AMD Ryzen AI 9 HX 370 APU Benchmarks Leak: 12-Core 20% Faster In Multi-Threading, 40% Faster “Radeon 890M” GPU Performance Versus 8945HS

Hassan Mujtaba
AMD Ryzen AI 9 HX 370 APU Benchmarks Leak: 12-Core 20% Faster In Multi-Threading, 40% Faster "Radeon 880M" GPU Performance Versus 8945HS 1

The first benchmarks of AMD's Ryzen AI 9 HX 370 "Strix Point" APU have leaked and they show some big uplifts in both CPU & GPU performance with Zen 5 & RDNA 3.5 cores.

AMD Ryzen 9 AI HX 170 APU Leak Shows Up To 20% Faster Zen 5 CPU & Up To 40% Faster RDNA 3.5 GPU Versus Previous Flagship, The Ryzen 9 8945HS

Well that didn't take so long, AMD's first unofficial benchmarks of its upcoming Ryzen AI 300 APUs have started to leak out and they are very impressive in their first showcase. The chip in question is the Ryzen AI 9 HX 370 which is a very big and confusing name for some but we have to get used to it as both Intel and AMD will be going into the AI branding route in the future and we might see better naming schemes in the future, hopefully. So let's start with the specifications.

Related Story AMD Rolls Out FSR 4.1 For RX 7000 GPUs, Builds a Lightweight ML Model for RDNA 3.5 and RDNA 3 iGPUs

The AMD Ryzen AI 9 HX 370 APU is part of the Ryzen AI 300 "Strix Point" family and features a 12-core and 24-thread chip that features a four Zen 5 and eight Zen 5C configuration. This chip runs at up to 5.1 GHz boost clocks, offers 36 MB of cache (24 MB L3 + 12 MB L2), & the Radeon 890M iGPU with 16 compute units or 1024 cores. So versus the previous flagship, the Ryzen 9 8945HS, you are getting 50% more cores/threads, 33.3% more compute units, and 3.12x the NPU performance which is great gen-over-gen gains.

Coming to the Geekbench leak, it looks like we are looking at an early sample considering that while it matches the 2.0 GHz base clock, the log file shows a boost clock of around 4.2 GHz which is below its highest-rated clock rate of 5.1 GHz.

Image Source: Geekbench

AMD Ryzen AI 300 "Strix/Krackan" APUs:

CPU NameCores / ThreadsCore ConfigClock Speeds (Max)Cache (Total)AI CapabilitiesiGPUTDP
Ryzen AI 9 HX 37512/244x Zen 5 / 8x Zen 5C2.0 / 5.1 GHz36 MB / 24 MB L385 AI TOPs (55 TOPS NPU)Radeon 890M (16 CU @ 2.9 GHz)28W (cTDP 15-54W)
Ryzen AI 9 HX 37012/244x Zen 5 / 8x Zen 5C2.0 / 5.1 GHz36 MB / 24 MB L380 AI TOPs (50 TOPS NPU)Radeon 890M (16 CU @ 2.9 GHz)28W (cTDP 15-54W)
Ryzen AI 9 HX PRO 37012/244x Zen 5 / 8x Zen 5C2.0 / 5.1 GHz36 MB / 24 MB L380 AI TOPs (50 TOPS NPU)Radeon 890M (16 CU @ 2.9 GHz)28W (cTDP 15-54W)
Ryzen AI 7 36510/204x Zen 5 / 6x Zen 5C2.0 / 5.0 GHz30 MB / 20 MB L380 AI TOPs (50 TOPS NPU)Radeon 880M (12 CU @ 2.9 GHz)28W (cTDP 15-54W)
Ryzen AI 7 PRO 3608/163x Zen 5 / 5x Zen 5C2.0 / 5.0 GHz24 MB / 16 MB L372 AI TOPs (50 TOPS NPU)Radeon 880M (12 CU @ 2.9 GHz)28W (cTDP 15-54W)
Ryzen AI 7 3508/164x Zen 5 / 4x Zen 5C2.0 / 5.0 GHz24 MB / 16 MB L366 AI TOPs (50 TOPS NPU)Radeon 860M (8 CU @ 3.0 GHz)28W (cTDP 15-54W)
Ryzen AI 5 3406/123x Zen 5 / 3x Zen 5C2.0 / 4.8 GHz22 MB / 16 MB L359 AI TOPs (50 TOPS NPU)Radeon 840M (4 CU @ 2.9 GHz)28W (cTDP 15-54W)
Ryzen AI 5 3304/81x Zen 5 / 3x Zen 5C2.0 / 4.5 GHz12 MB / 8 MB L350 TOPS (NPU)Radeon 820M (2 CU @ 2.8 GHz)28W (cTDP 15-54W)

The APU is mentioned as the Ryzen AI 9 HX 170 with Radeon 880M iGPU but it should be pointed out that AMD made a very last-minute change and moved to a higher number. We have seen many Strix Point laptops on the Computex show floor that still haven't been updated with the new Ryzen AI 300 branding and use the older Ryzen AI 100 series numbering.

Ryzen 9 AI HX 370 APU Benchmark Leak (Geekbench 6.3.0) Result:

Ryzen 9 AI HX 370 APU Benchmark Leak (Geekbench 5.4.5) Result:

Geekbench 6.3.0 CPU Test (Higher is Better)
Single-Core
Multi-Core
0
4000
8000
12000
16000
20000
24000
0
4000
8000
12000
16000
20000
24000
Ryzen 7 7700X
2912
15273
Ryzen AI 9 HX 370
2544
14158
Core Ultra 9 185H
2246
12084
Ryzen 9 8945HS
2380
11775
Ryzen 9 7940HS
2367
11527

Coming to the numbers, the AMD Ryzen 9 AI HX 370 APU was tested in Geekbench 5, Geekbench 6, and the OpenCL tests. In Geekbench 5.4.5, the chip scored 1847 points in single-core and 14,316 points in multi-core tests. In the Geekbench 6.3.0 benchmark, the chip scored 2544 points in single-core and 14,158 points in multi-core tests. Finally, in the OpenCL test, the RDNA 3.5 (Radeon 890M) iGPU scored 41,995 points.

The CPU performance of the Zen 5 cores on the Strix Point APU looks great despite this being an early sample. We can expect the final performance to be much higher when the retail silicon ships with up to 5.1 GHz.

Geekbench OpenCL Test (Higher is Better)
Score
0
9000
18000
27000
36000
45000
54000
0
9000
18000
27000
36000
45000
54000
RTX 2050 (Laptop)
42323
Radeon 890M (Laptop)
41995
GTX 1650 Ti (Desktop)
41986
GTX 1650 (Desktop)
39685
Arc A380 (Desktop)
37136
Radeon 780M (Laptop)
30151
Arc A310 (Desktop)
29352
Arc 8 Xe (Laptop)
29158

Compared to the AMD Ryzen 9 8945HS APU which is the flagship of the Hawk Point lineup, the AMD Ryzen AI 9 HX 370 "Strix Point" APU scored a 7% lead in single-core, 20% lead in multi-core and a massive 40% gain in the graphics test which puts it on par with the RTX 2050 discrete GPU.

Image Source: Geekbench

The most important thing to keep in mind is that with its new Ryzen AI 300 series, AMD is eliminating a set TDP so there won't be an HX, HS, H, or U SKU. Instead, manufacturers will have to decide themselves what TDP target they want to use as these chips can scale from 15W and up to 54W so it's going to be harder to tell what actual TDP this benchmark ran at. The default TDP is 28W while the AMD Ryzen 9 8945HS has a default TDP of 45W. So if tested at default, then that's a great gain but if tested at a lower TDP say 15-20W, then this result is even more impressive.

AMD's Ryzen AI 300 CPUs will be available starting July 2024 through several OEM partners and we can expect better availability starting the holiday 2024 season or Q4.

News Sources: Benchleaks #1 , #2 , #3

Hassan Mujtaba Photo

About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.

Follow Wccftech on Google to get more of our news coverage in your feeds.

Button