GPU Comparison

AMD
RADEON

AMD Radeon RX 6700M

CORE STATE Navi 22
VRAM 10 GB
CLOCK SPEED 2400 MHz
TDP 135 W
BUS WIDTH 160 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2021
VS
Intel
GPU

Arc B580

CORE STATE BMG-G21
VRAM 12 GB
CLOCK SPEED 2670 MHz
TDP 190 W
BUS WIDTH 192 bit
ARCHITECTURE Xe2-HPG
nm
PROCESS 5 nm
LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,845
3,068
geekbench_metal
91,911
N/A
geekbench_opencl
77,666
92,821
geekbench_vulkan
90,816
109,672
passmark_directx_10
92
76
passmark_directx_11
129
128
passmark_directx_12
65
76
passmark_directx_9
155
183
passmark_g2d
555
709
passmark_g3d
13,536
15,748
passmark_gpu_compute
5,191
7,729

Analysis: AMD Radeon RX 6700M vs Intel Arc B580

Head-to-Head Benchmarks

The benchmark data presents a clear overall picture, but the details matter for specific workloads. Out of ten head-to-head tests, the Intel Arc B580 claims eight wins, while the AMD Radeon RX 6700M takes two. The margin of victory varies dramatically between tests, which tells a more nuanced story than the raw win count.

The biggest single win for the Intel Arc B580 comes in the 3DMark Steel Nomad DX12 test. The Arc B580 scores 3068 against the RX 6700M’s 1845, a 39.9% advantage. This is a substantial gap, indicating that in modern DX12 workloads with heavy geometry and ray tracing effects, the Intel card has a commanding lead. This is the type of benchmark that predicts performance in current AAA titles, so the delta is significant for gamers.

Compute workloads also show a significant Intel advantage. In Passmark GPU Compute, the Arc B580 scores 7729 versus 5191 for the RX 6700M, a 32.8% difference. This suggests the Intel GPU has a more capable compute pipeline, which matters for GPGPU tasks, rendering, and some productivity applications. The Geekbench OpenCL result follows the same pattern, with the Arc B580 at 92821 and the RX 6700M at 77666, a 16.3% lead. The Vulkan result is similar: 109672 for the Arc B580 against 90816, a 17.2% edge. These API-agnostic compute and graphics tests consistently favor the Intel card.

In the Passmark G3D test, which is a broad measure of overall 3D graphics performance, the Arc B580 scores 15748 against 13536, a 14% advantage. This aligns with the 3DMark result and suggests that the Intel GPU is generally faster in modern 3D workloads. The 2D performance also favors Intel: the Arc B580 scores 709 in Passmark G2D versus 555 for the RX 6700M, a 21.7% lead. While 2D performance is rarely a bottleneck, it does indicate that the Intel card handles basic desktop compositing and 2D acceleration more efficiently.

Older DirectX versions show a mixed picture. In Passmark DirectX 9, the Arc B580 wins with 183 against 155, a 15.3% margin. In DirectX 12, the Arc B580 wins again with 76 against 65, a 14.5% edge. However, in DirectX 10, the AMD card takes a decisive win: 92 versus 76, a 21.1% advantage. In DirectX 11, the RX 6700M edges out the Arc B580 by a razor-thin margin: 129 versus 128, just 0.8% apart. These legacy API results are interesting because they show the AMD card is not universally slower, particularly in older DirectX versions where its driver optimization or hardware design retains an edge.

The AMD Radeon RX 6700M also maintains a higher average benchmark score overall. Its average across all recorded tests is 25633, while the Intel Arc B580 averages 23021. This is an important nuance: despite losing most head-to-head tests, the AMD card has a higher average because its wins in DirectX 10 and DirectX 11, combined with its scores in compute tests, balance out the larger losses in other areas. The RX 6700M sits at the 71st percentile of all GPUs, while the Arc B580 sits at the 68th percentile. The nearest rivals for the RX 6700M are the AMD Radeon Pro W5700 (0.4% lower), NVIDIA GeForce RTX 3080 Ti Mobile (0.4% lower), AMD FirePro D700 (0.8% lower), and AMD FirePro W7100 (0.9% lower). The Arc B580’s nearest rivals are the AMD Radeon RX 580 2048SP (0.2% lower), NVIDIA GeForce RTX 2080 (0.6% higher), NVIDIA GeForce RTX 3080 (0.7% lower), and NVIDIA P106-100 (1% lower).

The Verdict

The data suggests two different use cases with a clear performance split. The Intel Arc B580 is the stronger choice for modern gaming and compute-heavy workloads. Its 39.9% lead in 3DMark Steel Nomad DX12 is the most decisive metric in this comparison, and it is supported by consistent wins across Vulkan, OpenCL, DirectX 12, DirectX 9, and the overall Passmark G3D test. For anyone building a desktop system focused on current games or productivity tasks that leverage GPU compute, the Arc B580’s benchmark profile is more compelling.

The AMD Radeon RX 6700M is a mobile part, and its data reflects that positioning. It wins in DirectX 10 and DirectX 11, which are older APIs, and it holds a higher average benchmark score. It also carries the higher percentile ranking at 71 versus 68. However, its losses in the most modern and demanding tests are substantial. The 39.9% deficit in Steel Nomad and the 32.8% deficit in compute are not minor gaps; they represent real performance differences in current generation workloads.

The production status also matters. The RX 6700M is listed as end-of-life, while the Arc B580 is active. This means the Intel card is a current product with ongoing driver support, while the AMD part is a legacy mobile component. For a new build, the Arc B580 is the more future-proof option. The RX 6700M, released in May 2021, is now several generations behind, while the Arc B580, released in December 2024, is a current generation product.

The Arc B580 also offers more memory: 12 GB versus 10 GB, with a wider 192-bit bus and higher bandwidth at 456.0 GB/s versus 320.0 GB/s. This matters for texture-heavy games and higher resolutions, where memory capacity and bandwidth become limiting factors.

Where Each One Wins

The Intel Arc B580 wins in the categories that matter most for modern gaming and content creation. Its 3DMark Steel Nomad DX12 result is the strongest indicator of current generation gaming performance, and its 39.9% advantage is the largest margin in the entire comparison. The compute results (Passmark GPU Compute, Geekbench OpenCL) point to advantages in rendering, video encoding, and GPGPU workloads. The Vulkan win suggests strong performance in Vulkan-based games and applications. DirectX 12 and DirectX 9 wins round out a profile that is strong across both old and new API generations. The 2D performance win, while less critical, indicates a more responsive desktop experience.

The AMD Radeon RX 6700M wins in two specific areas: DirectX 10 and DirectX 11. These are older APIs, but they still matter for legacy games and some enterprise applications. The DirectX 10 win is particularly decisive at 21.1%, while the DirectX 11 win is marginal at 0.8%. The RX 6700M also maintains a higher average benchmark score (25633 versus 23021) and a higher percentile ranking (71 versus 68). This suggests that in a broad mix of workloads, including the older API tests where it wins, the AMD card holds up well. Its nearest rivals in the database are all within 0.9% of its average score, indicating it sits in a tightly competitive performance tier.

For users who primarily play older titles or run applications that rely on DirectX 10 or DirectX 11, the RX 6700M is the better choice. Its 21.1% lead in DirectX 10 is substantial and not something to dismiss. However, the Arc B580’s wins are in the APIs that dominate current software, so for forward-looking use cases, Intel is the pick.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 6700M has the higher average at 25633, compared to 23021 for the Intel Arc B580. The RX 6700M also ranks at the 71st percentile of all GPUs versus the 68th percentile for the Arc B580.

Q: How large is the performance gap in 3DMark Steel Nomad DX12?

A: The Intel Arc B580 scores 3068 against 1845 for the RX 6700M, a 39.9% advantage. This is the largest margin in any head-to-head test between the two.

Q: Which GPU wins in compute-heavy workloads?

A: The Intel Arc B580 wins in Passmark GPU Compute with a score of 7729 versus 5191, a 32.8% lead. It also wins in Geekbench OpenCL with 92821 versus 77666, a 16.3% advantage.

Q: Does the AMD Radeon RX 6700M win any benchmarks?

A: Yes, it wins in Passmark DirectX 10 (92 versus 76, a 21.1% lead) and Passmark DirectX 11 (129 versus 128, a 0.8% lead).

Q: What is the memory configuration difference?

A: The Intel Arc B580 has 12 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth. The AMD Radeon RX 6700M has 10 GB of GDDR6 on a 160-bit bus with 320.0 GB/s bandwidth.

Q: Which GPU is currently in production?

A: The Intel Arc B580 is listed as active, while the AMD Radeon RX 6700M is end-of-life. The Arc B580 was released on 2024-12-12, while the RX 6700M was released on 2021-05-30.

Architecture Differences

The two GPUs come from different architectural generations and design philosophies. The AMD Radeon RX 6700M uses the Navi 22 chip built on RDNA 2.0 architecture, part of the Navi Mobile generation (RX 6000M series). It is fabricated on a 7 nm process at TSMC, with 17,200 million transistors on a 335 mm² die. The transistor density is 51.3 million per mm².

The Intel Arc B580 uses the BMG-G21 chip built on Xe2-HPG architecture, part of the Battlemage generation (Arc 5). It is fabricated on a 5 nm process at TSMC, with 19,600 million transistors on a 272 mm² die. The transistor density is 72.1 million per mm². This is a denser, more modern process node, which explains how Intel packs more transistors into a smaller die.

The core configurations differ significantly. The RX 6700M has 2304 shading units, 144 TMUs, 64 ROPs, and 36 ray tracing cores. The Arc B580 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The Intel card has more shading units, TMUs, and ROPs, but fewer dedicated ray tracing cores. The pixel rate tells the story: the Arc B580 delivers 213.6 GPixel/s versus 153.6 GPixel/s for the RX 6700M. The texture rate is similarly higher on the Intel card at 427.2 GTexel/s versus 345.6 GTexel/s. FP32 throughput is 13.67 TFLOPS for the Arc B580 and 11.06 TFLOPS for the RX 6700M, while FP16 is 27.34 TFLOPS for Intel and 22.12 TFLOPS for AMD.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so feature-level API support is identical. Neither has dedicated tensor cores listed in the database. The RX 6700M’s predecessor is the Polaris Mobile series, while the Arc B580’s predecessor is the Alchemist series.

Specification Differences

The clock speeds differ noticeably. The RX 6700M has a base clock of 1489 MHz, a boost clock of 2400 MHz, and a game clock of 2300 MHz. The Arc B580 has a base and boost clock of 2670 MHz, with no separate game clock listed. The memory clock is 2000 MHz (16 Gbps effective) for the AMD card and 2375 MHz (19 Gbps effective) for the Intel card.

The power characteristics are a major differentiator. The RX 6700M has a TDP of 135 W, while the Arc B580 has a TDP of 190 W. The RX 6700M is an integrated graphics package (IGP) with no power connectors and no suggested PSU, reflecting its mobile design. The Arc B580 is a dual-slot desktop card with one 8-pin power connector and a suggested PSU of 450 W.

The bus interface also differs: the RX 6700M uses PCIe 4.0 x16, while the Arc B580 uses PCIe 4.0 x8. The display outputs are portable device dependent for the AMD card, while the Intel card offers 1x HDMI 2.1a and 3x DisplayPort 2.1. Physical dimensions are listed only for the Arc B580: 272 mm in length, 115 mm in height, and 45 mm in width. The RX 6700M has no listed dimensions, consistent with its mobile IGP form factor. The launch MSRP for the Arc B580 is 249 USD; the RX 6700M has no launch MSRP listed.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6700M
B580
Core Specs
Shading Units
2,304
2,560 +11.1%
Shaders
2,304
2,560 +11.1%
TMUs
144
160 +11.1%
ROPs
64
80 +25.0%
Compute Units
36
Execution Units
20
Clocks
Base Clock
1489 MHz
2670 MHz
Boost Clock
2400 MHz
2670 MHz
Game Clock
2300 MHz
Memory Clock
2000 MHz 16 Gbps effective
2375 MHz 19 Gbps effective
Memory
Memory Size
10 GB
12 GB
VRAM (MB)
10,240
12,288 +20.0%
Memory Type
GDDR6
GDDR6
Memory Bus
160 bit
192 bit
Bandwidth
320.0 GB/s
456.0 GB/s
Cache
L1 Cache
128 KB per Array
256 KB (per EU)
L2 Cache
3 MB
18 MB
L3 Cache
80 MB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
153.6 GPixel/s
213.6 GPixel/s
Texture Rate
345.6 GTexel/s
427.2 GTexel/s
FP32 (TFLOPS)
11.06 TFLOPS
13.67 TFLOPS
FP64 (TFLOPS)
691.2 GFLOPS (1:16)
854.4 GFLOPS (1:16)
FP16 (TFLOPS)
22.12 TFLOPS (2:1)
27.34 TFLOPS (2:1)
AI/RT
RT Cores
36
20 -44.4%
XMX Cores
160
Power
TDP
135 W
190 W
TDP (W)
135
190 +40.7%
Suggested PSU
450 W
Power Connectors
None
1x 8-pin
Architecture
Architecture
RDNA 2.0
Xe2-HPG
GPU Name
Navi 22
BMG-G21
Generation
Navi Mobile (RX 6000M)
Battlemage (Arc 5)
Process Size
7 nm
5 nm
Transistors
17,200 million
19,600 million
Die Size
335 mm²
272 mm²
Foundry
TSMC
TSMC
Density
51.3M / mm²
72.1M / 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
3.0
Shader Model
6.8
6.6
Physical
Slot Width
IGP
Dual-slot
Length
272 mm 10.7 inches
Height
115 mm 4.5 inches
Outputs
Portable Device Dependent
1x HDMI 2.1a3x DisplayPort 2.1
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x8
Other
Launch Price
249 USD
Production
End-of-life
Active
Predecessor
Polaris Mobile
Alchemist
View Radeon RX 6700M Details View Arc B580 Details