llm-benchmarks
githubdrose.io

MiniMax-M2.5 Benchmarks


Measured on deepinfra

3 runs
deepinfra site
Avg Tokens / Second
22.70
Avg Time to First Token (ms)
0.00
Runs Analysed
3
Last Updated
Aug 4, 2026, 02:18 PM

Throughput distribution

  • MiniMax-M2.5 deepinfra23 tok/s
02550

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

MiniMax-M2.5deepinfra1tok/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)
deepinfraMiniMax-M2.522.7019.9027.300.00

Frequently Asked Questions

How fast is MiniMax-M2.5?
The latest rolling average throughput is 22.70 tokens per second with an average time to first token of 0.00 ms across 3 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 4, 2026, 02:18 PM.