llm-benchmarks
githubdrose.io

ERNIE-Light-DT-1.0 Benchmarks


Measured on baidu

45 runs
Avg Tokens / Second
28.60
Decode Tokens / Second
—
Avg Time to First Token (ms)
2110.00
Runs Analysed
45
Last Updated
Nov 21, 2026, 04:22 PM

Throughput distribution

Throughput over time

ERNIE-Light-DT-1.0baidu32tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 78 tok/s (99th percentile) · dashed rule is the model's own mean

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
baiduvia OpenRouter28.608.6842.402110.0045

Frequently Asked Questions

How fast is ERNIE-Light-DT-1.0?
The latest rolling average throughput is 28.60 tokens per second with an average time to first token of 2110.00 ms across 45 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 21, 2026, 04:22 PM.

Related models