llm-benchmarks
githubdrose.io

MiMo-V2.6-Flash Benchmarks


Measured on relace

2 runs
Avg Tokens / Second
18.30
Decode Tokens / Second
—
Avg Time to First Token (ms)
2380.00
Runs Analysed
2
Last Updated
Sep 30, 2026, 12:51 AM

Throughput distribution

Throughput over time

MiMo-V2.6-Flashrelace36tok/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 38 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples

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
relacevia OpenRouter18.3016.3020.302380.002

Frequently Asked Questions

How fast is MiMo-V2.6-Flash?
The latest rolling average throughput is 18.30 tokens per second with an average time to first token of 2380.00 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 Sep 30, 2026, 12:51 AM.

Related models