Apple M3 Benchmark, Test and specs

Last updated:
The Apple M3 has 8 cores with 8 threads and is based on the 3. gen of the Apple M series series. The processor was released in Q4/2023. The Apple M3 scores 2,150 points in the Geekbench 5 single-core benchmark. In the Geekbench 5 multi-core benchmark, the result is 10,450 points.
Apple M3

CPU lineage

The segment in which we have classified the Apple M3. Here you can see if it is a desktop processor or a mobile processor or which processor may be the successor of the Apple M3.

Name: Apple M3
Family: Apple M series (23)
CPU group: Apple M3 (6)
Architecture: M3
Segment: Mobile
Generation: 3
Predecessor: Apple M2
Successor: --

CPU Cores and Base Frequency

The Apple M3 has 8 CPU cores and can calculate 8 threads in parallel. The clock frequency of the Apple M3 is 0.70 GHz (4.06 GHz). The number of CPU cores greatly affects the speed of the processor and is an important performance indicator.

CPU Cores / Threads: 8 / 8
Core architecture: hybrid (big.LITTLE)
A-Core: 4x P-Core
B-Core: 4x E-Core
Hyperthreading / SMT: No
Overclocking: No
A-Core Frequency: 0.70 GHz (4.06 GHz)
B-Core Frequency: 0.74 GHz (2.75 GHz)

Artificial Intelligence and Machine Learning

Processors with the support of artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. Algorithms for ML improve their performance the more data they have collected via software. ML tasks can be processed up to 10,000 times faster than with a classic processor.

AI hardware: Apple Neural Engine
AI specifications: 16 Neural cores @ 35 TOPS

Internal Graphics

The Apple M3 has integrated graphics, called iGPU for short. Specifically, the Apple M3 uses the Apple M3 (10 Core), which has 1280 texture shaders and 160 execution units. The iGPU uses the system's main memory as graphics memory and sits on the processor's die.

GPU name: Apple M3 (10 Core)
GPU frequency: 0.39 GHz
GPU (Turbo): 1.40 GHz
Compute units: 160
Shader: 1280
Hardware Raytracing: Yes
Release date: Q4/2023
Max. displays: 2
Generation: 3
Direct X: --
Technology: 3 nm
Max. GPU Memory: 24 GB
Frame Generation: No

Hardware codec support

A photo or video codec that is accelerated in hardware can greatly accelerate the working speed of a processor and extend the battery life of notebooks or smartphones when playing videos.

h265 / HEVC (8 bit): Decode / Encode
h265 / HEVC (10 bit): Decode / Encode
h264: Decode / Encode
VP8: Decode
VP9: Decode / Encode
AV1: Decode
AVC: Decode
VC-1: Decode
JPEG: Decode / Encode

Memory & PCIe

The processor can use up to 24 GB memory in 2 (Dual Channel) memory channels. The maximum memory bandwidth is 102.4 GB/s. The memory type as well as the amount of memory can greatly affect the speed of the system.

Memory type: Memory bandwidth:
LPDDR5-6400
102.4 GB/s
Max. Memory: 24 GB
Memory channels: 2 (Dual Channel)
ECC: No
PCIe: 4.0
PCIe Bandwidth: --

Thermal Management

The thermal design power (TDP for short) of the processor is 22 W. The TDP specifies the necessary cooling solution that is required to cool the processor sufficiently. The TDP usually gives a rough idea of the actual power consumption of the CPU.

TDP (PL1 / PBP): 22 W
TDP (PL2): --
TDP up: --
TDP down: 15 W
Tjunction max.: 100 °C

Technical details

The Apple M3 is made in 3 nm. The smaller the manufacturing process of a CPU, the more modern and energy-efficient it is. Overall, the processor has 20.00 MB cache. A large cache can greatly speed up the processor's speed in some cases such as games.

Technology: 3 nm
Chip design: Chiplet
Socket: --
L2-Cache: 20.00 MB
L3-Cache: --
AES-NI: Yes
Operating systems: macOS, iPadOS
Virtualization: Apple Virtualization Framework
Instruction set (ISA): Armv8-A (64 bit)
ISA extensions: Rosetta 2 x86-Emulation
Release date: Q4/2023
Release price: --
Part Number: --
Documents: --

Benchmark results

Verified Benchmark results
The benchmark results for the Apple M3 have been carefully checked by us. We only publish benchmark results that have been created by us or that have been submitted by a visitor and then checked by a team member. All results are based on and fullfill our benchmark guidelines.

Screenshots:

Cinebench 2024 (Single-Core)

The Cinebench 2024 benchmark is based on the Redshift rendering engine, which is also used in Maxon's 3D program Cinema 4D. The benchmark runs are each 10 minutes long to test whether the processor is limited by its heat generation.
Apple M3 Pro (11-CPU 14-GPU) Apple M3 Pro (11-CPU 14-GPU)
11C 11T @ 4.06 GHz
139
Intel Core i9-14900K Intel Core i9-14900K
24C 32T @ 6.00 GHz
139
Intel Core i9-14900KF Intel Core i9-14900KF
24C 32T @ 6.00 GHz
139
Apple M3 Apple M3
8C 8T @ 4.06 GHz
137
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
137
Intel Core i9-13900KS Intel Core i9-13900KS
24C 32T @ 6.00 GHz
134
Qualcomm Snapdragon X Elite Qualcomm Snapdragon X Elite
12C 12T @ 4.25 GHzNot verified
132

Cinebench 2024 (Multi-Core)

The Multi-Core test of the Cinebench 2024 benchmark uses all cpu cores to render using the Redshift rendering engine, which is also used in Maxons Cinema 4D. The benchmark run is 10 minutes long to test whether the processor is limited by its heat generation.
Intel Xeon E5-2680 v4 Intel Xeon E5-2680 v4
14C 28T @ 3.30 GHz
695
Intel Core i9-9900KS Intel Core i9-9900KS
8C 16T @ 5.00 GHz
687
AMD Ryzen 7 5800H AMD Ryzen 7 5800H
8C 16T @ 4.40 GHz
665
Apple M3 Apple M3
8C 8T @ 4.06 GHz
659
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
659
Intel Core i5-12500 Intel Core i5-12500
6C 12T @ 4.60 GHz
659
AMD Ryzen 5 5600 AMD Ryzen 5 5600
6C 12T @ 4.40 GHz
657

Cinebench R23 (Single-Core)

Cinebench R23 is the successor of Cinebench R20 and is also based on the Cinema 4 Suite. Cinema 4 is a worldwide used software to create 3D forms. The single-core test only uses one CPU core, the amount of cores or hyperthreading ability doesn't count.
AMD Ryzen 5 7600X AMD Ryzen 5 7600X
6C 12T @ 5.30 GHz
1976
Apple M3 Max (14-CPU 30-GPU) Apple M3 Max (14-CPU 30-GPU)
14C 14T @ 4.06 GHz
1968
Apple M3 Max (16-CPU 40-GPU) Apple M3 Max (16-CPU 40-GPU)
16C 16T @ 4.06 GHz
1968
Apple M3 Apple M3
8C 8T @ 4.06 GHz
1965
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
1965
AMD Ryzen 9 PRO 7945 AMD Ryzen 9 PRO 7945
12C 24T @ 5.40 GHz
1964
AMD Ryzen 9 7900 AMD Ryzen 9 7900
12C 24T @ 5.40 GHz
1964

Cinebench R23 (Multi-Core)

Cinebench R23 is the successor of Cinebench R20 and is also based on the Cinema 4 Suite. Cinema 4 is a worldwide used software to create 3D forms. The multi-core test involves all CPU cores and taks a big advantage of hyperthreading.
Intel Core i5-10600K Intel Core i5-10600K
6C 12T @ 4.50 GHz
10489
Intel Core i5-10600KF Intel Core i5-10600KF
6C 12T @ 4.50 GHz
10489
AMD Ryzen 7 5800HS AMD Ryzen 7 5800HS
8C 16T @ 3.50 GHz
10472
Apple M3 Apple M3
8C 8T @ 4.06 GHz
10437
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
10437
Intel Core i7-1360P Intel Core i7-1360P
12C 16T @ 2.20 GHz
10422
AMD Ryzen 7 6800U AMD Ryzen 7 6800U
8C 16T @ 3.40 GHz
10412

Geekbench 5, 64bit (Single-Core)

Geekbench 5 is a cross plattform benchmark that heavily uses the systems memory. A fast memory will push the result a lot. The single-core test only uses one CPU core, the amount of cores or hyperthreading ability doesn't count.
AMD Ryzen 7 7700 AMD Ryzen 7 7700
8C 16T @ 5.30 GHz
2177
AMD Ryzen Threadripper 7970X AMD Ryzen Threadripper 7970X
32C 64T @ 5.30 GHz
2166
Intel Core i9-14900HX Intel Core i9-14900HX
24C 32T @ 5.80 GHz
2161
Apple M3 Apple M3
8C 8T @ 4.06 GHz
2150
Apple M3 Max (16-CPU 40-GPU) Apple M3 Max (16-CPU 40-GPU)
16C 16T @ 4.06 GHz
2150
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
2150
Apple M3 Max (14-CPU 30-GPU) Apple M3 Max (14-CPU 30-GPU)
14C 14T @ 4.06 GHz
2150

Geekbench 5, 64bit (Multi-Core)

Geekbench 5 is a cross plattform benchmark that heavily uses the systems memory. A fast memory will push the result a lot. The multi-core test involves all CPU cores and taks a big advantage of hyperthreading.
Intel Xeon W-1370P Intel Xeon W-1370P
8C 16T @ 4.40 GHz
10467
Intel Core i9-9820X Intel Core i9-9820X
10C 20T @ 4.00 GHz
10465
Intel Xeon E5-2680 v4 Intel Xeon E5-2680 v4
14C 28T @ 2.70 GHz
10459
Apple M3 Apple M3
8C 8T @ 4.06 GHz
10450
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
10450
Intel Core i5-13500H Intel Core i5-13500H
12C 16T @ 4.40 GHz
10420
Intel Core i5-13505H Intel Core i5-13505H
12C 16T @ 4.40 GHz
10420

Geekbench 6 (Single-Core)

Geekbench 6 is a benchmark for modern computers, notebooks and smartphones. What is new is an optimized utilization of newer CPU architectures, e.g. based on the big.LITTLE concept and combining CPU cores of different sizes. The single-core benchmark only evaluates the performance of the fastest CPU core, the number of CPU cores in a processor is irrelevant here.
Apple M3 Max (14-CPU 30-GPU) Apple M3 Max (14-CPU 30-GPU)
14C 14T @ 4.06 GHz
3125
Apple M3 Max (16-CPU 40-GPU) Apple M3 Max (16-CPU 40-GPU)
16C 16T @ 4.06 GHz
3125
Apple M3 Pro (11-CPU 14-GPU) Apple M3 Pro (11-CPU 14-GPU)
11C 11T @ 4.06 GHz
3125
Apple M3 Apple M3
8C 8T @ 4.06 GHz
3076
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
3076
Intel Core i9-13900KS Intel Core i9-13900KS
24C 32T @ 6.00 GHz
2997
AMD Ryzen 9 7950X AMD Ryzen 9 7950X
16C 32T @ 5.70 GHz
2974

Geekbench 6 (Multi-Core)

Geekbench 6 is a benchmark for modern computers, notebooks and smartphones. What is new is an optimized utilization of newer CPU architectures, e.g. based on the big.LITTLE concept and combining CPU cores of different sizes. The multi-core benchmark evaluates the performance of all of the processor's CPU cores. Virtual thread improvements such as AMD SMT or Intel's Hyper-Threading have a positive impact on the benchmark result.
Intel Core i9-12900H Intel Core i9-12900H
14C 20T @ 3.80 GHz
11894
Intel Core i9-12900HK Intel Core i9-12900HK
14C 20T @ 3.80 GHz
11894
Intel Core i5-13450HX Intel Core i5-13450HX
10C 16T @ 4.00 GHz
11891
Apple M3 Apple M3
8C 8T @ 4.06 GHz
11863
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 4.06 GHz
11863
Intel Core i9-10980XE Intel Core i9-10980XE
18C 36T @ 4.30 GHz
11836
AMD Ryzen 9 3950X AMD Ryzen 9 3950X
16C 32T @ 4.00 GHz
11830

iGPU - FP32 Performance (Single-precision GFLOPS)

The theoretical computing performance of the internal graphics unit of the processor with simple accuracy (32 bit) in GFLOPS. GFLOPS indicates how many billion floating point operations the iGPU can perform per second.
AMD Ryzen 9 6900HX AMD Ryzen 9 6900HX
AMD Radeon 680M @ 2.40 GHz
3686
Intel Core i7-8709G Intel Core i7-8709G
AMD Radeon RX Vega M GH @ 1.19 GHz
3656
Intel Core i7-8809G Intel Core i7-8809G
AMD Radeon RX Vega M GH @ 1.19 GHz
3656
Apple M3 Apple M3
Apple M3 (10 Core) @ 1.40 GHz
3550
Apple M2 Apple M2
Apple M2 (10 Core) @ 1.40 GHz
3550
AMD Ryzen 7 7735HS AMD Ryzen 7 7735HS
AMD Radeon 680M @ 2.20 GHz
3379
AMD Ryzen 7 7736U AMD Ryzen 7 7736U
AMD Radeon 680M @ 2.20 GHz
3379

CPU performance per watt (efficiency)

Efficiency of the processor under full load in the Cinebench R23 (multi-core) benchmark. The benchmark result is divided by the average energy required (CPU package power in watts). The higher the value, the more efficient the CPU is under full load.
Apple M3 Apple M3
10,437 CB R23 MC @ 22 W
474
Apple M3 (8-GPU) Apple M3 (8-GPU)
10,437 CB R23 MC @ 22 W
474
AMD Ryzen 7 8840U AMD Ryzen 7 8840U
13,450 CB R23 MC @ 30 W
448
AMD Ryzen 7 7840U AMD Ryzen 7 7840U
13,450 CB R23 MC @ 30 W
448
AMD Ryzen 5 8640U AMD Ryzen 5 8640U
10,675 CB R23 MC @ 24 W
445
AMD Ryzen 5 7640U AMD Ryzen 5 7640U
10,675 CB R23 MC @ 24 W
445
Apple M1 Apple M1
7,759 CB R23 MC @ 18 W
431

Performance for Artificial Intelligence (AI) and Machine Learning (ML)

Processors with the support of artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. The performance is given in the number (trillions) of arithmetic operations per second (TOPS).
Qualcomm Snapdragon X Elite Qualcomm Snapdragon X Elite
12C 12T @ 3.80 GHzNot verified
45
Samsung Exynos 2400 Samsung Exynos 2400
10C 10T @ 3.20 GHz
44
Apple M3 Apple M3
8C 8T @ 0.70 GHz
35
Apple M3 Max (16-CPU 40-GPU) Apple M3 Max (16-CPU 40-GPU)
16C 16T @ 0.70 GHz
35
Apple M3 Pro (12-CPU 18-GPU) Apple M3 Pro (12-CPU 18-GPU)
12C 12T @ 0.70 GHz
35
Apple M3 (8-GPU) Apple M3 (8-GPU)
8C 8T @ 0.70 GHz
35
Apple M3 Max (14-CPU 30-GPU) Apple M3 Max (14-CPU 30-GPU)
14C 14T @ 0.70 GHz
35

Benchmarks


Description of the processor

With the Apple M3, the manufacturer has introduced its first third-generation processor. The SoC contains a CPU part that has the same features as the Apple M1 or Apple M2 with 4 P cores and 4 E cores. The cores now clock a little higher at up to 4.06 GHz. This also results in slightly higher CPU performance compared to its predecessors.

The jump in performance compared to the Apple M2 is between 10 and 20 percent and mainly comes from the increased clock frequency. However, minor optimizations have further increased the efficiency of the processor. In our Cinebench R23 efficiency benchmark, which compares the multi-core performance achieved with the energy consumption under full load, the Apple M3 currently takes first place.

The increased efficiency is certainly also due to TSMCs new manufacturing process. TSMC now manufactures the Apple M3 in 3 nm, while the Apple M2 was still manufactured in 5 nm. Due to the increased performance, the TDP of the Apple M3 was increased to 22 watts, while its predecessor still had to make do with 20 watts.

Apple has not touched the memory connection compared to the Apple M2. Up to 24 GB of LPDDR5-6400 memory can still be addressed. The maximum bandwidth is 102.4 GB/s. What is new is the management of shared memory. This is now divided more intelligently between the CPU and the internal graphics (iGPU). Apple calls this “Dynamic Cache”. The new memory management should give the Apple M3 significantly better graphics performance.

And although the pure FP32 raw graphics performance of 3.55 TFLOPS has not changed compared to the Apple M2, the Apple M3 achieves really better frame rates in practice. The AI area of the SoC, which is now twice as large at 35 TOPS, also contributes to this. At the same time, the internal graphics now support hardware decoding of the AV1 code and enable ray tracing in hardware.



Popular comparisons

1. Apple M3 Intel Core i9-13900H Apple M3 vs Intel Core i9-13900H
2. Apple M1 Apple M3 Apple M1 vs Apple M3
3. Apple M3 Apple M2 (8-GPU) Apple M3 vs Apple M2 (8-GPU)
4. Apple M3 Apple M2 Pro (10-CPU 16-GPU) Apple M3 vs Apple M2 Pro (10-CPU 16-GPU)
5. Apple M3 Apple M1 Pro (8-CPU) Apple M3 vs Apple M1 Pro (8-CPU)
6. Apple M2 Apple M3 Apple M2 vs Apple M3
7. Apple M3 Intel Core i9-14900K Apple M3 vs Intel Core i9-14900K
8. Apple M3 Intel Core i9-13900K Apple M3 vs Intel Core i9-13900K
9. Apple M3 Intel Core i7-12850HX Apple M3 vs Intel Core i7-12850HX
10. Apple M1 Max (32-GPU) Apple M3 Apple M1 Max (32-GPU) vs Apple M3


back to index