6% lead) and in the Passmark G2D test with a score of 877 versus 641 (a 36.8% lead).

Q: How do the two GPUs compare in compute performance?

A: The NVIDIA GeForce RTX 3070 Mobile leads in compute workloads. It scores 92939 in Geekbench OpenCL versus 69603 for the RX 5700 (a 25.1% difference) and 6827 versus 6517 in Passmark GPU Compute (a 4.5% difference).

Q: What are the average benchmark scores for these cards?

A: The AMD Radeon RX 5700 has an average benchmark score of 22170, while the NVIDIA GeForce RTX 3070 Mobile has an average score of 20534.

Q: Which GPU has a higher percentile ranking among all GPUs?

A: The AMD Radeon RX 5700 has a higher percentile ranking, placing in the 67th percentile, while the NVIDIA GeForce RTX 3070 Mobile is in the 65th percentile.

Q: What is the DirectX feature level of each GPU?

A: The AMD Radeon RX 5700 supports DirectX 12 (12_1), while the NVIDIA GeForce RTX 3070 Mobile supports DirectX 12 Ultimate (12_2).

Architecture Differences

The performance disparities between these two GPUs are rooted in their fundamentally different architectures. The AMD Radeon RX 5700 is built on the RDNA 1.0 architecture using the Navi 10 chip, fabricated on a 7 nm process at TSMC. It contains 10,300 million transistors on a 251 mm² die, resulting in a transistor density of 41.0M per mm². In contrast, the NVIDIA GeForce RTX 3070 Mobile uses the Ampere architecture with the GA104 chip, built on an 8 nm process at Samsung. This chip is significantly larger, containing 17,400 million transistors on a 392 mm² die, for a density of 44.4M per mm².

The architectural differences extend to the core configurations. The RX 5700 has 2304 shading units, 144 texture mapping units (TMUs), and 64 render output units (ROPs). It has no dedicated RT or Tensor cores. The RTX 3070 Mobile, on the other hand, is equipped with 5120 shading units, 160 TMUs, and 80 ROPs. Crucially, it includes 40 RT cores and 160 Tensor cores, which are absent in the AMD part. This explains the RTX 3070 Mobile's support for DirectX 12 Ultimate (12_2) and its superior performance in modern APIs, which can leverage these dedicated hardware units.

The memory subsystems are identical on paper. Both GPUs feature 8 GB of GDDR6 memory on a 256-bit bus, providing 448.0 GB/s of bandwidth. However, the compute capabilities diverge sharply. The RX 5700 delivers 7.949 TFLOPS of FP32 performance and 15.90 TFLOPS of FP16 (2:1). The RTX 3070 Mobile, with its larger core count, delivers 15.97 TFLOPS of FP32 and 15.97 TFLOPS of FP16 (1:1). This near-doubling of FP32 throughput is the primary driver behind the RTX 3070 Mobile's significant lead in compute benchmarks like Geekbench OpenCL.

Power and physical characteristics also differ. The RX 5700 has a TDP of 180 W, while the RTX 3070 Mobile has a TDP of 115 W, a notable difference given the latter's higher performance. The RX 5700 is a dual-slot card requiring 1x 6-pin and 1x 8-pin power connectors and a 450 W power supply, whereas the RTX 3070 Mobile has no power connectors listed, as it is a mobile part. The RX 5700's clock speeds are higher (1465 MHz base, 1725 MHz boost, 1625 MHz game) compared to the RTX 3070 Mobile (1110 MHz base, 1560 MHz boost). This indicates that the NVIDIA card's performance advantage comes not from clock speed, but from its significantly larger and more feature-rich architecture.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 5700
RTX 3070 Mobile
Core Specs
Shading Units
2,304
5,120 +122.2%
Shaders
2,304
5,120 +122.2%
TMUs
144
160 +11.1%
ROPs
64
80 +25.0%
Compute Units
36
—
SM Count
—
40
Clocks
Base Clock
1465 MHz
1110 MHz
Boost Clock
1725 MHz
1560 MHz
Game Clock
1625 MHz
—
Memory Clock
1750 MHz 14 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
8 GB
8 GB
VRAM (MB)
8,192
8,192 0.0%
Memory Type
GDDR6
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
448.0 GB/s
448.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
4 MB
4 MB
Performance
Pixel Rate
110.4 GPixel/s
124.8 GPixel/s
Texture Rate
248.4 GTexel/s
249.6 GTexel/s
FP32 (TFLOPS)
7.949 TFLOPS
15.97 TFLOPS
FP64 (TFLOPS)
496.8 GFLOPS (1:16)
249.6 GFLOPS (1:64)
FP16 (TFLOPS)
15.90 TFLOPS (2:1)
15.97 TFLOPS (1:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
160
Power
TDP
180 W
115 W
TDP (W)
180
115 -36.1%
Suggested PSU
450 W
—
Power Connectors
1x 6-pin + 1x 8-pin
None
Architecture
Architecture
RDNA 1.0
Ampere
GPU Name
Navi 10
GA104
Generation
Navi (RX 5000)
GeForce 30 Mobile
Process Size
7 nm
8 nm
Transistors
10,300 million
17,400 million
Die Size
251 mm²
392 mm²
Foundry
TSMC
Samsung
Density
41.0M / mm²
44.4M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
8.6
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
—
Length
268 mm 10.6 inches
—
Height
111 mm 4.4 inches
—
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
Portable Device Dependent
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Other
Launch Price
349 USD
—
Production
End-of-life
End-of-life
Predecessor
Vega
GeForce 20 Mobile
Successor
Navi II
—
View Radeon RX 5700 Details View GeForce RTX 3070 Mobile Details