BENCHMARKFirst benchmarks recorded: MiniMax M3 → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: Kimi K3 → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: DeepSeek V4 Pro → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: GLM-4.7 → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: GLM-5.2 → Cortecs → ?4h

Kimi K3

1 providers · MoE · — context · 1 regions · all models →

Kimi K3 across 1 providers

Same model. Different infrastructure. DEV DATA
TTFT spread1.0×Throughput spread1.0×Output price1.0×Tool reliability0.0 pts
TTFT1777 ms1777 msbest: Cortecs
Throughput191 tok/s191 tok/sbest: Cortecs
Output price$0.60/M$0.60/Mbest: Cortecs
Reliability41.9%41.9%best: Cortecs
Tool success85.7%85.7%best: Cortecs

Kimi K3 — tool-calling benchmark

1 providers · 85.7% → 85.7% · 0.0 pt spread · DEV DATA
#ProviderToolsΔ bestRel.JSONTTFTP95Tok/s$ Out
01Cortecs85.7%—41.9%100.0%1777 ms2769 ms191$0.60