M
Best token generation
551,0 tok/s
MiniMax-M2.5
Best prefill
7.167,2 tok/s
MiniMax-M2.7
∅ Token generation
79,0 tok/s
Average of 141 runs
∅ Prefill
1.512,4 tok/s
Average of 141 runs
Best TTFT
105 ms
MiniMax-M2.7
Best harness rate
81%
MiniMax-M2.5
🏆
MiniMax-M2.5 · fastest model at 551,0 tok/s token generation
Best prefill of this manufacturer: 7.167,2 tok/s (MiniMax-M2.7)
Best prefill of this manufacturer: 7.167,2 tok/s (MiniMax-M2.7)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.