AMD Radeon R9 370X vs AMD Radeon RX 7900 XT Comparison

AMD
RADEON

AMD Radeon R9 370X

CORE STATE Trinidad
VRAM 2 GB
CLOCK SPEED 1030 MHz
TDP 180 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
AMD
RADEON

Radeon RX 7900 XT

CORE STATE Navi 31
VRAM 20 GB
CLOCK SPEED 2394 MHz
TDP 300 W
BUS WIDTH 320 bit
ARCHITECTURE RDNA 3.0
nm
PROCESS 5 nm
LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_metal
12,676
N/A
geekbench_opencl
25,893
12,756
geekbench_vulkan
9,018
71,068
3dmark_3dmark_steel_nomad_dx12
N/A
5,623
passmark_directx_10
N/A
158
passmark_directx_11
N/A
340
passmark_directx_12
N/A
110
passmark_directx_9
N/A
322
passmark_g2d
N/A
1,232
passmark_g3d
N/A
29,009
passmark_gpu_compute
N/A
16,828

Analysis: AMD Radeon R9 370X vs AMD Radeon RX 7900 XT

Head-to-Head Benchmarks

The recorded data contains two directly comparable benchmark results between the AMD Radeon R9 370X and the AMD Radeon RX 7900 XT, and each card claims one decisive victory. In Geekbench OpenCL, the R9 370X scores 25,893 against the RX 7900 XT's 12,756, a 103% advantage that places the older card firmly ahead in this specific compute workload. This is not a marginal edge; it is a doubling of performance, and it suggests that the R9 370X's driver maturity or workload characteristics give it an unexpected lead in OpenCL testing. Conversely, the Geekbench Vulkan result flips the script entirely: the RX 7900 XT posts 71,068 while the R9 370X manages 9,018, a delta of -87.3% from the perspective of the older card. In Vulkan, the newer architecture is nearly eight times faster, reflecting the massive generational leap in graphics API throughput.

The average benchmark scores in the database further contextualize these head-to-head results. The R9 370X carries an average benchmark score of 15,862, while the RX 7900 XT averages 13,745. These averages, however, are drawn from different benchmark suites, so they do not directly compare the two cards against each other. Instead, they show where each card sits relative to its own peer group. The R9 370X's nearest rivals include the AMD Radeon RX 7700 (average 15,852, delta 0.1%), the AMD Radeon RX 9060 (16,014, delta -1%), the AMD Radeon Pro W5500 (15,679, delta 1.2%), and the NVIDIA GeForce RTX 3060 Ti (16,129, delta -1.7%). This places the R9 370X in a tight cluster where it trades blows with modern mid-range cards, often within a few percentage points. The RX 7900 XT, by contrast, sits near the AMD Radeon 660M (13,812, delta -0.5%), the NVIDIA RTX A2000 Mobile (13,821, delta -0.5%), the AMD Radeon RX 570X (13,871, delta -0.9%), and the AMD Radeon RX 9070 XT (13,543, delta 1.5%). The RX 7900 XT's average is dragged down by its inclusion of PassMark DirectX 9, 10, 11, and 12 scores, which are low (322, 158, 340, and 110 respectively) compared to its Geekbench Vulkan result.

The head-to-head data tells a clear story: the R9 370X owns OpenCL, the RX 7900 XT owns Vulkan, and the two benchmarks measure fundamentally different aspects of GPU capability. The OpenCL result likely rewards the R9 370X's simpler GCN 1.0 compute pipeline, while the Vulkan result rewards the RX 7900 XT's modern RDNA 3.0 architecture with dedicated ray tracing cores and a much higher shading unit count. The wins are split evenly at one apiece, but the magnitude of the Vulkan victory dwarfs the OpenCL lead in raw point difference. The RX 7900 XT's Vulkan score is 62,050 points higher than the R9 370X's, while the R9 370X's OpenCL lead is 13,137 points. In absolute terms, the newer card's advantage is nearly five times larger.

Where Each One Wins

The R9 370X wins in OpenCL compute workloads, as evidenced by its 25,893 score versus the RX 7900 XT's 12,756. This suggests that users running OpenCL-based applications, such as certain scientific simulations, video encoding pipelines, or legacy compute tasks, may find the older card unexpectedly competitive. The R9 370X's 2.637 TFLOPS of FP32 performance and 80 texture units, paired with its 28 nm process node, appear to handle this specific workload efficiently. The database also shows the R9 370X holds a 58th percentile rank among all GPUs, which is surprisingly high for a card released in 2015, and its average benchmark score of 15,862 places it within 1.7% of the NVIDIA GeForce RTX 3060 Ti.

The RX 7900 XT wins decisively in Vulkan graphics, scoring 71,068 versus the R9 370X's 9,018. This is the modern gaming and compute API, and the RX 7900 XT's 5,376 shading units, 336 texture units, 192 ROPs, and 84 ray tracing cores deliver the kind of raw throughput that the R9 370X cannot match. The RX 7900 XT also posts strong PassMark results: 29,009 in G3D, 16,828 in GPU compute, and 1,232 in G2D. Its DirectX 12 score of 110 is low, but its DirectX 11 score of 340 and DirectX 9 score of 322 show better legacy compatibility than the modern API numbers suggest. For any workload that leans on Vulkan, the RX 7900 XT is the clear choice, and its 20 GB of GDDR6 memory with 800.0 GB/s bandwidth provides a massive data pipeline for high-resolution textures and complex scenes.

The split is clean: compute-heavy OpenCL favors the older card, graphics-heavy Vulkan favors the newer card. The R9 370X's 2 GB of GDDR5 memory with 179.2 GB/s bandwidth is a bottleneck for modern workloads, but its OpenCL score proves that raw memory bandwidth is not always the limiting factor. The RX 7900 XT's 20 GB memory and 800.0 GB/s bandwidth, combined with its 51.48 TFLOPS FP32 and 103.0 TFLOPS FP16 (2:1), give it a massive theoretical ceiling that the Vulkan benchmark confirms. Users should pick based on the API their applications use, not on general-purpose assumptions about newer being better.

FAQ

Q: Which card wins in Geekbench Vulkan?

A: The AMD Radeon RX 7900 XT wins with a score of 71,068 against the R9 370X's 9,018, a delta of -87.3% from the older card's perspective.

Q: Which card wins in Geekbench OpenCL?

A: The AMD Radeon R9 370X wins with a score of 25,893 against the RX 7900 XT's 12,756, a 103% advantage.

Q: How does the R9 370X compare to its nearest rivals?

A: The R9 370X has an average benchmark score of 15,862, which is 0.1% above the AMD Radeon RX 7700, 1% above the AMD Radeon RX 9060, 1.2% below the AMD Radeon Pro W5500, and 1.7% below the NVIDIA GeForce RTX 3060 Ti.

Q: How does the RX 7900 XT compare to its nearest rivals?

A: The RX 7900 XT has an average benchmark score of 13,745, which is 0.5% below the AMD Radeon 660M and the NVIDIA RTX A2000 Mobile, 0.9% below the AMD Radeon RX 570X, and 1.5% above the AMD Radeon RX 9070 XT.

Q: What is the percentile ranking for each card?

A: The R9 370X ranks in the 58th percentile among all GPUs, while the RX 7900 XT ranks in the 55th percentile.

Q: What are the head-to-head win counts?

A: Each card wins one benchmark. The R9 370X wins Geekbench OpenCL, and the RX 7900 XT wins Geekbench Vulkan.

Specification Differences

The two cards differ across nearly every specification category. The R9 370X uses a 28 nm process node from TSMC, while the RX 7900 XT uses a 5 nm node from the same foundry. Transistor counts range from 2,800 million on the R9 370X to 57,700 million on the RX 7900 XT, with die sizes of 212 mm² and 529 mm² respectively. Transistor density scales from 13.2M per mm² to 109.1M per mm². Clock speeds show a similar gap: the R9 370X has a base clock of 980 MHz and a boost clock of 1030 MHz, while the RX 7900 XT has a base of 1387 MHz, a boost of 2394 MHz, and a game clock of 2025 MHz. Memory clocks are 1400 MHz with 5.6 Gbps effective on the older card versus 2500 MHz with 20 Gbps effective on the newer card.

Memory configuration differs substantially: the R9 370X has 2 GB of GDDR5 on a 256-bit bus with 179.2 GB/s bandwidth, while the RX 7900 XT has 20 GB of GDDR6 on a 320-bit bus with 800.0 GB/s bandwidth. Shading units jump from 1,280 to 5,376, texture units from 80 to 336, and ROPs from 32 to 192. The RX 7900 XT adds 84 ray tracing cores, a feature the R9 370X lacks entirely. Pixel rate goes from 32.96 GPixel/s to 459.6 GPixel/s, texture rate from 82.40 GTexel/s to 804.4 GTexel/s, and FP32 from 2.637 TFLOPS to 51.48 TFLOPS. The RX 7900 XT also lists FP16 at 103.0 TFLOPS (2:1), which the R9 370X does not specify. Power draw rises from 180 W to 300 W, power connectors from 2x 6-pin to 2x 8-pin, and suggested PSU from 450 W to 700 W. The bus interface advances from PCIe 3.0 x16 to PCIe 4.0 x16. Display outputs change from 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2 on the R9 370X to 1x HDMI 2.1a, 2x DisplayPort 2.1, and 1x USB Type-C on the RX 7900 XT. Dimensions grow from 221 mm length and 111 mm height to 276 mm length, 110 mm height, and 51 mm width. The launch MSRP for the R9 370X is 199 USD, and for the RX 7900 XT it is 899 USD. Release dates are 2015-08-26 for the older card and 2022-11-02 for the newer card.

Architecture Differences

The R9 370X is built on the GCN 1.0 architecture with the Trinidad chip, part of the Pirate Islands (R9 300) generation, with a predecessor in Volcanic Islands and a successor in Arctic Islands. The RX 7900 XT uses the RDNA 3.0 architecture with the Navi 31 chip, codenamed Plum Bonito, part of the Navi III (RX 7000) generation, with a predecessor in Navi II and a successor in Navi IV. The API support differs markedly: the R9 370X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170, while the RX 7900 XT supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The DirectX 12 Ultimate designation on the newer card indicates full feature support including ray tracing, which aligns with its 84 dedicated ray tracing cores. The R9 370X has no ray tracing cores or tensor cores, and its GCN 1.0 architecture predates the hardware-accelerated ray tracing features found in RDNA 3.0. The RX 7900 XT's 5 nm process node allows for a transistor density of 109.1M per mm², which is over eight times denser than the R9 370X's 13.2M per mm², enabling the massive increase in shading units, texture units, and ROPs within a larger die. Both cards are dual-slot, but the R9 370X is 55 mm shorter and 1 mm taller, while the RX 7900 XT adds 51 mm of width. Both are marked end-of-life in production status.

The Verdict

The data does not support a single overall winner; it supports a choice based on workload. For OpenCL compute tasks, the AMD Radeon R9 370X is the stronger performer, delivering a 103% higher score than the RX 7900 XT. This is a narrow use case, but for users running legacy OpenCL applications, the older card holds a genuine advantage. The R9 370X also sits in a respectable 58th percentile among all GPUs, and its average benchmark score of 15,862 places it within 1.7% of the NVIDIA GeForce RTX 3060 Ti, a much newer card. For Vulkan-based workloads, which include most modern games and many contemporary compute APIs, the RX 7900 XT is overwhelmingly superior, with a score of 71,068 that is 87.3% higher than the R9 370X's 9,018. The RX 7900 XT's 20 GB memory, 800.0 GB/s bandwidth, 84 ray tracing cores, and 51.48 TFLOPS FP32 make it the only reasonable choice for current-generation graphics. Its 55th percentile ranking and average score of 13,745 are lower than the R9 370X's, but this is an artifact of the benchmark mix, not a reflection of real-world capability. The RX 7900 XT wins in every meaningful graphics-related metric, while the R9 370X wins in one specific compute benchmark. Users who prioritize Vulkan performance should pick the RX 7900 XT without hesitation. Users whose software stacks rely on OpenCL and do not use Vulkan may find the R9 370X adequate, but they should also note that the RX 7900 XT's nearest rivals, such as the AMD Radeon RX 9070 XT, are only 1.5% lower in average score, suggesting that the newer card is part of a competitive field. The verdict is workload-dependent, but for the vast majority of modern use cases, the RX 7900 XT is the data-backed choice.

DETAILED SPECIFICATIONS

SPECIFICATION
R9 370X
RX 7900 XT
Core Specs
Shading Units
1,280
5,376 +320.0%
Shaders
1,280
5,376 +320.0%
TMUs
80
336 +320.0%
ROPs
32
192 +500.0%
Compute Units
24
84 +250.0%
Clocks
Base Clock
980 MHz
1387 MHz
Boost Clock
1030 MHz
2394 MHz
Game Clock
—
2025 MHz
Shader Clock
—
2025 MHz
Memory Clock
1400 MHz 5.6 Gbps effective
2500 MHz 20 Gbps effective
Memory
Memory Size
2 GB
20 GB
VRAM (MB)
2,048
20,480 +900.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
320 bit
Bandwidth
179.2 GB/s
800.0 GB/s
Cache
L1 Cache
16 KB (per CU)
256 KB per Array
L2 Cache
512 KB
6 MB
L3 Cache
—
80 MB
L0 Cache
—
64 KB per WGP
Performance
Pixel Rate
32.96 GPixel/s
459.6 GPixel/s
Texture Rate
82.40 GTexel/s
804.4 GTexel/s
FP32 (TFLOPS)
2.637 TFLOPS
51.48 TFLOPS
FP64 (TFLOPS)
164.8 GFLOPS (1:16)
1.609 TFLOPS (1:32)
FP16 (TFLOPS)
—
103.0 TFLOPS (2:1)
AI/RT
RT Cores
—
84
Matrix Cores
—
168
Power
TDP
180 W
300 W
TDP (W)
180
300 +66.7%
Suggested PSU
450 W
700 W
Power Connectors
2x 6-pin
2x 8-pin
Architecture
Architecture
GCN 1.0
RDNA 3.0
GPU Name
Trinidad
Navi 31
Codename
—
Plum Bonito
Generation
Pirate Islands (R9 300)
Navi III (RX 7000)
Process Size
28 nm
5 nm
Transistors
2,800 million
57,700 million
Die Size
212 mm²
529 mm²
Foundry
TSMC
TSMC
Density
13.2M / mm²
109.1M / mm²
AMD MCM
GCD Transistors
—
45,400 million
GCD Die Size
—
304.35 mm²
MCD Transistors
—
2,050 million x6
API Support
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1 (1.2)
2.2
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
221 mm 8.7 inches
276 mm 10.9 inches
Height
111 mm 4.4 inches
110 mm 4.3 inches
Outputs
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
1x HDMI 2.1a2x DisplayPort 2.11x USB Type-C
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Launch Price
199 USD
899 USD
Production
End-of-life
End-of-life
Predecessor
Volcanic Islands
Navi II
Successor
Arctic Islands
Navi IV
View Radeon R9 370X Details View Radeon RX 7900 XT Details