AMD Radeon 780M vs Intel Arc B390 Comparison

AMD
RADEON

AMD Radeon 780M

CORE STATE Phoenix
VRAM System Shared
CLOCK SPEED 2900 MHz
TDP 15 W
BUS WIDTH System Shared
ARCHITECTURE RDNA 3.0
nm
PROCESS 4 nm
LAUNCH DATE 2024
VS
Intel
GPU

Arc B390

CORE STATE Panther Lake
VRAM System Shared
CLOCK SPEED 2500 MHz
TDP 80 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
480
1,482
geekbench_opencl
18,602
N/A
geekbench_vulkan
33,683
N/A

Analysis: AMD Radeon 780M vs Intel Arc B390

Where Each One Wins

The recorded benchmark data splits the two integrated GPUs into completely different performance tiers. The AMD Radeon 780M holds the overall average score advantage, with an average benchmark score of 17,588 across three tests, while the Intel Arc B390 has a single recorded benchmark result of 1,482. The 780M sits at the 61st percentile among all GPUs in the database, placing it near the middle of the entire graphics card population. The Arc B390, by contrast, sits at the 9th percentile, placing it in the lower decile of all recorded GPUs.

The single head-to-head comparison available, the 3DMark Steel Nomad DX12 test, goes entirely to the Intel part. In that test the Arc B390 scores 1,482 versus the 780M's 480, a delta of 67.6 percent in Intel's favor. That is the only direct matchup in the database, so any use-case analysis must account for the fact that the 780M's higher average comes from additional tests the Arc B390 does not have recorded.

For the AMD Radeon 780M, its wins are spread across compute-oriented workloads. The Geekbench OpenCL score of 18,602 and the Geekbench Vulkan score of 33,683 demonstrate strong general compute performance across both OpenCL and Vulkan APIs. These are the tests that push the 780M's average upward. The 780M also shows a favorable comparison against its nearest rivals in the database: it sits 0.2 percent above the AMD Radeon Pro 560, 0.5 percent above the AMD Radeon Pro 460, and only 0.3 percent below the NVIDIA GeForce RTX 4060 in average score. That places the 780M in the company of discrete desktop graphics cards from several generations ago, despite being an integrated processor graphics solution.

For the Intel Arc B390, its single recorded win is the 3DMark Steel Nomad DX12 test. That test is a modern DirectX 12 workload, and the Arc B390's score of 1,482 is roughly three times the 780M's 480. The Intel part's nearest rivals in the database are all low-end NVIDIA parts: the GeForce GT 520MX (1.3 percent behind), the GeForce 800M (1.5 percent behind), the GeForce GT 625 OEM (2.5 percent behind), and the GeForce GT 710 (2.7 percent behind). The Arc B390 leads all of those by small margins, indicating it clusters with very old, very low-end discrete GPUs in the database's scoring system.

What the data does not show is any test where the 780M wins a direct head-to-head. The database records zero wins for the AMD part and one win for the Intel part. The 780M's higher average score is a product of its broader benchmark coverage, not a direct victory over the Arc B390 in any shared test. This is an important distinction: the 780M is the better overall GPU by average score, but the only test where both parts appear together, Intel wins decisively.

The Verdict

The data points to a split verdict based on workload type. For general compute performance across OpenCL and Vulkan, the AMD Radeon 780M is the stronger part. Its Geekbench scores of 18,602 (OpenCL) and 33,683 (Vulkan) are far above the Arc B390's single 3DMark result, and its average benchmark score of 17,588 places it near the NVIDIA GeForce RTX 4060 in the database's ranking. The 780M's 61st percentile standing confirms it as a mid-range performer among all GPUs.

For the specific DirectX 12 workload in 3DMark Steel Nomad, the Intel Arc B390 is the clear winner. Its 1,482 score versus 480 for the 780M represents a 67.6 percent lead, which is a massive margin in a single test. The Arc B390's 9th percentile ranking, however, indicates that this single strong result does not translate to overall competitiveness. Its nearest rivals are all ancient low-end NVIDIA parts from a different era of graphics hardware.

The practical interpretation is that the 780M serves as a general-purpose integrated GPU with compute capabilities that rival older discrete cards, while the Arc B390 appears specialized for the specific DirectX 12 workload in which it excels. The 780M's additional benchmark coverage provides a more complete picture of its capabilities across multiple APIs. The Arc B390's limited data leaves its broader performance profile unknown, but its single strong result in Steel Nomad suggests it handles that particular modern rendering path efficiently.

Users who run OpenCL or Vulkan compute workloads should favor the 780M based on the recorded scores. Users who prioritize the specific DirectX 12 rendering path tested in Steel Nomad should favor the Arc B390. The database does not contain enough shared tests to declare an overall winner across all workloads. The 780M has the higher average and better percentile, but the Arc B390 has the only direct comparative victory.

Head-to-Head Benchmarks

The database contains exactly one head-to-head benchmark between the AMD Radeon 780M and the Intel Arc B390: the 3DMark Steel Nomad DX12 test. In this test, the Intel Arc B390 scores 1,482, while the AMD Radeon 780M scores 480. The delta percentage is 67.6 percent in favor of Intel. This means the Arc B390 delivers approximately three times the performance of the 780M in this specific DirectX 12 workload.

To put that margin in context, the Arc B390's nearest rival in the database, the NVIDIA GeForce GT 520MX, scores 1,463, which is 1.3 percent behind the Intel part. The GeForce 800M scores 1,460 (1.5 percent behind), and the GeForce GT 625 OEM scores 1,446 (2.5 percent behind). The Arc B390's Steel Nomad result places it just above these parts, which are all very old low-end mobile or OEM graphics solutions. The 780M's 480 score in the same test is not close to any of these figures; it is roughly one-third of the Arc B390's result.

The 780M's other recorded benchmarks, while not head-to-head comparisons, help explain its higher average score. In Geekbench OpenCL, the 780M scores 18,602. In Geekbench Vulkan, it scores 33,683. These are substantial scores that pull the 780M's average benchmark score to 17,588. The Arc B390 has no Geekbench results in the database, so its average benchmark score is simply its 3DMark result of 1,482.

The 780M's average of 17,588 places it 0.2 percent above the AMD Radeon Pro 560 (17,551) and 0.5 percent above the AMD Radeon Pro 460 (17,509). It sits 0.3 percent below the NVIDIA GeForce RTX 4060 (17,639) and 0.4 percent below the AMD Radeon HD 7790 (17,666). These narrow margins around the 780M's average indicate that the AMD part performs in a tight cluster with several discrete desktop GPUs from past generations.

The Arc B390's average of 1,482 places it 1.3 percent above the NVIDIA GeForce GT 520MX (1,463), 1.5 percent above the GeForce 800M (1,460), 2.5 percent above the GeForce GT 625 OEM (1,446), and 2.7 percent above the GeForce GT 710 (1,443). These are all very small margins, showing that the Arc B390 barely outpaces a set of GPUs that are more than a decade old in the database's scoring.

The head-to-head data shows a single, decisive Intel victory in a modern DirectX 12 test, but it does not demonstrate any comparable AMD victory because no other shared test exists. The 780M's overall standing in the database is higher, but that standing is built on tests the Arc B390 does not have recorded.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 780M has an average benchmark score of 17,588, while the Intel Arc B390 has an average benchmark score of 1,482.

Q: Which GPU won the 3DMark Steel Nomad DX12 test?

A: The Intel Arc B390 won, scoring 1,482 versus the AMD Radeon 780M's 480, a delta of 67.6 percent.

Q: How does the AMD Radeon 780M compare to the NVIDIA GeForce RTX 4060 in the database?

A: The 780M's average benchmark score of 17,588 is 0.3 percent below the RTX 4060's average score of 17,639.

Q: What are the Intel Arc B390's nearest rivals in the database?

A: The Arc B390's nearest rivals are the NVIDIA GeForce GT 520MX (1.3 percent behind), GeForce 800M (1.5 percent behind), GeForce GT 625 OEM (2.5 percent behind), and GeForce GT 710 (2.7 percent behind).

Q: What benchmarks does the AMD Radeon 780M have recorded?

A: The 780M has three recorded benchmarks: 3DMark Steel Nomad DX12 (480), Geekbench OpenCL (18,602), and Geekbench Vulkan (33,683).

Q: What is the Intel Arc B390's percentile ranking among all GPUs?

A: The Arc B390 sits at the 9th percentile among all GPUs in the database. The AMD Radeon 780M sits at the 61st percentile.

Architecture Differences

The AMD Radeon 780M uses the RDNA 3.0 architecture on the Phoenix chip, part of the Navi III IGP generation. It is built on a 4 nm process at TSMC, with 25,390 million transistors on a 178 mm² die, giving a transistor density of 142.6 million per square millimeter. The Intel Arc B390 uses the Xe3-LPG architecture on the Panther Lake chip, part of the Arc Graphics-M generation. It is built on a 3 nm process at Intel, with transistor count and die size listed as unknown in the database.

The 780M features 768 shading units, 48 texture mapping units, and 32 render output units. It has 12 ray tracing cores. The Arc B390 features 1,536 shading units, 48 texture mapping units, and 24 render output units. It also has 12 ray tracing cores. The Intel part has twice the shading units of the AMD part, but fewer ROPs (24 versus 32). Both parts have the same TMU count at 48.

Clock speeds differ significantly. The 780M has a base clock of 800 MHz and a boost clock of 2,900 MHz. The Arc B390 has a base clock of 300 MHz and a boost clock of 2,500 MHz. Despite the lower clocks, the Arc B390's higher shading unit count gives it a pixel rate of 60.00 GPixel/s, compared to the 780M's 92.80 GPixel/s. The texture rates are 120.0 GTexel/s for the Arc B390 and 139.2 GTexel/s for the 780M.

Compute throughput differs by precision. The 780M delivers 8.909 TFLOPS for both FP32 and FP16, with a 1:1 ratio. The Arc B390 delivers 7.680 TFLOPS for FP32 but 15.36 TFLOPS for FP16, with a 2:1 ratio. This means the Intel part has lower FP32 throughput but much higher FP16 throughput compared to the AMD part.

Power characteristics differ substantially. The 780M has a TDP of 15 W, while the Arc B390 has a TDP of 80 W. Both are integrated graphics processors with no power connectors and no dedicated slot width. The 780M uses a PCIe 4.0 x8 bus interface, while the Arc B390's bus interface is listed as IGP. Display outputs are motherboard dependent for the 780M and portable device dependent for the Arc B390.

Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The 780M was released on January 30, 2024, and the Arc B390 on January 26, 2026. The 780M lists its predecessor as Navi II IGP and its successor as Navi III IGP. The Arc B390 has no predecessor or successor listed in the database.

Specification Differences

The AMD Radeon 780M and Intel Arc B390 differ across nearly every recorded specification. The 780M uses the Phoenix chip with RDNA 3.0 architecture, while the Arc B390 uses the Panther Lake chip with Xe3-LPG architecture. The 780M is built on a 4 nm process at TSMC; the Arc B390 is built on a 3 nm process at Intel.

Transistor count and die size are known for the 780M (25,390 million transistors, 178 mm²) but unknown for the Arc B390. Transistor density is 142.6 million per square millimeter for the 780M and not listed for the Arc B390.

Clock speeds differ: the 780M has an 800 MHz base and 2,900 MHz boost, while the Arc B390 has a 300 MHz base and 2,500 MHz boost. Memory is system shared for both, with system dependent bandwidth for both.

The shading unit count is 768 for the 780M and 1,536 for the Arc B390. TMU count is identical at 48 for both. ROP count is 32 for the 780M and 24 for the Arc B390. Both have 12 ray tracing cores.

Pixel rate is 92.80 GPixel/s for the 780M and 60.00 GPixel/s for the Arc B390. Texture rate is 139.2 GTexel/s for the 780M and 120.0 GTexel/s for the Arc B390. FP32 throughput is 8.909 TFLOPS for the 780M and 7.680 TFLOPS for the Arc B390. FP16 throughput is 8.909 TFLOPS (1:1) for the 780M and 15.36 TFLOPS (2:1) for the Arc B390.

TDP is 15 W for the 780M and 80 W for the Arc B390. Both use IGP slot width and have no power connectors. The 780M uses a PCIe 4.0 x8 bus interface; the Arc B390's bus interface is listed as IGP. Display outputs are motherboard dependent for the 780M and portable device dependent for the Arc B390.

Release dates are January 30, 2024, for the 780M and January 26, 2026, for the Arc B390. Both support the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The 780M has a predecessor (Navi II IGP) and successor (Navi III IGP) listed; the Arc B390 has neither. Production status is Active for both.

DETAILED SPECIFICATIONS

SPECIFICATION
780M
B390
Core Specs
Shading Units
768
1,536 +100.0%
Shaders
768
1,536 +100.0%
TMUs
48
48 0.0%
ROPs
32
24 -25.0%
Compute Units
12
Execution Units
12
Clocks
Base Clock
800 MHz
300 MHz
Boost Clock
2900 MHz
2500 MHz
Memory Clock
System Shared
System Shared
Memory
Memory Size
System Shared
System Shared
Memory Type
System Shared
System Shared
Memory Bus
System Shared
System Shared
Bandwidth
System Dependent
System Dependent
Cache
L1 Cache
128 KB per Array
64 KB (per EU)
L2 Cache
2 MB
16 MB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
92.80 GPixel/s
60.00 GPixel/s
Texture Rate
139.2 GTexel/s
120.0 GTexel/s
FP32 (TFLOPS)
8.909 TFLOPS
7.680 TFLOPS
FP64 (TFLOPS)
556.8 GFLOPS (1:16)
960.0 GFLOPS (1:8)
FP16 (TFLOPS)
8.909 TFLOPS (1:1)
15.36 TFLOPS (2:1)
AI/RT
RT Cores
12
12 0.0%
XMX Cores
96
Power
TDP
15 W
80 W
TDP (W)
15
80 +433.3%
Power Connectors
None
None
Architecture
Architecture
RDNA 3.0
Xe3-LPG
GPU Name
Phoenix
Panther Lake
Generation
Navi III IGP (Phoenix)
Arc Graphics-M (Panther Lake)
Process Size
4 nm
3 nm
Transistors
25,390 million
unknown
Die Size
178 mm²
unknown
Foundry
TSMC
Intel
Density
142.6M / 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
6.9
Physical
Slot Width
IGP
IGP
Outputs
Motherboard Dependent
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
IGP
Other
Production
Active
Active
Predecessor
Navi II IGP
Successor
Navi III IGP
View Radeon 780M Details View Arc B390 Details