llm-benchmarks
githubdrose.io

minimax Provider Benchmarks


Measured over the last 30 days

Models Tracked
7
Avg Tokens / Second
15.65
Avg Time to First Token (ms)
8390.00
Last Updated
Oct 17, 2026

All minimax models

7 live · one row per model · fastest first · 2 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
MiniMax M2-her43.2043.2043.201010.00
MiniMax-0125.8025.8025.80780.00
MiniMax M319.006.2231.603100.00
MiniMax M2.16.346.346.349740.00
MiniMax M25.345.345.3411000.00
MiniMax M2.55.312.697.7814500.00
MiniMax M2.74.541.848.9418600.00

Frequently Asked Questions

Which minimax model is fastest?
Based on recent tests, MiniMax M2-her shows the highest average throughput among tracked minimax models.
How many recent measurements feed this dashboard?
This provider summary aggregates 274 individual prompts measured across 274 monitoring runs over the past month.