llm-benchmarks
githubdrose.io

minimax Provider Benchmarks


Measured over the last 30 days

Models Tracked
13
Avg Tokens / Second
14.00
Avg Time to First Token (ms)
8585.00
Last Updated
Sep 1, 2026

All minimax models

13 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
MiniMax M2-her35.0012.9050.301420.00
MiniMax M2-her34.8020.9040.501360.00
MiniMax-0123.3021.3025.90860.00
MiniMax-0122.5010.5031.001150.00
MiniMax M114.6012.2019.005520.00
MiniMax M114.4012.9016.405160.00
MiniMax M314.409.8017.104360.00
MiniMax M29.745.1916.808060.00
MiniMax M28.445.7313.209010.00
MiniMax M2.56.972.5516.3014500.00
MiniMax M2.15.782.5912.7015100.00
MiniMax M2.75.411.5915.2015100.00
MiniMax M2.74.722.398.7416500.00

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 556 individual prompts measured across 502 monitoring runs over the past month.