As Intel's Alder Lake platform falls into the hands of more and more developers, it is inevitable that specifications of engineering samples and preliminary benchmark results get revealed to broader audiences. On Saturday someone added benchmark results of a 14-core Alder Lake processor to Primate Labs' Geekbench 5 database.
Intel's Alder Lake is a hybrid processor packing high-performance (HP) Golden Cove cores, energy-efficient (EE) Gracemont cores, Intel Xe graphics as well as supporting a PCIe 5.0 interface and four types of memory (DDR4, DDR4, LPDDR4, LPDDR5). Alder Lake will be Intel's first hybrid CPU for mainstream PCs, so enthusiasts are eager to learn about its performance and whether it can finally beat the best CPUs, including AMD's Ryzen processors, in multi-thread workloads, so all performance leaks immediately attract a lot of attention.
This time around, an Intel partner currently working with the company's AlderLake-P DDR5 RVP (reference validation platform) based on a 14-core Alder Lake processor featuring a 1.40 GHz base clock (and a 27.1 GHz boost clock, which is clearly wrong) and a 24MB cache has accidentally posted Geekbench 5 results of the CPU. The Alder Lake RVP chip scored 1287 single-thread points and 8950 multi-thread points.
| CPU | Single-Core | Multi-Core | Cores/Threads, uArch | Cache | Clocks | TDP | Link |
|---|---|---|---|---|---|---|---|
| AMD Ryzen 9 5980HS | 1,540 | 8,225 | 8C/16T, Zen 3 | 16MB | 3.30 ~ 4.53 GHz | 35W | https://browser.geekbench.com/v5/cpu/6027200 |
| AMD Ryzen 9 4900H | 1,230 | 7,125 | 8C/16T, Zen 2 | 8MB | 3.30 ~ 4.44 GHz | 35~54W | https://browser.geekbench.com/v5/cpu/6028856 |
| Intel Alder Lake-P | 1,287 | 8950 | 14C/20T: 8HP + 6EE | 24MB | 1.40 GHz ~ 27.1 GHz (?) | ? | https://browser.geekbench.com/v5/cpu/8014264 |
| Intel Core i9-11900 | 1,715 | 10,565 | 8C/16T, Cedar Cove | 16MB | 2.50 ~ 5.20 GHz | 65W | https://browser.geekbench.com/v5/cpu/7485886 |
| Intel Core i9-11950H | 1,365 | 6,266 | 8C/16T, Willow Cove | 24MB | 2.60 ~ 4.90 GHz | ? | https://browser.geekbench.com/v5/cpu/7670672 |
| Intel Core i9-10885H | 1,335 | 7,900 | 8C/16T, Skylake | 16MB | 2.40 ~ 5.08 GHz | 45W | https://browser.geekbench.com/v5/cpu/6006773 |
| Intel Core i7-1185G7 | 1,550 | 5,600 | 4C/8T, Willow Cove | 12MB | 3.0 ~ 4.80 GHz | 28W | https://browser.geekbench.com/v5/cpu/5644005 |
| Apple M1 | 1,710 | 7,660 | 4C Firestorm + 4C Icestorm | 12MB + 4MB | 3.20 GHz | 20~24W | https://browser.geekbench.com/v5/cpu/6038094 |
Since we do not know the actual boost frequency of the processor, it is hard to make any conclusions or even guesses about the real-world performance potential of Intel's upcoming platform. Meanwhile, considering a low base frequency and the power plan of the board set to 'balanced', we are probably dealing with a notebook platform rather than with a no-compromise enthusiast-grade system.
We do observe that single-thread Geekbench 5 performance of a 14-core Alder Lake reference design board working at an unknown CPU clock is comparable to that of AMD's Ryzen 9 4900H (Zen 2, 3.30 GHz ~ 4.44 GHz). Yet, it is significantly behind results of Willow Cove-based Tiger Lake parts. Meanwhile, the same ADL-P RVP significantly outperforms AMD's Ryzen 9 5980HS (eight Zen 3 cores at 3.30 ~ 4.53 GHz) in multi-thread Geekbench 5 workloads.
Overall, the Geekbench 5 results obtained on an Intel's AlderLake-P DDR5 RVP board look rather good, especially keeping in mind that production Alder Lake platform is expected to hit the market late this year, several months from now. Still, such leaked results should always be taken with a huge grain of salt.
