BENCHMARKFirst benchmarks recorded: MiniMax M3 → Cortecs → ?3hBENCHMARKFirst benchmarks recorded: Kimi K3 → Cortecs → ?3hBENCHMARKFirst benchmarks recorded: DeepSeek V4 Pro → Cortecs → ?3hBENCHMARKFirst benchmarks recorded: GLM-4.7 → Cortecs → ?3hBENCHMARKFirst benchmarks recorded: GLM-5.2 → Cortecs → ?3h

Models

Models are inputs to the benchmark — pick one to see who runs it best. 0 models observed across the registry.

Benchmarked models

DEV DATA
ModelFamilyContextProvidersBest providerBest TTFTBest $/M out
Qwen3-235BQwen128k12Fireworks 97.8148 ms$0.31
DeepSeek-V3DeepSeek128k6Fireworks 97.6340 ms$0.39
Llama 3.3 70BLlama128k10Fireworks 97.0110 ms$0.20
GLM-5.2GLM—1Cortecs 94.5525 ms$0.51
GLM-4.7GLM—1Cortecs 93.81311 ms$0.42
DeepSeek V4 ProDeepSeek—1Cortecs 94.0381 ms$0.66
Kimi K3Kimi—1Cortecs 94.31777 ms$0.60
MiniMax M3MiniMax—1Cortecs 93.82253 ms$0.48

Observed across the registry

Live discovery data