LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking.


LeelaChessZero 0.31.1

Backend: BLAS

OpenBenchmarking.org metrics for this test profile configuration based on 144 public results since 11 August 2024 with the latest data as of 20 January 2025.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component
Details
Percentile Rank
# Compatible Public Results
Nodes Per Second (Average)
Zen 5 [8 Cores / 16 Threads]
99th
5
572 +/- 3
Zen 5 [6 Cores / 12 Threads]
95th
4
384 +/- 13
Zen 5 [8 Cores / 16 Threads]
92nd
4
316 +/- 1
Zen 4 [32 Cores / 64 Threads]
89th
3
311 +/- 3
Zen 4 [16 Cores / 32 Threads]
79th
4
239 +/- 12
Zen 5 [16 Cores / 32 Threads]
79th
18
237 +/- 16
Mid-Tier
75th
< 226
Raptor Lake [24 Cores / 32 Threads]
71st
4
201 +/- 5
Zen 4 [16 Cores / 32 Threads]
65th
11
174 +/- 3
Zen 3 [8 Cores / 16 Threads]
56th
4
129 +/- 2
Zen 4 [8 Cores / 16 Threads]
56th
4
129 +/- 5
Zen 3 [32 Cores / 64 Threads]
53rd
4
123 +/- 3
Median
50th
119
Zen 2 [8 Cores / 16 Threads]
49th
4
112 +/- 1
Zen 2 [32 Cores / 64 Threads]
45th
4
107 +/- 1
Cascade Lake [18 Cores / 36 Threads]
43rd
3
95 +/- 5
Zen 4 [8 Cores / 16 Threads]
40th
4
90 +/- 3
Alder Lake [10 Cores / 16 Threads]
37th
3
82 +/- 1
Tiger Lake [4 Cores / 8 Threads]
28th
4
55 +/- 2
Low-Tier
25th
< 52
Zen 3 [8 Cores / 16 Threads]
24th
4
39
Cascade Lake [16 Cores / 32 Threads]
22nd
4
37 +/- 1
Zen 3 [8 Cores / 16 Threads]
18th
3
30 +/- 1
Zen 3 [8 Cores / 16 Threads]
17th
6
29
Meteor Lake [16 Cores / 22 Threads]
11th
3
26 +/- 1
Ice Lake [4 Cores / 8 Threads]
8th
3
21 +/- 1