llm-benchmarks
githubdrose.io

Mercury 2.5 Preview Benchmarks


Measured on inception

1 runs
Avg Tokens / Second
41.50
Avg Time to First Token (ms)
2270.00
Runs Analysed
1
Last Updated
Sep 1, 2026, 06:49 PM

Throughput distribution

Throughput over time

Mercury 2.5 Previewinception0tok/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 1 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
inceptionMercury 2.5 Preview41.5041.5041.502270.00

Frequently Asked Questions

How fast is Mercury 2.5 Preview?
The latest rolling average throughput is 41.50 tokens per second with an average time to first token of 2270.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 06:49 PM.

Related models