AI hardware re-ranked by inference-category score — the throughput profile that matters for serving already-trained models rather than training or raw compute benchmarks. GT and the other two category scores stay visible for context. Results: 26Q3.
| # | Device Accelerator / GPU | GT Global Score | Training Category | Inference Category | Compute Category | Platform OS |
|---|---|---|---|---|---|---|
| 1 |
1306.35
|
1089.67
|
2224.55
|
611.10
|
Native Linux | |
| 2 |
1277.42
|
1080.48
|
2105.93
|
624.58
|
Native Linux | |
| 3 |
1044.99
|
811.98
|
1914.61
|
480.83
|
Native Linux | |
| 4 |
939.45
|
709.35
|
1678.11
|
487.13
|
Native Linux | |
| 5 |
986.72
|
727.23
|
1304.04
|
1023.28
|
Native Linux | |
| 6 |
718.86
|
587.80
|
1201.04
|
366.56
|
Native Linux | |
| 7 |
692.67
|
588.50
|
1123.94
|
347.75
|
Native Linux | |
| 8 |
597.49
|
515.26
|
985.84
|
279.64
|
Native Linux | |
| 9 |
440.29
|
415.55
|
660.97
|
210.04
|
Native Linux | |
| 10 |
450.05
|
335.94
|
659.37
|
367.89
|
Native Linux | |
| 11 |
403.38
|
387.30
|
584.07
|
201.12
|
Native Linux | |
| 12 |
395.82
|
316.04
|
528.12
|
344.33
|
Native Linux | |
| 13 |
202.73
|
207.55
|
294.13
|
87.37
|
Native Linux | |
| 14 |
213.06
|
165.01
|
283.82
|
197.45
|
WSL | |
| 15 |
160.52
|
163.70
|
240.49
|
64.77
|
Native Linux | |
| 16 |
146.10
|
133.08
|
239.43
|
61.68
|
Native Linux | |
| 17 |
158.79
|
157.40
|
231.75
|
72.52
|
WSL | |
| 18 |
76.32
|
37.28
|
122.73
|
112.62
|
Native Linux | |
| 19 |
74.55
|
60.71
|
100.85
|
60.59
|
WSL | |
| 20 |
7.87
|
6.69
|
9.05
|
8.30
|
Native Linux | |
| 21 |
6.35
|
8.52
|
5.78
|
4.19
|
WSL | |
| 22 |
5.20
|
8.58
|
2.69
|
6.32
|
Native Linux | |
| 23 |
0.34
|
0.70
|
0.34
|
0.07
|
WSL | |
| 24 |
0.30
|
0.20
|
0.17
|
1.59
|
WSL |
The Personal Edition submits your benchmark results to TechnoLynx's servers as part of participating in the public leaderboard. If that isn't acceptable for your use case, contact TechnoLynx about Press, Pro, or Enterprise licenses.
LynxBenchAI End-User License Agreement · LynxBenchAI Privacy Policy
Results: 26Q3 · ranked by inference-category score, higher is better. GT (Global Score) is LynxBenchAI's overall crown; this view answers "which hardware leads specifically on inference," not "which hardware wins overall." Bars are scaled to each column's own leader, not a shared ceiling -- compare bars down a column, not across.