llm-benchmarks
githubdrose.io

Seed-2.0-pro Benchmarks


Measured on deepinfra

126 runs
deepinfra site
Avg Tokens / Second
2.72
Avg Time to First Token (ms)
0.00
Runs Analysed
126
Last Updated
Aug 12, 2026, 06:55 PM

Throughput distribution

Throughput over time

Seed-2.0-prodeepinfra9tok/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 · shared vertical scale, 0 to 68 tok/s (99th percentile) · dashed rule is the model's own mean

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
deepinfraSeed-2.0-pro2.721.1315.400.00

Frequently Asked Questions

How fast is Seed-2.0-pro?
The latest rolling average throughput is 2.72 tokens per second with an average time to first token of 0.00 ms across 126 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 12, 2026, 06:55 PM.