AMD Radeon RX 6700 XT vs AMD Radeon RX 9070 Comparison

AMD
RADEON

AMD Radeon RX 6700 XT

CORE STATE Navi 22
VRAM 12 GB
CLOCK SPEED 2581 MHz
TDP 230 W
BUS WIDTH 192 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2021
VS
AMD
RADEON

Radeon RX 9070

CORE STATE Navi 48
VRAM 16 GB
CLOCK SPEED 2520 MHz
TDP 220 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 4.0
nm
PROCESS 4 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,435
6,290
geekbench_metal
130,896
N/A
geekbench_opencl
44,152
131,539
geekbench_vulkan
93,500
58,705
passmark_directx_10
124
141
passmark_directx_11
173
281
passmark_directx_12
77
74
passmark_directx_9
242
343
passmark_g2d
951
1,280
passmark_g3d
19,786
25,381
passmark_gpu_compute
9,336
14,737

Analysis: AMD Radeon RX 6700 XT vs AMD Radeon RX 9070

Where Each One Wins

The recorded benchmark data splits the two AMD cards into distinct roles. The AMD Radeon RX 9070 dominates the overall win count, taking 8 of the 10 head-to-head comparisons. Its victories span modern DirectX workloads, compute-heavy tests, and legacy DirectX paths. The AMD Radeon RX 6700 XT, meanwhile, wins only 2 tests, but those wins are not trivial: they come in the Vulkan API and the DirectX 12 PassMark test.

The RX 9070’s largest margin comes in the Geekbench OpenCL workload, where it scores 131,539 against the RX 6700 XT’s 44,152, a 66.4% difference in favor of the newer card. This is a compute-oriented result, and the RX 9070 also shows a 36.6% lead in PassMark GPU Compute (14,737 vs 9,336). For raw throughput tasks, such as rendering, physics simulation, or any workload that leans on general-purpose GPU compute, the RX 9070 is clearly the stronger option.

In DirectX 11, the RX 9070 again pulls ahead, scoring 281 versus 173, a 38.4% advantage. The DirectX 9 test shows a similar pattern: 343 for the RX 9070 versus 242 for the RX 6700 XT, a 29.4% gap. Even the 2D PassMark test favors the RX 9070 at 1,280 versus 951, a 25.7% lead. The 3DMark Steel Nomad DX12 result is also one-sided: 6,290 for the RX 9070 against 2,435 for the RX 6700 XT, a 61.3% difference. This is a modern, DirectX 12-based benchmark, and the RX 9070’s margin there is the second largest of the entire comparison.

The RX 6700 XT’s wins are narrower. In Geekbench Vulkan, it scores 93,500 against the RX 9070’s 58,705, a 59.3% lead for the older card. That is a substantial win, and it is the only API where the RX 6700 XT shows a clear advantage. The other win is in PassMark DirectX 12, where the RX 6700 XT scores 77 versus 74, a slim 4.1% margin. This is a close result, but it still counts as a victory for the RX 6700 XT in the recorded data.

Looking at the percentile rankings against all GPUs, the RX 6700 XT sits at the 72nd percentile, while the RX 9070 sits at the 69th percentile. Despite the RX 9070 winning most head-to-head tests, its average benchmark score is 23,877, which is lower than the RX 6700 XT’s 27,425. This is an important nuance: the RX 9070’s wins are concentrated in specific tests, but its overall average is dragged down by the Vulkan result and the DirectX 12 PassMark score. The RX 6700 XT’s nearest rivals include the NVIDIA GeForce RTX 4070 Mobile (average 27,435, delta 0%) and the NVIDIA GeForce RTX 3090 (average 27,565, delta -0.5%), indicating it competes with high-end mobile and previous-generation desktop parts. The RX 9070’s nearest rivals are the NVIDIA GeForce GTX TITAN Z (average 23,736, delta 0.6%) and the AMD Radeon RX 6800S (average 24,063, delta -0.8%), which places it in a different performance tier.

The Verdict

The data points to a clear choice for users who prioritize modern DirectX 12 and compute workloads: the AMD Radeon RX 9070. Its 61.3% lead in 3DMark Steel Nomad and 66.4% lead in Geekbench OpenCL are decisive. Anyone running current games that use DirectX 12, or any application that leverages OpenCL for acceleration, should favor the RX 9070 based on these measurements.

The AMD Radeon RX 6700 XT, however, is not obsolete. Its 59.3% advantage in Geekbench Vulkan is substantial, and it also edges out the RX 9070 in the PassMark DirectX 12 test, albeit by a tiny 4.1% margin. For users who rely on Vulkan-based applications or games, the RX 6700 XT is the better performer in the recorded data. This is a niche but real consideration.

The average benchmark scores complicate the verdict. The RX 6700 XT’s 27,425 average is higher than the RX 9070’s 23,877, and its 72nd percentile ranking beats the RX 9070’s 69th. If a user cares about overall consistency across a wide range of tests, the RX 6700 XT looks better on paper. But the RX 9070’s wins are in more demanding, modern workloads, which suggests it handles current software more effectively.

The production status also matters. The RX 6700 XT is end-of-life, while the RX 9070 is active. For new purchases, the RX 9070’s active status and its dominance in most benchmarks make it the pragmatic choice. The RX 6700 XT remains viable for Vulkan-specific use cases, but its end-of-life status and narrower wins limit its appeal.

Head-to-Head Benchmarks

The biggest win for the RX 9070 is in Geekbench OpenCL. The RX 9070 scores 131,539, while the RX 6700 XT scores 44,152. The delta is -66.4%, meaning the RX 6700 XT trails by that margin. This is the largest gap in the entire comparison, and it points to a fundamental difference in compute capability.

The 3DMark Steel Nomad DX12 test shows a similar story. The RX 9070 posts 6,290, and the RX 6700 XT posts 2,435, a 61.3% deficit for the older card. This is a modern DirectX 12 benchmark, and the RX 9070’s lead here is nearly as large as its OpenCL advantage. For current-generation gaming, this result is highly relevant.

PassMark GPU Compute favors the RX 9070 at 14,737 versus 9,336, a 36.6% lead. PassMark DirectX 11 shows the RX 9070 at 281 against 173, a 38.4% margin. DirectX 9 is also RX 9070 territory: 343 versus 242, a 29.4% gap. The 2D test, PassMark G2D, goes to the RX 9070 at 1,280 versus 951, a 25.7% lead. Even the DirectX 10 test, which is closer, still favors the RX 9070: 141 versus 124, a 12.1% advantage.

The RX 6700 XT’s wins are fewer but notable. In Geekbench Vulkan, it scores 93,500 against the RX 9070’s 58,705, a 59.3% margin. This is the second-largest delta in the entire set, and it flips the narrative in the Vulkan API. The other win is PassMark DirectX 12, where the RX 6700 XT scores 77 and the RX 9070 scores 74, a 4.1% margin. This is a narrow result, but it is a consistent edge for the RX 6700 XT in that specific test.

The overall win count is 8 for the RX 9070 and 2 for the RX 6700 XT. The RX 9070’s wins are also larger in magnitude, with three deltas above 36% and one above 60%. The RX 6700 XT’s wins include one above 59% and one close to 4%. The data shows the RX 9070 as the stronger card in most scenarios, with the RX 6700 XT holding a specific Vulkan niche.

FAQ

Q: Which card wins the Geekbench Vulkan test?

A: The AMD Radeon RX 6700 XT wins, scoring 93,500 against the RX 9070’s 58,705, a 59.3% advantage.

Q: What is the largest benchmark margin between the two cards?

A: The largest margin is in Geekbench OpenCL, where the RX 9070 scores 131,539 and the RX 6700 XT scores 44,152, a 66.4% difference.

Q: How does the RX 9070 fare in 3DMark Steel Nomad DX12?

A: The RX 9070 scores 6,290, while the RX 6700 XT scores 2,435, giving the RX 9070 a 61.3% lead.

Q: Which card has the higher average benchmark score?

A: The RX 6700 XT has the higher average at 27,425, compared to the RX 9070’s 23,877.

Q: Are there any tests where the RX 6700 XT beats the RX 9070?

A: Yes, the RX 6700 XT wins Geekbench Vulkan (93,500 vs 58,705) and PassMark DirectX 12 (77 vs 74).

Q: What are the percentile rankings for each card?

A: The RX 6700 XT sits at the 72nd percentile against all GPUs, while the RX 9070 sits at the 69th percentile.

Architecture Differences

The two cards come from different generations of AMD’s architecture. The RX 6700 XT uses the Navi 22 chip on RDNA 2.0, built on a 7 nm process at TSMC. The RX 9070 uses the Navi 48 chip on RDNA 4.0, built on a 4 nm process, also at TSMC. The process node shrink is significant: 7 nm versus 4 nm, and the transistor count reflects this. The RX 6700 XT packs 17,200 million transistors on a 335 mm² die, giving a transistor density of 51.3M per mm². The RX 9070 packs 53,900 million transistors on a 357 mm² die, with a density of 151.0M per mm². The die sizes are similar, but the RX 9070 fits over three times more transistors into a comparable area.

The architecture generations differ as well. The RX 6700 XT is from the Navi II generation (RX 6000), while the RX 9070 is from Navi IV (RX 9000). The successor to the RX 6700 XT is Navi III, and the RX 9070 is the successor of Navi III. This places the RX 9070 two generations ahead of the RX 6700 XT in AMD’s numbering scheme.

The memory subsystem also differs. The RX 6700 XT uses 12 GB of GDDR6 on a 192-bit bus, with a bandwidth of 384.0 GB/s. The RX 9070 uses 16 GB of GDDR6 on a 256-bit bus, with a bandwidth of 644.6 GB/s. The RX 9070 has more memory, a wider bus, and higher bandwidth.

Compute resources are higher on the RX 9070. It has 3,584 shading units, 224 texture mapping units, and 128 ROPs, versus the RX 6700 XT’s 2,560 shading units, 160 TMUs, and 64 ROPs. Ray tracing cores also increase from 40 on the RX 6700 XT to 56 on the RX 9070. Neither card lists tensor cores.

The FP32 and FP16 throughput figures reflect the architecture change. The RX 6700 XT delivers 13.21 TFLOPS FP32 and 26.43 TFLOPS FP16 (2:1 ratio). The RX 9070 delivers 36.13 TFLOPS FP32 and 36.13 TFLOPS FP16 (1:1 ratio). The RX 9070 has nearly triple the FP32 throughput, and its FP16 is no longer a doubled rate, indicating a different execution approach.

Specification Differences

The two cards differ in several recorded specifications. The process node changes from 7 nm to 4 nm. The transistor count goes from 17,200 million to 53,900 million. Die size goes from 335 mm² to 357 mm². Transistor density jumps from 51.3M per mm² to 151.0M per mm².

Clocks differ. The RX 6700 XT has a base clock of 2321 MHz, a boost of 2581 MHz, and a game clock of 2424 MHz. The RX 9070 has a lower base clock of 1330 MHz, a boost of 2520 MHz, and a game clock of 2070 MHz. Memory clocks also differ: the RX 6700 XT runs at 2000 MHz (16 Gbps effective), while the RX 9070 runs at 2518 MHz (20.1 Gbps effective).

Memory capacity is 12 GB for the RX 6700 XT versus 16 GB for the RX 9070. The bus width increases from 192 bit to 256 bit. Bandwidth rises from 384.0 GB/s to 644.6 GB/s.

Shading units increase from 2,560 to 3,584. TMUs go from 160 to 224. ROPs double from 64 to 128. Ray tracing cores go from 40 to 56.

Pixel rate and texture rate differ. The RX 6700 XT has a pixel rate of 165.2 GPixel/s and a texture rate of 413.0 GTexel/s. The RX 9070 has a pixel rate of 322.6 GPixel/s and a texture rate of 564.5 GTexel/s.

The TDP is 230 W for the RX 6700 XT and 220 W for the RX 9070. Power connectors differ: 1x 6-pin + 1x 8-pin for the RX 6700 XT, versus 2x 8-pin for the RX 9070. Both have a suggested PSU of 550 W.

The bus interface changes from PCIe 4.0 x16 to PCIe 5.0 x16. Display outputs differ: the RX 6700 XT has 1x HDMI 2.1 and 3x DisplayPort 1.4a, while the RX 9070 has 1x HDMI 2.1b and 3x DisplayPort 2.1a.

The RX 6700 XT is 267 mm long, 110 mm high, and 40 mm wide. The RX 9070 has no recorded dimensions. The RX 6700 XT is end-of-life, while the RX 9070 is active. Release dates differ: the RX 6700 XT launched on 2021-03-02, and the RX 9070 on 2025-03-05. Both are dual-slot cards.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6700 XT
RX 9070
Core Specs
Shading Units
2,560
3,584 +40.0%
Shaders
2,560
3,584 +40.0%
TMUs
160
224 +40.0%
ROPs
64
128 +100.0%
Compute Units
40
56 +40.0%
Clocks
Base Clock
2321 MHz
1330 MHz
Boost Clock
2581 MHz
2520 MHz
Game Clock
2424 MHz
2070 MHz
Memory Clock
2000 MHz 16 Gbps effective
2518 MHz 20.1 Gbps effective
Memory
Memory Size
12 GB
16 GB
VRAM (MB)
12,288
16,384 +33.3%
Memory Type
GDDR6
GDDR6
Memory Bus
192 bit
256 bit
Bandwidth
384.0 GB/s
644.6 GB/s
Cache
L1 Cache
128 KB per Array
—
L2 Cache
3 MB
8 MB
L3 Cache
96 MB
64 MB
L0 Cache
32 KB per WGP
32 KB per WGP
Performance
Pixel Rate
165.2 GPixel/s
322.6 GPixel/s
Texture Rate
413.0 GTexel/s
564.5 GTexel/s
FP32 (TFLOPS)
13.21 TFLOPS
36.13 TFLOPS
FP64 (TFLOPS)
825.9 GFLOPS (1:16)
1,129.0 GFLOPS (1:32)
FP16 (TFLOPS)
26.43 TFLOPS (2:1)
36.13 TFLOPS (1:1)
AI/RT
RT Cores
40
56 +40.0%
Matrix Cores
—
112
Power
TDP
230 W
220 W
TDP (W)
230
220 -4.3%
Suggested PSU
550 W
550 W
Power Connectors
1x 6-pin + 1x 8-pin
2x 8-pin
Architecture
Architecture
RDNA 2.0
RDNA 4.0
GPU Name
Navi 22
Navi 48
Generation
Navi II (RX 6000)
Navi IV (RX 9000)
Process Size
7 nm
4 nm
Transistors
17,200 million
53,900 million
Die Size
335 mm²
357 mm²
Foundry
TSMC
TSMC
Density
51.3M / mm²
151.0M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
2.2
Shader Model
6.8
6.9
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
—
Height
110 mm 4.3 inches
—
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x HDMI 2.1b3x DisplayPort 2.1a
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Launch Price
479 USD
549 USD
Production
End-of-life
Active
Predecessor
Navi
Navi III
Successor
Navi III
—
View Radeon RX 6700 XT Details View Radeon RX 9070 Details