FHE Benchmarking Results - ML Inference (Small Batch - 100)

Submitter					Bandwidth			Quality	Timing (harness)									Timing (server)
Name	Date	Env	R/L	Model	Keys	Input	Result	Accuracy	Total	DB Gen	Keygen	Model Prep	Input Gen	Input Prep	Input Enc	Compute	Decrypt	Total	DB Gen	Keygen	Model Prep	Input Gen	Input Prep	Input Enc	Compute	Decrypt	I/O
Lattica-ai	2026‑02‑23 16:49:29	GPU	R	mlp	16.5M	196M	2.5M	0.94	31.52s	7.1059s	1.8748s	200us	2.6519s	1.6481s	5.0716s	3.5294s	2.2439s								615ms
Lattica-ai	2026‑05‑25 08:42:44	GPU	R	mlp	7.3M	98M	1.3M	0.94	27.99s	7.0467s	1.7335s	200us	2.6087s	1.6324s	3.1283s	2.4577s	1.9247s								215.7ms
Reference	2026‑02‑20 03:38:16	CPU	L	mlp	1G	500.3M	100.2M	0.96	11.42m	4.1259s	966.1ms	3.7ms	2.0002s	22.13ms	3.0613s	10.76m	2.5396s	10.55m							10.55m