llm-benchmarks
githubdrose.io

MiMo-V2.5 Benchmarks


Measured on venice

2 runs
Avg Tokens / Second
15.40
Decode Tokens / Second
—
Avg Time to First Token (ms)
2750.00
Runs Analysed
2
Last Updated
Nov 10, 2026, 07:32 PM

Throughput distribution

Throughput over time

MiMo-V2.5venice27tok/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 36 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples

Every lane measuring this model

2 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
venicevia OpenRouter15.4010.4020.502750.002
venicedirect14.2014.2014.203400.001

Frequently Asked Questions

How fast is MiMo-V2.5?
The latest rolling average throughput is 15.40 tokens per second with an average time to first token of 2750.00 ms across 2 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 10, 2026, 07:32 PM.

Related models