Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Inference Efficiency on 1x H100 96GB GPU (synthetic)

161,312Throughput

SRM

-2,527.5240,007.7482,543125,078.26May 9, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
161,312512,000
2026.05
61,4651,000
2026.05
32,1346,000
2026.05
23,1551,000
2026.05
15,2724,000
2026.05
3,8201,024
2026.05
3,7741,024