Intel Arc Graphics 24EU vs Intel Arc Pro B65 Comparison

Intel
GPU

Intel Arc Graphics 24EU

CORE STATE Arrow Lake-S
VRAM System Shared
CLOCK SPEED 2000 MHz
TDP 65 W
BUS WIDTH System Shared
ARCHITECTURE Xe-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2024
VS
Intel
GPU

Arc Pro B65

CORE STATE BMG-G21
VRAM 32 GB
CLOCK SPEED 2400 MHz
TDP 200 W
BUS WIDTH 256 bit
ARCHITECTURE Xe2-HPG
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
733
N/A

Analysis: Intel Arc Graphics 24EU vs Intel Arc Pro B65

Intel Arc Graphics 24EU and Intel Arc Pro B65 occupy separate corners of Intel’s graphics lineup, one designed for integration into desktop processors and the other for professional discrete workloads. The recorded data shows a substantial capability gap between them, driven by differences in architecture, memory configuration, and execution resources. This analysis compares the two strictly from database measurements.

Head-to-Head Benchmarks

The database contains a single benchmark entry for the Intel Arc Graphics 24EU: a 3DMark Steel Nomad DX12 score of 733. The Intel Arc Pro B65 has no recorded benchmark scores in the database, and no head-to-head benchmark entries exist for the pair. Consequently, direct score comparisons are limited to the 24EU’s position against its nearest rivals.

The 24EU’s 733 score places it at the 3rd percentile of all GPUs, indicating performance at the very low end of the database spectrum. Its nearest rival, the Intel Arc Graphics 32EU, also scores 733, showing a 0% difference. The Intel Arc Graphics 64EU matches that score as well, also at 0% delta. This suggests that within the Arc Graphics integrated family, increasing execution units from 24 to 64 does not translate into a measurable improvement in this particular DirectX 12 workload, at least according to the recorded data.

Against older discrete parts, the 24EU sits narrowly ahead of the AMD Radeon HD 6470M, which scores 723, a 1.4% advantage for the Intel part. The NVIDIA GeForce GT 415M scores 751, placing it 2.4% ahead of the 24EU. These deltas are small, keeping the 24EU in a tight performance cluster with these legacy mobile GPUs. The Arc Pro B65, with no benchmark score recorded, cannot be positioned against the 24EU or any other part using measured results. Its 50th percentile ranking across all GPUs, however, indicates a mid-pack standing, a stark contrast to the 24EU’s 3rd percentile placement.

Where Each One Wins

Based on the available data, the Intel Arc Graphics 24EU wins in scenarios where an integrated GPU with minimal power draw is sufficient. Its 65 W TDP, IGP slot width, and system-shared memory make it suitable for basic desktop tasks and light 2D acceleration. It matches the performance of the Arc Graphics 32EU and 64EU in the Steel Nomad test, meaning users with standard office workloads or media playback would not see a difference between these integrated options. The 24EU also edges out the AMD Radeon HD 6470M by 1.4%, confirming it can handle the same legacy workload class.

The Intel Arc Pro B65 wins in every compute-heavy and professional scenario by virtue of its specifications, even without a benchmark score. It delivers 2560 shading units against the 24EU’s 192, a 13.3x difference in raw shader count. Its pixel rate of 192.0 GPixel/s is 16x higher than the 24EU’s 12.00 GPixel/s, and its texture rate of 384.0 GTexel/s is 16x higher than 24.00 GTexel/s. FP32 throughput measures 12.29 TFLOPS versus 768.0 GFLOPS, a 16x advantage. The Pro B65 also has 20 ray tracing cores, which the 24EU lacks entirely. For 3D rendering, video encoding, CAD, or any workload that uses ray tracing, the Pro B65 is the only viable option between the two.

Memory bandwidth separates them further. The Pro B65 uses 32 GB of GDDR6 on a 256-bit bus, delivering 608.0 GB/s. The 24EU relies on system shared memory with bandwidth listed as system dependent. The Pro B65’s dedicated memory avoids contention with the CPU and provides predictable bandwidth for large datasets. The 24EU’s performance in memory-sensitive tasks will vary with the host system’s RAM configuration, a factor the database cannot quantify.

Architecture Differences

The two GPUs use different architectures and process nodes. The Intel Arc Graphics 24EU is built on Xe-LPG architecture, fabricated by TSMC on a 3 nm process. The chip is part of the Arrow Lake-S processor family, with a die size of 243 mm² and 17,800 million transistors. Transistor density measures 73.3M per mm². The Intel Arc Pro B65 uses Xe2-HPG architecture, fabricated by TSMC on a 5 nm process. Its chip, BMG-G21, has a die size of 272 mm² and 19,600 million transistors, with a density of 72.1M per mm². The newer 3 nm node gives the 24EU a slightly higher transistor density despite having fewer total transistors.

Execution resource counts diverge sharply. The 24EU has 192 shading units, 12 texture mapping units, and 6 render output units. The Pro B65 has 2560 shading units, 160 TMUs, and 80 ROPs. The Pro B65 also includes 20 ray tracing cores; the 24EU has none. Neither part lists tensor cores in the database. Clock speeds differ as well: the 24EU runs at a 300 MHz base and 2000 MHz boost, while the Pro B65 runs at a flat 2400 MHz for both base and boost. The Pro B65’s higher clock rate, combined with its much larger shader count, accounts for its massive throughput advantage.

Memory architecture reflects their different roles. The 24EU uses system shared memory with no dedicated VRAM, a typical configuration for integrated graphics. The Pro B65 has 32 GB of GDDR6 running at 2375 MHz (19 Gbps effective) on a 256-bit bus. The Pro B65’s bus interface is PCIe 5.0 x16, while the 24EU uses a Ring Bus connection, consistent with its integrated nature. Display outputs also differ: the 24EU’s outputs are motherboard dependent, while the Pro B65 provides 4x DisplayPort 2.1.

Power and physical specs reinforce the divide. The 24EU has a 65 W TDP and is listed as IGP slot width with no power connectors. The Pro B65 has a 200 W TDP, is dual-slot, requires a single 8-pin power connector, and suggests a 550 W power supply. The Pro B65’s release date is later in the database, with the 24EU appearing first.

FAQ

Q: Which GPU has better raw compute performance?

A: The Intel Arc Pro B65. Its FP32 throughput is 12.29 TFLOPS versus 768.0 GFLOPS for the Intel Arc Graphics 24EU, a 16x difference in favor of the Pro B65.

Q: Does the Intel Arc Graphics 24EU support ray tracing?

A: No. The database lists no ray tracing cores for the 24EU. The Intel Arc Pro B65 includes 20 ray tracing cores.

Q: How does the memory configuration affect these GPUs?

A: The 24EU uses system shared memory with bandwidth listed as system dependent, meaning performance varies with the host PC’s RAM. The Pro B65 has 32 GB of dedicated GDDR6 on a 256-bit bus with 608.0 GB/s of bandwidth, providing consistent and far higher memory throughput.

Q: What is the performance gap between the 24EU and its closest rivals?

A: In the 3DMark Steel Nomad DX12 test, the 24EU scores 733. The Intel Arc Graphics 32EU and 64EU both score 733, a 0% difference. The AMD Radeon HD 6470M scores 723 (1.4% slower), and the NVIDIA GeForce GT 415M scores 751 (2.4% faster).

Q: What power delivery does each require?

A: The 24EU is an integrated GPU with a 65 W TDP and no power connectors. The Pro B65 is a discrete card with a 200 W TDP, one 8-pin power connector, and a suggested power supply of 550 W.

Q: Which GPU supports newer display outputs?

A: The Intel Arc Pro B65 provides 4x DisplayPort 2.1 outputs. The Intel Arc Graphics 24EU’s display outputs are motherboard dependent, so the available ports depend on the specific motherboard design.

Specification Differences

The following fields differ between the two parts:

  • Architecture: Xe-LPG (24EU) vs Xe2-HPG (Pro B65)
  • Process node: 3 nm (24EU) vs 5 nm (Pro B65)
  • Transistors: 17,800 million (24EU) vs 19,600 million (Pro B65)
  • Die size: 243 mm² (24EU) vs 272 mm² (Pro B65)
  • Base clock: 300 MHz (24EU) vs 2400 MHz (Pro B65)
  • Boost clock: 2000 MHz (24EU) vs 2400 MHz (Pro B65)
  • Memory size: System Shared (24EU) vs 32 GB (Pro B65)
  • Memory type: System Shared (24EU) vs GDDR6 (Pro B65)
  • Memory bus width: System Shared (24EU) vs 256 bit (Pro B65)
  • Memory bandwidth: System Dependent (24EU) vs 608.0 GB/s (Pro B65)
  • Shading units: 192 (24EU) vs 2560 (Pro B65)
  • TMUs: 12 (24EU) vs 160 (Pro B65)
  • ROPs: 6 (24EU) vs 80 (Pro B65)
  • Ray tracing cores: None (24EU) vs 20 (Pro B65)
  • Pixel rate: 12.00 GPixel/s (24EU) vs 192.0 GPixel/s (Pro B65)
  • Texture rate: 24.00 GTexel/s (24EU) vs 384.0 GTexel/s (Pro B65)
  • FP32 performance: 768.0 GFLOPS (24EU) vs 12.29 TFLOPS (Pro B65)
  • FP16 performance: 1.536 TFLOPS (24EU) vs 24.58 TFLOPS (Pro B65)
  • TDP: 65 W (24EU) vs 200 W (Pro B65)
  • Slot width: IGP (24EU) vs Dual-slot (Pro B65)
  • Power connectors: None (24EU) vs 1x 8-pin (Pro B65)
  • Suggested PSU: None (24EU) vs 550 W (Pro B65)
  • Bus interface: Ring Bus (24EU) vs PCIe 5.0 x16 (Pro B65)
  • Display outputs: Motherboard Dependent (24EU) vs 4x DisplayPort 2.1 (Pro B65)
  • Release date: 2024-10-23 (24EU) vs 2026-03-31 (Pro B65)

The Verdict

The data draws a clear line. The Intel Arc Graphics 24EU is an integrated solution for systems where a discrete GPU is absent or unnecessary. Its 3rd percentile ranking and 733 Steel Nomad score place it at the entry level, competitive only with legacy mobile parts like the Radeon HD 6470M and GeForce GT 415M. It matches the 32EU and 64EU variants in the recorded test, so users with basic needs will find it sufficient. Its 65 W TDP and system shared memory make it a low-power option for office machines or media centers.

The Intel Arc Pro B65 is a professional discrete GPU aimed at workloads that demand throughput. Its 50th percentile standing, while not a top-tier rank, indicates mainstream capability. The 16x advantage in FP32, pixel rate, and texture rate over the 24EU, combined with 20 ray tracing cores and 608.0 GB/s of dedicated bandwidth, positions it for 3D rendering, compute tasks, and high-resolution display output. Its 200 W TDP and 550 W suggested PSU reflect the power needed for that performance.

The choice depends on the task. For integrated graphics with minimal power draw, the 24EU delivers baseline performance. For any workload that stresses the GPU, the Pro B65 is the only one of the two that can handle it, and its specifications confirm that role. The absence of benchmark scores for the Pro B65 means its exact performance relative to other discrete GPUs remains unmeasured in the database, but its resource counts and memory subsystem leave no doubt about its advantage over the 24EU.

DETAILED SPECIFICATIONS

SPECIFICATION
Graphics 24EU
Pro B65
Core Specs
Shading Units
192
2,560 +1233.3%
Shaders
192
2,560 +1233.3%
TMUs
12
160 +1233.3%
ROPs
6
80 +1233.3%
Execution Units
24
20 -16.7%
Clocks
Base Clock
300 MHz
2400 MHz
Boost Clock
2000 MHz
2400 MHz
Memory Clock
System Shared
2375 MHz 19 Gbps effective
Memory
Memory Size
System Shared
32 GB
VRAM (MB)
32,768
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
608.0 GB/s
Cache
L1 Cache
256 KB (per EU)
L2 Cache
10 MB
Performance
Pixel Rate
12.00 GPixel/s
192.0 GPixel/s
Texture Rate
24.00 GTexel/s
384.0 GTexel/s
FP32 (TFLOPS)
768.0 GFLOPS
12.29 TFLOPS
FP64 (TFLOPS)
768.0 GFLOPS (1:16)
FP16 (TFLOPS)
1.536 TFLOPS (2:1)
24.58 TFLOPS (2:1)
AI/RT
RT Cores
20
XMX Cores
160
Power
TDP
65 W
200 W
TDP (W)
65
200 +207.7%
Suggested PSU
550 W
Power Connectors
1x 8-pin
Architecture
Architecture
Xe-LPG
Xe2-HPG
GPU Name
Arrow Lake-S
BMG-G21
Generation
Arc Graphics (Arrow Lake)
Battlemage (Pro Series)
Process Size
3 nm
5 nm
Transistors
17,800 million
19,600 million
Die Size
243 mm²
272 mm²
Foundry
TSMC
TSMC
Density
73.3M / 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
3.0
3.0
Shader Model
6.8
6.6
Physical
Slot Width
IGP
Dual-slot
Outputs
Motherboard Dependent
4x DisplayPort 2.1
Bus Interface
Ring Bus
PCIe 5.0 x16
Other
Production
Active
Active
Predecessor
HD Graphics
View Arc Graphics 24EU Details View Arc Pro B65 Details